Refereed Conferences and Journals

2024
  • Benchmarking Zero-Shot Recognition with Vision-Language Models: Challenges on Granularity and Specificity

    Zhenlin Xu, Yi Zhu, Siqi Deng, Abhay Mittal, Yanbei Chen, Manchen Wang, Paolo Favaro, Joseph Tighe, Davide Modolo, in the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024.

    PDF 
    @InProceedings{Xu_2024_CVPR,
    author    = {Xu, Zhenlin and Zhu, Yi and Deng, Siqi and Mittal, Abhay and Chen, Yanbei and Wang, Manchen and Favaro, Paolo and Tighe, Joseph and Modolo, Davide},
    title     = {Benchmarking Zero-Shot Recognition with Vision-Language Models: Challenges on Granularity and Specificity},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
    month     = {June},
    year      = {2024},
    pages     = {1827-1836}
}
  • Denoising and Selecting Pseudo-Heatmaps for Semi-Supervised Human Pose Estimation

    Zhuoran Yu, Manchen Wang, Yanbei Chen, Paolo Favaro, Davide Modolo, in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024.

    PDF 
    @InProceedings{Yu_2024_WACV,
    author    = {Yu, Zhuoran and Wang, Manchen and Chen, Yanbei and Favaro, Paolo and Modolo, Davide},
    title     = {Denoising and Selecting Pseudo-Heatmaps for Semi-Supervised Human Pose Estimation},
    booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
    month     = {January},
    year      = {2024},
    pages     = {6280-6289}
}
  • Masked and Shuffled Blind Spot Denoising for Real-World Images

    Hamadi Chihaoui and Paolo Favaro, in the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

    PDF arXiv Project 
    @misc{chihaoui2024masked,
      title={Masked and Shuffled Blind Spot Denoising for Real-World Images}, 
      author={Hamadi Chihaoui and Paolo Favaro},
      year={2024},
      eprint={2404.09389},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}
  • SemiGPC: Distribution-Aware Label Refinement for Imbalanced Semi-Supervised Learning Using Gaussian Processes

    Abdelhak Lemkhenter, Manchen Wang, Luca Zancato, Gurumurthy Swaminathan, Paolo Favaro and Davide Modolo, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2576-2585, 2024.

    PDF arXiv 
    @inproceedings{lemkhenter2024semigpc,
  title={SemiGPC: Distribution-Aware Label Refinement for Imbalanced Semi-Supervised Learning Using Gaussian Processes},
  author={Lemkhenter, Abdelhak and Wang, Manchen and Zancato, Luca and Swaminathan, Gurumurthy and Favaro, Paolo and Modolo, Davide},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={2576--2585},
  year={2024}
}
  • Sparse 3D Reconstruction via Object-Centric Ray Sampling

    Llukman Cerkezi and Paolo Favaro, in International Conference on 3D Vision (3DV), 2024.

    PDF arXiv 
    @misc{cerkezi2023sparse,
      title={Sparse 3D Reconstruction via Object-Centric Ray Sampling}, 
      author={Llukman Cerkezi and Paolo Favaro},
      year={2023},
      eprint={2309.03008},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}
  • Learn the Force We Can: Enabling Sparse Motion Control in Multi-Object Video Generation

    Aram Davtyan and Paolo Favaro, in AAAI Conference on Artificial Intelligence, 2024.

    PDF arXiv Project 
    @misc{davtyan2023learn,
      title={Learn the Force We Can: Multi-Object Video Generation from Pixel-Level Interactions}, 
      author={Aram Davtyan and Paolo Favaro},
      year={2023},
      eprint={2306.03988},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}
  • Fast light-field 3D microscopy with out-of-distribution detection and adaptation through conditional normalizing flows

    Josué Page Vizcaíno, Panagiotis Symvoulidis, Zeguan Wang, Jonas Jelten, Paolo Favaro, Edward S. Boyden, and Tobias Lasser, in Biomedical Optics Express, vol. 15, no. 2, pp. 1219-1232, 2024.

    PDF 
    @article{PageVizcaino:24,
author = {Josu\'{e} Page Vizca\'{i}no and Panagiotis Symvoulidis and Zeguan Wang and Jonas Jelten and Paolo Favaro and Edward S. Boyden and Tobias Lasser},
journal = {Biomed. Opt. Express},
keywords = {Biomedical imaging; Imaging systems; Single pixel imaging; Spatial resolution; Three dimensional microscopy; Three dimensional reconstruction},
number = {2},
pages = {1219--1232},
publisher = {Optica Publishing Group},
title = {Fast light-field 3D microscopy with out-of-distribution detection and adaptation through conditional normalizing flows},
volume = {15},
month = {Feb},
year = {2024},
url = {https://opg.optica.org/boe/abstract.cfm?URI=boe-15-2-1219},
doi = {10.1364/BOE.504039},
}
2023
  • Spatio-Temporal Crop Aggregation for Video Representation Learning

    Sepehr Sameni, Simon Jenni and Paolo Favaro, in International Conference on Computer Vision (ICCV), 2023.

    PDF arXiv 
    @InProceedings{Sameni_2023_ICCV,
    author    = {Sameni, Sepehr and Jenni, Simon and Favaro, Paolo},
    title     = {Spatio-Temporal Crop Aggregation for Video Representation Learning},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2023},
    pages     = {5664-5674}
}
  • Efficient Video Prediction via Sparsely Conditioned Flow Matching

    Aram Davtyan*, Sepehr Sameni* and Paolo Favaro, in International Conference on Computer Vision (ICCV), 2023.

    PDF arXiv Project Poster 
    @InProceedings{Davtyan_2023_ICCV,
    author    = {Davtyan, Aram and Sameni, Sepehr and Favaro, Paolo},
    title     = {Efficient Video Prediction via Sparsely Conditioned Flow Matching},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2023},
    pages     = {23263-23274}
}
  • ScaleDet: A scalable multi-dataset object detector

    Yanbei Chen, Manchen Wang, Abhay Mittal, Zhenlin Xu, Paolo Favaro, Joe Tighe, Davide Modolo, in the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.

    PDF 
    @Inproceedings{Chen2023,
 author = {Yanbei Chen and Manchen Wang and Abhay Mittal and Zhenlin Xu and Paolo Favaro and Joe Tighe and Davide Modolo},
 title = {ScaleDet: A scalable multi-dataset object detector},
 year = {2023},
 url = {https://www.amazon.science/publications/scaledet-a-scalable-multi-dataset-object-detector},
 booktitle = {CVPR 2023},
}
  • A Meta-Learning Approach to Predicting Performance and Data Requirements

    Achin Jain, Gurumurthy Swaminathan, Paolo Favaro, Hao Yang, Avinash Ravichandran, Hrayr Harutyunyan, Alessandro Achille, Onkar Dabeer, Bernt Schiele, Ashwin Swaminathan, Stefano Soatto, in the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.

    PDF arXiv 
    @Inproceedings{Jain2023,
 author = {Achin Jain and Gurumurthy Swaminathan and Paolo Favaro and Hao Yang and Avinash Ravichandran and Hrayr Harutyunyan and Alessandro Achille and Onkar Dabeer and Bernt Schiele and Ashwin Swaminathan and Stefano Soatto},
 title = {A meta-learning approach to predicting performance and data requirements},
 year = {2023},
 url = {https://www.amazon.science/publications/a-meta-learning-approach-to-predicting-performance-and-data-requirements},
 booktitle = {CVPR 2023},
}
  • Representation Learning by Detecting Incorrect Location Embeddings

    Sepehr Sameni, Simon Jenni and Paolo Favaro, in AAAI Conference on Artificial Intelligence, 2023.

    PDF 
    @article{Sameni_Jenni_Favaro_2023, 
    title={Representation Learning by Detecting Incorrect Location Embeddings}, 
    volume={37}, 
    url={https://ojs.aaai.org/index.php/AAAI/article/view/26160}, 
    DOI={10.1609/aaai.v37i8.26160}, 
    number={8},
    journal={Proceedings of the AAAI Conference on Artificial Intelligence}, 
    author={Sameni, Sepehr and Jenni, Simon and Favaro, Paolo},
    year={2023}, 
    month={Jun.}, 
    pages={9704-9713}
}
  • Multi-Scored Sleep Databases: How to Exploit the Multiple-Labels in Automated Sleep Scoring

    Luigi Fiorillo, Davide Pedroncelli, Valentina Agostini, Paolo Favaro and Francesca Dalia Faraci, in Sleep Journal, 2023.

    PDF arXiv 
    @article{10.1093/sleep/zsad028,
    author = {Fiorillo, Luigi and Pedroncelli, Davide and Agostini, Valentina and Favaro, Paolo and Faraci, Francesca Dalia},
    title = "{Multi-Scored Sleep Databases: How to Exploit the Multiple-Labels in Automated Sleep Scoring}",
    journal = {Sleep},
    year = {2023},
    month = {02},
    issn = {0161-8105},
    doi = {10.1093/sleep/zsad028},
    url = {https://doi.org/10.1093/sleep/zsad028},
    note = {zsad028},
    eprint = {https://academic.oup.com/sleep/advance-article-pdf/doi/10.1093/sleep/zsad028/49156616/zsad028.pdf},
}
  • U-Sleep: resilient to AASM guidelines

    Luigi Fiorillo, Giuliana Monachino, Julia van der Meer, Marco Pesce, Jan Warncke, Markus H. Schmidt, Claudio L.A. Bassetti, Athina Tzovara, Paolo Favaro and Francesca D. Faraci, in npj Digital Medicine, vol. 6, no. 33, 2023.

    PDF arXiv 
    TY  - JOUR
AU  - Fiorillo, Luigi
AU  - Monachino, Giuliana
AU  - van der Meer, Julia
AU  - Pesce, Marco
AU  - Warncke, Jan D.
AU  - Schmidt, Markus H.
AU  - Bassetti, Claudio L. A.
AU  - Tzovara, Athina
AU  - Favaro, Paolo
AU  - Faraci, Francesca D.
PY  - 2023
DA  - 2023/03/06
TI  - U-Sleep’s resilience to AASM guidelines
JO  - npj Digital Medicine
SP  - 33
VL  - 6
IS  - 1
AB  - AASM guidelines are the result of decades of efforts aiming at standardizing sleep scoring procedure, with the final goal of sharing a worldwide common methodology. The guidelines cover several aspects from the technical/digital specifications, e.g., recommended EEG derivations, to detailed sleep scoring rules accordingly to age. Automated sleep scoring systems have always largely exploited the standards as fundamental guidelines. In this context, deep learning has demonstrated better performance compared to classical machine learning. Our present work shows that a deep learning-based sleep scoring algorithm may not need to fully exploit the clinical knowledge or to strictly adhere to the AASM guidelines. Specifically, we demonstrate that U-Sleep, a state-of-the-art sleep scoring algorithm, can be strong enough to solve the scoring task even using clinically non-recommended or non-conventional derivations, and with no need to exploit information about the chronological age of the subjects. We finally strengthen a well-known finding that using data from multiple data centers always results in a better performing model compared with training on a single cohort. Indeed, we show that this latter statement is still valid even by increasing the size and the heterogeneity of the single data cohort. In all our experiments we used 28528 polysomnography studies from 13 different clinical studies.
SN  - 2398-6352
UR  - https://doi.org/10.1038/s41746-023-00784-0
DO  - 10.1038/s41746-023-00784-0
ID  - Fiorillo2023
ER  -
2022
  • Semi-supervised Vision Transformers at Scale

    Zhaowei Cai, Avinash Ravichandran, Paolo Favaro, Manchen Wang, Davide Modolo, Rahul Bhotika, Zhuowen Tu and Stefano Soatto, in 36th Conference on Neural Information Processing Systems (NeurIPS), 2022.

    PDF 
    @inproceedings{
cai2022,
title={Semi-supervised Vision Transformers at Scale},
author={Zhaowei Cai, Avinash Ravichandran, Paolo Favaro, Manchen Wang,
Davide Modolo, Rahul Bhotika, Zhuowen Tu and Stefano Soatto},
booktitle={Thirty-Sixth Conference on Neural Information Processing Systems},
year={2022},
url={https://openreview.net/forum?id=7a2IgJ7V4W}
}
  • MOVE: Unsupervised Movable Object Segmentation and Detection

    Adam Bielski and Paolo Favaro, in 36th Conference on Neural Information Processing Systems (NeurIPS 2022), 2022.

    PDF arXiv 
    @inproceedings{NEURIPS2022_d7eb232f,
 author = {Bielski, Adam and Favaro, Paolo},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {S. Koyejo and S. Mohamed and A. Agarwal and D. Belgrave and K. Cho and A. Oh},
 pages = {33371--33386},
 publisher = {Curran Associates, Inc.},
 title = {MOVE: Unsupervised Movable Object Segmentation and Detection},
 url = {https://proceedings.neurips.cc/paper_files/paper/2022/file/d7eb232f196124894f2e65b9010a5c57-Paper-Conference.pdf},
 volume = {35},
 year = {2022}
}
  • Towards Sleep Scoring Generalization Through Self-Supervised Meta-Learning

    Abdelhak Lemkhenter and Paolo Favaro, in 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), pp. 2961-2966, 2022.

    PDF arXiv 
    @INPROCEEDINGS{9871056, 
author={Lemkhenter, Abdelhak and Favaro, Paolo}, 
booktitle={2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)}, 
title={Towards Sleep Scoring Generalization Through Self-Supervised Meta-Learning},
year={2022}, 
volume={},  
number={},  
pages={2961-2966},  
doi={10.1109/EMBC48229.2022.9871056}}
  • Controllable Video Generation through Global and Local Motion Dynamics

    Aram Davtyan and Paolo Favaro, in European Conference on Computer Vision (ECCV), 2022.

    PDF arXiv Project Video Poster 
    @InProceedings{10.1007/978-3-031-19790-1_5,
author="Davtyan, Aram
and Favaro, Paolo",
editor="Avidan, Shai
and Brostow, Gabriel
and Ciss{\'e}, Moustapha
and Farinella, Giovanni Maria
and Hassner, Tal",
title="Controllable Video Generation Through Global and Local Motion Dynamics",
booktitle="Computer Vision -- ECCV 2022",
year="2022",
publisher="Springer Nature Switzerland",
address="Cham",
pages="68--84",
isbn="978-3-031-19790-1"
}
  • Learn to Zoom in Single Image Super-resolution

    Zili Zhang, Paolo Favaro, Yan Tian and Jianxiang Li, in IEEE Signal Processing Letters, 2022.

    PDF Project 
    @ARTICLE{9774911,
  author={Zhang, Zili and Favaro, Paolo and Tian, Yan and Li, Jianxiang},
  journal={IEEE Signal Processing Letters}, 
  title={Learn to Zoom in Single Image Super-resolution}, 
  year={2022},
  volume={},
  number={},
  pages={1-1},
  doi={10.1109/LSP.2022.3175126}}
  • KOALA: A Kalman Optimization Algorithm with Loss Adaptivity

    Aram Davtyan, Sepehr Sameni, Llukman Cerkezi, Givi Meishvili, Adam Bielski and Paolo Favaro, in AAAI Conference on Artificial Intelligence, 2022.

    PDF arXiv Project Poster 
    @article{Davtyan_Sameni_Cerkezi_Meishvili_Bielski_Favaro_2022,
    title={KOALA: A Kalman Optimization Algorithm with Loss Adaptivity},
    volume={36},
    url={https://ojs.aaai.org/index.php/AAAI/article/view/20599},
    DOI={10.1609/aaai.v36i6.20599},
    number={6},
    journal={Proceedings of the AAAI Conference on Artificial Intelligence},
    author={Davtyan, Aram and Sameni, Sepehr and Cerkezi, Llukman and Meishvili, Givi and Bielski, Adam and Favaro, Paolo},
    year={2022},
    month={Jun.},
    pages={6471-6479} 
}
2021
  • Learning to Deblur and Rotate Motion-Blurred Faces

    Givi Meishvili, Attila Szabo, Simon Jenni and Paolo Favaro, in British Machine Vision Conference (BMVC), 2021.

    Paper Supplement
    Project 
    inproceedings{meishvili2021deblur,
  title={Learning to Deblur and Rotate Motion-Blurred Faces},
  author={Meishvili, Givi and Szabo, Attila and Jenni, Simon and Favaro, Paolo},
  booktitle={BMVC},
  year={2021}
}
  • DeepSleepNet-Lite: A Simplified Automatic Sleep Stage Scoring Model with Uncertainty Estimates

    Luigi Fiorillo, Paolo Favaro and Francesca Dalia Faraci, in IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2021.

    PDF arXiv 
    @ARTICLE{9570807,
  author={Fiorillo, Luigi and Favaro, Paolo and Faraci, Francesca Dalia},
  journal={IEEE Transactions on Neural Systems and Rehabilitation Engineering},
  title={DeepSleepNet-Lite: A Simplified Automatic Sleep Stage Scoring Model with Uncertainty Estimates},
  year={2021},
  volume={},
  number={},
  pages={1-1},
  doi={10.1109/TNSRE.2021.3117970}}
  • ISD: Self-Supervised Learning by Iterative Similarity Distillation

    Ajinkya Tejankar*, Soroush Abbasi Koohpayegani*, Vipin Pillai, Paolo Favaro, Hamed Pirsiavash, in International Conference on Computer Vision (ICCV), 2021.

    PDF Project 
    inproceedings{tejankar2021isd,
  title={ISD: Self-Supervised Learning by Iterative Similarity Distillation},
  author={Tejankar, Ajinkya and Koohpayegani, Soroush Abbasi and Pillai, Vipin and Favaro, Paolo and Pirsiavash, Hamed},
  booktitle={ICCV},
  year={2021}
}
  • Learning to Reconstruct Confocal Microscopy Stacks from Single Light Field Images

    Josué Page Vizcaíno, Federico Saltarin, Yury Belyaev, Ruth Lyck, Tobias Lasser, and Paolo Favaro, in IEEE Transactions on Computational Imaging, 2021.

    Paper Supplement 
    author={Vizcaíno, Josué Page and Saltarin, Federico and Belyaev, Yury and Lyck, Ruth and Lasser, Tobias and Favaro, Paolo},
  journal={IEEE Transactions on Computational Imaging}, 
  title={Learning to Reconstruct Confocal Microscopy Stacks From Single Light Field Images}, 
  year={2021},
  volume={7},
  number={},
  pages={775-788},
  doi={10.1109/TCI.2021.3097611}}
  • A Unified Generative Adversarial Network Training via Self-Labeling and Self-Attention

    Tomoki Watanabe and Paolo Favaro, in International Conference on Machine Learning (ICML), 2021.

    PDF arXiv 
    @inproceedings{watanabeICML2021,
    author = {Watanabe, Tomoki and Favaro, Paolo},
    booktitle = {International Conference on Machine Learning ({ICML})},
    title = {A Unified Generative Adversarial Network Training via Self-Labeling and Self-Attention},
    year = {2021}
}
  • Real-Time Light Field 3D Microscopy via Sparsity-Driven Learned Deconvolution

    Josue Page Vizcaino, Zeguan Wang, Panagiotis Symvoulidis, Paolo Favaro, Burcu Guner-Ataman, Edward S. Boyden, and Tobias Lasser, in International Conference on Computational Photography (ICCP), 2021.

    PDF Project Video 
    @INPROCEEDINGS{pageXLFMNet2021,
	    author = {Page~Vizcaino, Josue and Wang, Zeguan and Symvoulidis, Panagiotis and Favaro, Paolo and Guner-Ataman, Burcu and Boyden, Edward~S. and Lasser, Tobias},
	    title = {Real-Time Light Field 3D Microscopy via Sparsity-Driven Learned Deconvolution},
	     booktitle={2021 IEEE International Conference on Computational Photography (ICCP)}, 
	    year = {2021}
}
  • Optical Flow Dataset Synthesis from Unpaired Images

    Adrian Wälchli and Paolo Favaro, 2021. Technical report.

    PDF arXiv 
    @article{walchli2021optical,
  title={Optical Flow Dataset Synthesis from Unpaired Images},
  author={W{\"a}lchli, Adrian and Favaro, Paolo},
  journal={arXiv preprint arXiv:2104.02615},
  year={2021}
}
2020
  • Self-Supervised Multi-View Synchronization Learning for 3D Pose Estimation

    Simon Jenni and Paolo Favaro, in Asian Conference on Computer Vision (ACCV), 2020.

    PDF arXiv Project 
    @inproceedings{jenniACCV2020,
    author = {Jenni, Simon and Favaro, Paolo},
    booktitle = {Asian Conference on Computer Vision ({ACCV})},
    title = {Self-Supervised Multi-View Synchronization Learning for 3D Pose Estimation},
    year = {2020}
}
  • Boosting Generalization in Bio-Signal Classification by Learning the Phase-Amplitude Coupling

    Abdelhak Lemkhenter and Paolo Favaro, in German Conference on Pattern Recognition (GCPR), 2020.

    PDF arXiv 
    @inproceedings{lemkhenterGCPR2020,
    author = {Lemkhenter, Abdelhak and Favaro, Paolo},
    booktitle = {German Conference on Pattern Recognition ({GCPR})},
    title = {Boosting Generalization in Bio-Signal Classification by Learning the Phase-Amplitude Coupling},
    year = {2020}
}
  • Video Representation Learning by Recognizing Temporal Transformations

    S. Jenni, G. Meishvili, and P. Favaro, in European Conference on Computer Vision (ECCV), 2020.

    PDF arXiv Project 
    @inproceedings{jenniECCV2020,
    author = {Jenni, Simon and Meishvili, Givi and Favaro, Paolo},
    booktitle = {European Conference on Computer Vision ({ECCV})},
    title = {Video Representation Learning by Recognizing Temporal Transformations},
    year = {2020}
}
  • Learning to Take Directions One Step at a Time

    Q. Hu, A. Wälchli, T. Portenier, M. Zwicker and P. Favaro, in International Conference on Pattern Recognition (ICPR), 2020.

    Paper Supplement
    arXiv Project Video Poster 
    @inproceedings{hu2020directions,
    author = {Hu, Qiyang and W\"alchli, Adrian and Portenier, Tiziano and Zwicker, Matthias and Favaro, Paolo},
    booktitle = {Proceedings of the International Conference on Pattern Recognition ({ICPR})},
    title = {Learning to Take Directions One Step at a Time},
    year = {2020}
}
  • Learning to Model and Calibrate Optics via a Differentiable Wave Optics Simulator

    Josue Page and Paolo Favaro, in IEEE International Conference on Image Processing (ICIP), 2020.

    PDF arXiv Project Video 
    @inproceedings{PageICIP2020,
    author = {Page, Josue and Favaro, Paolo},
    booktitle = {IEEE International Conference on Image Processing (ICIP)},
    title = {{L}earning to {M}odel and {C}alibrate {O}ptics via a {D}ifferentiable {W}ave {O}ptics {S}imulator},
    year = {2020}
}
  • Learning to Have an Ear for Face Super-Resolution

    G. Meishvili, S. Jenni and P. Favaro, in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.

    PDF Project 
    @inproceedings{meishvili2019ear,
    author = {Meishvili, Givi and Jenni, Simon and Favaro, Paolo},
    booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})},
    title = {Learning to Have an Ear for Face Super-Resolution},
    year = {2020}
}
  • Steering Self-Supervised Feature Learning Beyond Local Pixel Statistics

    S. Jenni, H. Jin and P. Favaro, in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.

    PDF Project 
    @inproceedings{jenni2020steering,
    author = {Jenni, Simon and Jin, Hailin and Favaro, Paolo},
    booktitle = {Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})},
    title = {Steering Self-Supervised Feature Learning Beyond Local Pixel Statistics},
    year = {2020}
}
  • Learning to Reconstruct Confocal Microscope Stacks from Single Light Field Images

    J. Page, F. Saltarin, Y. Belyaev, R. Lyck and P. Favaro, 2020. Under review (available as Technical Report).

    PDF arXiv Project 
    @misc{pageLFMNet2020,
    author = {Page, Josue and Saltarin, Federico and Belyaev, Yury and Lyck, Ruth and Favaro, Paolo},
    booktitle = {arXiv},
    eprint = {2003.11004},
    title = {Learning to Reconstruct Confocal Microscope Stacks from Single Light Field Images},
    year = {2020}
}
  • Temporal dependency in automatic sleep scoring via deep learning based architectures: An empirical study

    Luigi Fiorillo, Michael Wand, Italo Marino, Paolo Favaro, Francesca Dalia Faraci, in 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2020. 

    @inproceedings{FiorilloWMFDF2020,
    author = {Fiorillo, Luigi and Wand, Michael and Marino, Italo and Favaro, Paolo and Dalia Faraci, Francesca},
    booktitle = {42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)},
    title = {{T}emporal dependency in automatic sleep scoring via deep learning based architectures: {A}n empirical study},
    year = {2020}
}
2019
  • Unsupervised Generative 3D Shape Learning from Natural Images

    A. Szabó, G. Meishvili and P. Favaro, 2019. Technical Report.

    PDF arXiv Project 
    @article{szabo2019unsupervised,
  title = {Unsupervised Generative 3D Shape Learning from Natural Images},
  author = {Szab{\'o}, Attila and Meishvili, Givi and Favaro, Paolo},
  journal = {arXiv preprint arXiv:1910.00287},
  year = {2019}
}
  • Emergence of Object Segmentation in Perturbed Generative Models

    Adam Bielski and Paolo Favaro, in Neural Information Processing Systems (NeurIPS), 2019.

    PDF arXiv Project Poster 
    @incollection{bielski2019emergence,
title = {Emergence of Object Segmentation in Perturbed Generative Models},
author = {Bielski, Adam and Favaro, Paolo},
booktitle = {Advances in Neural Information Processing Systems 32},
editor = {H. Wallach and H. Larochelle and A. Beygelzimer and F. d\textquotesingle Alch\'{e}-Buc and E. Fox and R. Garnett},
pages = {7254--7264},
year = {2019},
publisher = {Curran Associates, Inc.},
url = {http://papers.nips.cc/paper/8946-emergence-of-object-segmentation-in-perturbed-generative-models.pdf}
}
  • EEG-based Outcome Prediction after Cardiac Arrest with Convolutional Neural Networks: Performance and Visualization of Discriminative Features

    S. Jonas, A. Rossetti, M. Oddo, S. Jenni, P. Favaro and F. Zubler, in Human Brain Mapping, 2019.

    PDF 
    @misc{jonas_rossetti_oddo_jenni_favaro_zubler_2019, 
    title={EEG‐based outcome prediction after cardiac arrest with convolutional neural networks: Performance and visualization of discriminative features - Jonas - - Human Brain Mapping - Wiley Online Library}, 
    url={https://onlinelibrary.wiley.com/doi/abs/10.1002/hbm.24724}, 
    journal={Human Brain Mapping}, 
    publisher={John Wiley & Sons, Ltd}, 
    author={Jonas, Stefan and Rossetti, Andrea O. and Oddo, Mauro and Jenni, Simon and Favaro, Paolo and Zubler, Frederic}, 
    year={2019}, 
    month={Jul}
}
  • Learning to Extract Flawless Slow Motion from Blurry Videos

    M. Jin, Z. Hu and P. Favaro, in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.

    PDF Project 
    @inproceedings{Jin_2019_CVPR,
    author = {Jin, Meiguang and Hu, Zhe and Favaro, Paolo},
    title = {Learning to Extract Flawless Slow Motion from Blurry Videos},
    booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    month = {June},
    year = {2019}
}
  • On Stabilizing Generative Adversarial Training with Noise

    Simon Jenni and Paolo Favaro, in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.

    PDF arXiv Project Poster 
    @inproceedings{Jenni_2019_CVPR,
    author = {Jenni, Simon and Favaro, Paolo},
    title = {On Stabilizing Generative Adversarial Training With Noise},
    booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    month = {June},
    year = {2019}
}
  • Automated sleep scoring: A review of the latest approaches

    L. Fiorillo, A. Puiatti, M. Papandrea, P. L. Ratti, P. Favaro, C. Roth, P. Bargiotas, C. Bassetti, F. D. Faraci, in Sleep Medicine Reviews, 2019.

    PDF 
    @article{fiorillo2019automated,
    author = {Fiorillo, Luigi and Puiatti, Alessandro and Papandrea, Michela and Ratti, Pietro Luca and Favaro, Paolo and Roth, Corinne and Bargiotas, Panagiotis and Bassetti, Claudio and Faraci, Francesca D},
    journal = {Sleep Medicine Reviews},
    publisher = {Elsevier},
    title = {{A}utomated sleep scoring: {A} review of the latest approaches},
    year = {2019}
}
2018
  • Video Synthesis from a Single Image and Motion Stroke

    Q. Hu, A. Wälchli, T. Portenier, M. Zwicker and P. Favaro, 2018. Technical Report.

    PDF arXiv 
    @article{hu2018video,
    author = {Hu, Qiyang and W{\"a}lchli, Adrian and Portenier, Tiziano and Zwicker, Matthias and Favaro, Paolo},
    journal = {arXiv preprint arXiv:1812.01874},
    title = {Video synthesis from a single image and motion stroke},
    year = {2018}
}
  • Motion Deblurring of Faces

    G. G. Chrysos, P. Favaro and S. Zafeiriou, in International Journal of Computer Vision, 2018.

    PDF 
    @article{chrysos2018motion,
  title={Motion deblurring of faces},
  author={Chrysos, Grigorios G and Favaro, Paolo and Zafeiriou, Stefanos},
  journal={International Journal of Computer Vision},
  pages={1--23},
  year={2018},
  publisher={Springer}
}
  • Normalized Blind Deconvolution

    M. Jin, S. Roth, P. Favaro, in European Conference on Computer Vision (ECCV), 2018.

    PDF Project 
    @inproceedings{jin2018normalized,
  title={Normalized Blind Deconvolution},
  author={Jin, Meiguang and Roth, Stefan and Favaro, Paolo},
  booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
  pages={668--684},
  year={2018}
}
  • Understanding Degeneracies and Ambiguities in Attribute Transfer

    A. Szabó, Q. Hu, T. Portenier, M. Zwicker, P. Favaro, in European Conference on Computer Vision (ECCV), pp. 700-714, 2018.

    PDF Poster 
    @inproceedings{szabo2018understanding,
  title={Understanding Degeneracies and Ambiguities in Attribute Transfer},
  author={Szabo, Attila and Hu, Qiyang and Portenier, Tiziano and Zwicker, Matthias and Favaro, Paolo},
  booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
  pages={700--714},
  year={2018}
}
  • Deep Bilevel Learning

    S. Jenni and P. Favaro, in European Conference on Computer Vision (ECCV), pp. 618-633, 2018.

    PDF arXiv Project 
    @inproceedings{jenni2018deep,
  title={Deep Bilevel Learning},
  author={Jenni, Simon and Favaro, Paolo},
  booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
  pages={618--633},
  year={2018}
}
  • Self-Supervised Feature Learning by Learning to Spot Artifacts

    S. Jenni, and P. Favaro, in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.

    PDF arXiv Project Poster 
    @inproceedings{jenni2018self,
  title={Self-supervised feature learning by learning to spot artifacts},
  author={Jenni, Simon and Favaro, Paolo},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={2733--2742},
  year={2018}
}
  • Boosting Self-Supervised Learning via Knowledge Transfer

    M. Noroozi, A. Vinjimoor, P. Favaro and H. Pirsiavash, in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.

    PDF arXiv Project 
    @inproceedings{noroozi2018boosting,
  title={Boosting self-supervised learning via knowledge transfer},
  author={Noroozi, Mehdi and Vinjimoor, Ananth and Favaro, Paolo and Pirsiavash, Hamed},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={9359--9367},
  year={2018}
}
  • Disentangling Factors of Variation by Mixing Them

    Q. Hu, A. Szabó, T. Portenier, M. Zwicker and P. Favaro, in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.

    PDF Project 
    @inproceedings{hu2018disentangling,
  title={Disentangling factors of variation by mixing them},
  author={Hu, Qiyang and Szab{\'o}, Attila and Portenier, Tiziano and Favaro, Paolo and Zwicker, Matthias},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={3399--3407},
  year={2018}
}
  • Fine-Grained Retrieval with Autoencoders

    T. Portenier, Q. Hu, M. Zwicker and P. Favaro, in Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, vol. 5, pp. 85-95, 2018.

    PDF 
    @inproceedings{portenier2018fine,
  title={Fine-Grained Retrieval with Autoencoders.},
  author={Portenier, Tiziano and Hu, Qiyang and Favaro, Paolo and Zwicker, Matthias},
  booktitle={VISIGRAPP (5: VISAPP)},
  pages={85--95},
  year={2018}
}
  • Learning to Extract a Video Sequence from a Single Motion-Blurred Image

    M. Jin, G. Meishvili, and P. Favaro, in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.

    Paper Supplement
    arXiv Project Video 
    @inproceedings{jin2018learning,
  title={Learning to extract a video sequence from a single motion-blurred image},
  author={Jin, Meiguang and Meishvili, Givi and Favaro, Paolo},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={6334--6342},
  year={2018}
}
  • FaceShop: Deep Sketch-based Image Editing

    T. Portenier, Q. Hu, A. Szabó, S. Bigdeli, P. Favaro, M. Zwicker, in SIGGRAPH, 2018.

    PDF arXiv Project 
    @article{portenier2018faceshop,
  title={Faceshop: Deep sketch-based face image editing},
  author={Portenier, Tiziano and Hu, Qiyang and Szabo, Attila and Bigdeli, Siavash Arjomand and Favaro, Paolo and Zwicker, Matthias},
  journal={ACM Transactions on Graphics (TOG)},
  volume={37},
  number={4},
  pages={99},
  year={2018},
  publisher={ACM}
}
  • Challenges in Disentangling Independent Factors of Variation

    A. Szabó, Q. Hu, T. Portenier, M. Zwicker, P. Favaro, in International Conference on Learning Representations (ICLR workshop — poster only), 2018.

    PDF arXiv 
    @article{szabo2017challenges,
  title={Challenges in disentangling independent factors of variation},
  author={Szab{\'o}, Attila and Hu, Qiyang and Portenier, Tiziano and Zwicker, Matthias and Favaro, Paolo},
  journal={arXiv preprint arXiv:1711.02245},
  year={2017}
}
  • Learning Face Deblurring Fast and Wide

    M. Jin, M. Hirsch and P. Favaro, in Proc. of New Trends in Image Restoration and Enhancement workshop, 2018.

    PDF Project 
    @inproceedings{jin2018learning,
  title={Learning face deblurring fast and wide},
  author={Jin, Meiguang and Hirsch, Michael and Favaro, Paolo},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops},
  pages={745--753},
  year={2018}
}
  • Learning to See through Reflections

    M. Jin, S. Süsstrunk and P. Favaro, in Proc. of International Conference on Computational Photography (ICCP), 2018. (oral)

    PDF Project 
    @inproceedings{jin2018learning,
  title={Learning to see through reflections},
  author={Jin, Meiguang and S{\"u}sstrunk, Sabine and Favaro, Paolo},
  booktitle={2018 IEEE International Conference on Computational Photography (ICCP)},
  pages={1--12},
  year={2018},
  organization={IEEE}
}
  • Plenoptic Image Motion Deblurring

    P. Chandramouli, M. Jin, D. Perrone and P. Favaro, in IEEE Transactions on Image Processing, 2018.

    PDF Project 
    @article{chandramouli2018plenoptic,
  title={Plenoptic Image Motion Deblurring},
  author={Chandramouli, Paramanand and Jin, Meiguang and Perrone, Daniele and Favaro, Paolo},
  journal={IEEE Transactions on Image Processing},
  volume={27},
  number={4},
  pages={1723--1734},
  year={2018},
  publisher={IEEE}
}
2017
  • Deep Mean-Shift Priors for Image Restoration

    S. A. Bigdeli, M. Jin, P. Favaro and M. Zwicker, in Neural Information Processing Systems (NIPS), 2017.

    PDF arXiv 
    @inproceedings{bigdeli2017deep,
  title={Deep mean-shift priors for image restoration},
  author={Bigdeli, Siavash Arjomand and Zwicker, Matthias and Favaro, Paolo and Jin, Meiguang},
  booktitle={Advances in Neural Information Processing Systems},
  pages={763--772},
  year={2017}
}
  • Representation Learning by Learning to Count

    M. Noroozi, H. Pirsiavash and P. Favaro, in International Conference on Computer Vision (ICCV), 2017. (oral)

    PDF 
    @inproceedings{noroozi2017representation,
  title={Representation learning by learning to count},
  author={Noroozi, Mehdi and Pirsiavash, Hamed and Favaro, Paolo},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
  pages={5898--5906},
  year={2017}
}
  • SmartSketcher: Sketch-based Image Retrieval with Dynamic Semantic Re-ranking

    T. Portenier, Q. Hu, P. Favaro and M. Zwicker, in Expressive, 2017.

    PDF 
    @inproceedings{portenier2017smartsketcher,
  title={SmartSketcher: sketch-based image retrieval with dynamic semantic re-ranking},
  author={Portenier, Tiziano and Hu, Qiyang and Favaro, Paolo and Zwicker, Matthias},
  booktitle={Proceedings of the Symposium on Sketch-Based Interfaces and Modeling},
  pages={1},
  year={2017},
  organization={ACM}
}
  • Motion Deblurring in the Wild

    M. Noroozi, P. Chandramouli and P. Favaro, in German Conference on Pattern Recognition (GCPR), 2017.

    PDF 
    @inproceedings{noroozi2017motion,
  title={Motion deblurring in the wild},
  author={Noroozi, Mehdi and Chandramouli, Paramanand and Favaro, Paolo},
  booktitle={German conference on pattern recognition},
  pages={65--77},
  year={2017},
  organization={Springer}
}
  • Noise-blind image deblurring

    M. Jin, S. Roth, and P. Favaro, in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, Hawaii, 2017.

    Paper Supplement 
    @inproceedings{jin2017noise,
  title={Noise-blind image deblurring},
  author={Jin, Meiguang and Roth, Stefan and Favaro, Paolo},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={3510--3518},
  year={2017}
}
2016
  • Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles

    Mehdi Noroozi and Paolo Favaro, in European Conference on Computer Vision (ECCV), 2016.

    PDF arXiv Project Video 
    @inproceedings{noroozi2016unsupervised,
  title={Unsupervised learning of visual representations by solving jigsaw puzzles},
  author={Noroozi, Mehdi and Favaro, Paolo},
  booktitle={European Conference on Computer Vision},
  pages={69--84},
  year={2016},
  organization={Springer}
}
  • 3D Face Reconstruction with Silhouette Constraints

    Q. Hu, M. Zwicker P. Favaro, in Vision, Modeling, and Visualization, 2016.

    PDF 
    @inproceedings{hu20163d,
  title={3D face reconstruction with silhouette constraints},
  author={Hu, Qiyang and Zwicker, Matthias and Favaro, Paolo},
  booktitle={Proceedings of the Conference on Vision, Modeling and Visualization},
  pages={37--42},
  year={2016},
  organization={Eurographics Association}
}
  • Synchronization of Independently Moving Cameras via Motion Recovery

    T. Gaspar, P. Oliveira and P. Favaro, in SIAM Journal on Imaging Sciences, vol. 9, no. 3, pp. 869-900, 2016.

    PDF 
    @article{gaspar2016synchronization,
  title={Synchronization of Independently Moving Cameras via Motion Recovery},
  author={Gaspar, Tiago and Oliveira, Paulo and Favaro, Paolo},
  journal={SIAM Journal on Imaging Sciences},
  volume={9},
  number={3},
  pages={869--900},
  year={2016},
  publisher={SIAM}
}
  • ConvNet-based Depth Estimation, Reflection Separation and Deblurring of Plenoptic Images

    P. Chandramouli, M. Noroozi and P. Favaro, in Asian Conference on Computer Vision (ACCV), 2016.

    PDF 
    @inproceedings{chandramouli2016convnet,
  title={ConvNet-based depth estimation, reflection separation and deblurring of plenoptic images},
  author={Chandramouli, Paramanand and Noroozi, Mehdi and Favaro, Paolo},
  booktitle={Asian Conference on Computer Vision},
  pages={129--144},
  year={2016},
  organization={Springer}
}
2015
  • A Clearer Picture of Total Variation Blind Deconvolution

    D. Perrone and P. Favaro, in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2015.

    PDF 
    @article{perrone2016clearer,
  title={A clearer picture of total variation blind deconvolution},
  author={Perrone, Daniele and Favaro, Paolo},
  journal={IEEE transactions on pattern analysis and machine intelligence},
  volume={38},
  number={6},
  pages={1041--1055},
  year={2016},
  publisher={IEEE}
}
  • A Logarithmic Image Prior for Blind Deconvolution

    D. Perrone and P. Favaro, in International Journal of Computer Vision (IJCV), pp. 1-14, 2015.

    PDF 
    @article{perrone2016logarithmic,
  title={A logarithmic image prior for blind deconvolution},
  author={Perrone, Daniele and Favaro, Paolo},
  journal={International Journal of Computer Vision},
  volume={117},
  number={2},
  pages={159--172},
  year={2016},
  publisher={Springer}
}
  • Blind Deconvolution via Lower-Bounded Logarithmic Image Priors

    D. Perrone, R. Diethelm and P. Favaro, in International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), 2015.

    PDF Project 
    @inproceedings{perrone2015blind,
  title={Blind deconvolution via lower-bounded logarithmic image priors},
  author={Perrone, Daniele and Diethelm, Remo and Favaro, Paolo},
  booktitle={International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition},
  pages={112--125},
  year={2015},
  organization={Springer}
}
  • Bilayer Blind Deconvolution with the Light Field Camera

    M. Jin, P. Chandramouli and P. Favaro, in IEEE International Conference on Computer Vision Workshop (ICCV Inverse Rendering Workshop), 2015.

    PDF 
    @inproceedings{jin2015bilayer,
  title={Bilayer blind deconvolution with the light field camera},
  author={Jin, Meiguang and Chandramouli, Paramanand and Favaro, Paolo},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision Workshops},
  pages={10--18},
  year={2015}
}
  • Building the View Graph of a Category by Exploiting Image Realism

    A. Szabó, A.Vedaldi and P. Favaro, in 5th International IEEE Workshop on 3D Representation and Recognition (3dRR-15), ICCV, 2015.

    PDF 
    @inproceedings{szabo2015building,
  title={Building the View Graph of a Category by Exploiting Image Realism},
  author={Szab{\'o}, Attila and Vedaldi, Andrea and Favaro, Paolo},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision Workshops},
  pages={10--18},
  year={2015}
}
  • A Convex Solution to Disparity Estimation from Light Fields via the Primal-Dual Method

    M. Hosseini Kamal, P. Favaro and P. Vandergheynst, in International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), 2015.

    PDF 
    @inproceedings{kamal2015convex,
  title={A convex solution to disparity estimation from light fields via the primal-dual method},
  author={Kamal, Mahdad Hosseini and Favaro, Paolo and Vandergheynst, Pierre},
  booktitle={International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition},
  pages={350--363},
  year={2015},
  organization={Springer}
}
2014
  • Coded Aperture Flow

    A. Sellent and P. Favaro, in Proceedings of the German Conference on Pattern Recognition, pp. 1-11, 2014.

    PDF Project 
    @inproceedings{sellent2014coded,
  title={Coded aperture flow},
  author={Sellent, Anita and Favaro, Paolo},
  booktitle={German Conference on Pattern Recognition},
  pages={582--592},
  year={2014},
  organization={Springer}
}
  • Low Rank Subspace Clustering

    R. Vidal and P. Favaro, in Pattern Recognition Letters, vol. 43, pp. 47–61, 2014.

    PDF Project 
    @article{vidal2014low,
  title={Low rank subspace clustering (LRSC)},
  author={Vidal, Ren{\'e} and Favaro, Paolo},
  journal={Pattern Recognition Letters},
  volume={43},
  pages={47--61},
  year={2014},
  publisher={Elsevier}
}
  • Optimized Aperture Shapes for Depth Estimation

    A. Sellent and P. Favaro, in Pattern Recognition Letters, pp. 96-103, 2014.

    PDF 
    @article{sellent2014optimized,
  title={Optimized aperture shapes for depth estimation},
  author={Sellent, Anita and Favaro, Paolo},
  journal={Pattern Recognition Letters},
  volume={40},
  pages={96--103},
  year={2014},
  publisher={Elsevier}
}
  • A Closed-Form, Consistent and Robust Solution to Uncalibrated Photometric Stereo Via Local Diffuse Reflectance Maxima

    T. Papadhimitri and P. Favaro, in International Journal of Computer Vision, vol. 107, no. 2, pp. 139-154, 2014.

    PDF 
    @article{papadhimitri2014closed,
  title={A closed-form, consistent and robust solution to uncalibrated photometric stereo via local diffuse reflectance maxima},
  author={Papadhimitri, Thoma and Favaro, Paolo},
  journal={International journal of computer vision},
  volume={107},
  number={2},
  pages={139--154},
  year={2014},
  publisher={Springer}
}
  • Total Variation Blind Deconvolution: The Devil is in the Details

    D. Perrone and P. Favaro, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.

    Paper Supplement
    Project Poster 
    @inproceedings{perrone2014total,
  title={Total variation blind deconvolution: The devil is in the details},
  author={Perrone, Daniele and Favaro, Paolo},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={2909--2916},
  year={2014}
}
  • Which Side of the Focal Plane are You on?

    A. Sellent and P. Favaro, in IEEE Conference on Computational Photography (ICCP), 2014.

    PDF Project 
    @inproceedings{sellent2014side,
  title={Which side of the focal plane are you on?},
  author={Sellent, Anita and Favaro, Paolo},
  booktitle={2014 IEEE international conference on computational photography (ICCP)},
  pages={1--8},
  year={2014},
  organization={IEEE}
}
  • Synchronization of two independently moving cameras without feature correspondences

    T. Gaspar, P. Oliveira and P. Favaro, in European Conference on Computer Vision (ECCV), 2014.

    PDF 
    @inproceedings{gaspar2014synchronization,
  title={Synchronization of two independently moving cameras without feature correspondences},
  author={Gaspar, Tiago and Oliveira, Paulo and Favaro, Paolo},
  booktitle={European Conference on Computer Vision},
  pages={189--204},
  year={2014},
  organization={Springer}
}
  • Uncalibrated Near-Light Photometric Stereo

    T. Papadhimitri and P. Favaro, in Proceedings of the British Machine Vision Conference, 2014.

    PDF 
    @article{papadhimitri2014uncalibrated,
  title={Uncalibrated near-light photometric stereo},
  author={Papadhimitri, Thoma and Favaro, Paolo},
  year={2014},
  publisher={BMVA Press}
}
  • Anamorphic Pixels for Multi-Channel Superresolution

    A. Oberdoerster, P. Favaro and H. Lensch, in IEEE Conference on Computational Photography (ICCP), 2014.

    PDF 
    @inproceedings{oberdorster2014anamorphic,
  title={Anamorphic pixels for multi-channel superresolution},
  author={Oberd{\"o}rster, Alexander and Favaro, Paolo and Lensch, Hendrik PA},
  booktitle={2014 IEEE International Conference on Computational Photography (ICCP)},
  pages={1--10},
  year={2014},
  organization={IEEE}
}
2013
  • Optimising Aperture Shapes for Depth Estimation

    A. Sellent and P. Favaro, in Workshop on Vision, Modeling and Visualization (VMV), 2013.

    PDF Poster 
    @article{sellent2013optimising,
  title={Optimising Aperture Shapes for Depth Estimation},
  author={Sellent, Anita and Favaro, Paolo},
  year={2013},
  publisher={The Eurographics Association}
}
  • Sparse representation based action and gesture recognition

    S. Bomma, N. Robertson and P. Favaro, in IEEE International Conference on Image Processing (ICIP), 2013.

    PDF 
    @inproceedings{bomma2013sparse,
  title={Sparse representation based action and gesture recognition},
  author={Bomma, Sushma and Favaro, Paolo and Robertson, Neil M},
  booktitle={2013 IEEE International Conference on Image Processing},
  pages={141--145},
  year={2013},
  organization={IEEE}
}
  • A New Perspective on Uncalibrated Photometric Stereo

    T. Papadhimitri and P. Favaro, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013.

    Paper Supplement
    Poster 
    @inproceedings{papadhimitri2013new,
  title={A new perspective on uncalibrated photometric stereo},
  author={Papadhimitri, Thoma and Favaro, Paolo},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={1474--1481},
  year={2013}
}
2012
  • The Light Field Camera: Extended Depth of Field, Aliasing and Super-resolution

    T. Bishop and P. Favaro, in IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 34, no. 5, pp. 972-986, 2012.

    PDF Project 
    @article{bishop2012light,
  title={The light field camera: Extended depth of field, aliasing, and superresolution},
  author={Bishop, Tom E and Favaro, Paolo},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  volume={34},
  number={5},
  pages={972--986},
  year={2012},
  publisher={IEEE}
}
  • Evaluation of image deblurring methods via a classification metric

    D. Perrone, D. Humphreys, R. Lamb and P. Favaro, in Proc. SPIE Electro-Optical Remote Sensing, Photonic Technologies, and Applications VI, 2012.

    PDF 
    @inproceedings{perrone2012evaluation,
  title={Evaluation of image deblurring methods via a classification metric},
  author={Perrone, Daniele and Humphreys, David and Lamb, Robert A and Favaro, Paolo},
  booktitle={Electro-Optical Remote Sensing, Photonic Technologies, and Applications VI},
  volume={8542},
  pages={854215},
  year={2012},
  organization={International Society for Optics and Photonics}
}
  • A Closed-Form Solution to Uncalibrated Photometric Stereo via Diffuse Maxima

    P. Favaro and T. Papadhimitri, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 821-828, 2012.

    Paper Supplement
    Project 
    @inproceedings{favaro2012closed,
  title={A closed-form solution to uncalibrated photometric stereo via diffuse maxima},
  author={Favaro, Paolo and Papadhimitri, Thoma},
  booktitle={2012 IEEE Conference on Computer Vision and Pattern Recognition},
  pages={821--828},
  year={2012},
  organization={IEEE}
}
  • Image Priors for Image Deblurring with Uncertain Blur

    D. Perrone, A. Ravichandran, R. Vidal and P. Favaro, in Proceedings of the British Machine Vision Conference, 2012.

    PDF 
    @inproceedings{perrone2012image,
  title={Image Priors for Image Deblurring with Uncertain Blur.},
  author={Perrone, Daniele and Ravichandran, Avinash and Vidal, Ren{\'e} and Favaro, Paolo},
  booktitle={BMVC},
  pages={1--11},
  year={2012}
}
  • A split-sensor light field camera for extended depth of field and superresolution

    P. Favaro, in Proc. SPIE Optics, Photonics, and Digital Technologies for Multimedia Applications II, pp. 821-828, 2012.

    PDF 
    @inproceedings{favaro2012split,
  title={A split-sensor light field camera for extended depth of field and superresolution},
  author={Favaro, Paolo},
  booktitle={Optics, Photonics, and Digital Technologies for Multimedia Applications II},
  volume={8436},
  pages={843602},
  year={2012},
  organization={International Society for Optics and Photonics}
}
2011
  • Depth estimation from a video sequence with moving and deformable objects

    M. Martinello and P. Favaro, in IET Conference on Image Processing, pp. 1-6, 2011.

    PDF 
    @article{martinello2012depth,
  title={Depth estimation from a video sequence with moving and deformable objects},
  author={Martinello, Manuel and Favaro, Paolo},
  year={2012},
  publisher={IET}
}
  • Single Image Blind Deconvolution with Higher-Order Texture Statistics

    M. Martinello and P. Favaro, in Video Processing and Computational Video, Dagstuhl Proceedings, pp. 124-151, 2011.

    PDF Project 
    @incollection{martinello2011single,
  title={Single image blind deconvolution with higher-order texture statistics},
  author={Martinello, Manuel and Favaro, Paolo},
  booktitle={Video Processing and Computational Video},
  pages={124--151},
  year={2011},
  publisher={Springer}
}
  • Fragmented Aperture Imaging for Motion and Defocus Deblurring

    M. Martinello and P. Favaro, in IEEE International Conference on Image Processing (ICIP), pp. 3413-3416, 2011.

    PDF 
    @inproceedings{martinello2011fragmented,
  title={Fragmented aperture imaging for motion and defocus deblurring},
  author={Martinello, Manuel and Favaro, Paolo},
  booktitle={2011 18th IEEE International Conference on Image Processing},
  pages={3413--3416},
  year={2011},
  organization={IEEE}
}
  • Coded Aperture Videography

    M. Martinello and P. Favaro, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Demos, pp. 124-151, 2011. 

    @inproceedings{martinello2011coded,
  title={Coded Aperture Videography },
  author={Martinello, Manuel and Favaro, Paolo},
  booktitle={2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Demos},
  pages={124-151},
  year={2011},
  organization={IEEE}
}
  • A Closed Form Solution to Robust Subspace Estimation and Clustering

    P. Favaro, R. Vidal and A. Ravichandran, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1801-1807, 2011.

    PDF 
    @inproceedings{Favaro2011,
  doi = {10.1109/cvpr.2011.5995365},
  url = {https://doi.org/10.1109/cvpr.2011.5995365},
  year  = {2011},
  month = {jun},
  publisher = {{IEEE}},
  author = {Paolo Favaro and Rene Vidal and Avinash Ravichandran},
  title = {A closed form solution to robust subspace estimation and clustering},
  booktitle = {{CVPR} 2011}
}
2010
  • Textureless Macula Swelling Detection with Multiple Retinal Fundus Images

    L. Giancardo, F. Meriaudeau, T. P. Karnowski, K. W. Tobin Jr., E. Grisan, P. Favaro, A. Ruggeri and E. Chaum, in IEEE Transactions on Biomedical Engineering, 2010.

    PDF 
    @article{Giancardo2011,
  doi = {10.1109/tbme.2010.2095852},
  url = {https://doi.org/10.1109/tbme.2010.2095852},
  year  = {2011},
  month = {mar},
  publisher = {Institute of Electrical and Electronics Engineers ({IEEE})},
  volume = {58},
  number = {3},
  pages = {795--799},
  author = {L Giancardo and F Meriaudeau and T P Karnowski and Kenneth W Tobin and E Grisan and P Favaro and A Ruggeri and E Chaum},
  title = {Textureless Macula Swelling Detection With Multiple Retinal Fundus Images},
  journal = {{IEEE} Transactions on Biomedical Engineering}
}
  • A Convex Multi-View Stereo Formulation with Robustness to Occlusions and Time-Varying Clutter

    Q. Dou and P. Favaro, in ACM Indian Conference on Computer Vision, Graphics and Image Processing, pp. 243-250, 2010.

    PDF 
    @inproceedings{Dou:2010:CMS:1924559.1924592,
 author = {Dou, Qingxu and Favaro, Paolo},
 title = {A Convex Multi-view Stereo Formulation with Robustness to Occlusions and Time-varying Clutter},
 booktitle = {Proceedings of the Seventh Indian Conference on Computer Vision, Graphics and Image Processing},
 series = {ICVGIP '10},
 year = {2010},
 isbn = {978-1-4503-0060-5},
 location = {Chennai, India},
 pages = {243--250},
 numpages = {8},
 url = {http://doi.acm.org/10.1145/1924559.1924592},
 doi = {10.1145/1924559.1924592},
 acmid = {1924592},
 publisher = {ACM},
 address = {New York, NY, USA},
}
  • A Unified Approach to Segmentation and Categorization of Dynamic Textures

    A. Ravichandran, P. Favaro and R. Vidal, in Asian Conference on Computer Vision (ACCV), pp. 425-438, 2010.

    PDF 
    @inproceedings{Ravichandran:2010:UAS:1964320.1964364,
 author = {Ravichandran, Avinash and Favaro, Paolo and Vidal, Ren{\'e}},
 title = {A Unified Approach to Segmentation and Categorization of Dynamic Textures},
 booktitle = {Proceedings of the 10th Asian Conference on Computer Vision - Volume Part I},
 series = {ACCV'10},
 year = {2011},
 isbn = {978-3-642-19314-9},
 location = {Queenstown, New Zealand},
 pages = {425--438},
 numpages = {14},
 url = {http://dl.acm.org/citation.cfm?id=1964320.1964364},
 acmid = {1964364},
 publisher = {Springer-Verlag},
 address = {Berlin, Heidelberg},
}
  • Full-Resolution Depth Map Estimation from an Aliased Plenoptic Light Field

    T. E. Bishop and P. Favaro, in Asian Conference on Computer Vision (ACCV), pp. 186-200, 2010.

    PDF 
    @inproceedings{Bishop:2010:FDM:1965992.1966008,
 author = {Bishop, Tom E. and Favaro, Paolo},
 title = {Full-resolution Depth Map Estimation from an Aliased Plenoptic Light Field},
 booktitle = {Proceedings of the 10th Asian Conference on Computer Vision - Volume Part II},
 series = {ACCV'10},
 year = {2011},
 isbn = {978-3-642-19308-8},
 location = {Queenstown, New Zealand},
 pages = {186--200},
 numpages = {15},
 url = {http://dl.acm.org/citation.cfm?id=1965992.1966008},
 acmid = {1966008},
 publisher = {Springer-Verlag},
 address = {Berlin, Heidelberg},
}
  • A Bayesian Approach to Shape From Coded Aperture

    M. Martinello, T. E. Bishop and P. Favaro, in IEEE International Conference on Image Processing (ICIP), pp. 3521-3524, 2010.

    PDF 
    @inproceedings{Martinello2010,
  doi = {10.1109/icip.2010.5653070},
  url = {https://doi.org/10.1109/icip.2010.5653070},
  year  = {2010},
  month = {sep},
  publisher = {{IEEE}},
  author = {Manuel Martinello and Tom E. Bishop and Paolo Favaro},
  title = {A Bayesian approach to shape from coded aperture},
  booktitle = {2010 {IEEE} International Conference on Image Processing}
}
  • Recovering Thin Structures via Nonlocal-Means Regularization with Application to Depth from Defocus

    P. Favaro, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1133-1140, 2010.

    PDF 
    @inproceedings{Favaro2010,
  doi = {10.1109/cvpr.2010.5540089},
  url = {https://doi.org/10.1109/cvpr.2010.5540089},
  year  = {2010},
  month = {jun},
  publisher = {{IEEE}},
  author = {Paolo Favaro},
  title = {Recovering thin structures via nonlocal-means regularization with application to depth from defocus},
  booktitle = {2010 {IEEE} Computer Society Conference on Computer Vision and Pattern Recognition}
}
2009
  • Plenoptic Depth Estimation From Multiple Aliased Views

    T. E. Bishop and P. Favaro, in IEEE International Conference on Computer Vision Workshops (ICCV Workshops), pp. 1622-1629, 2009.

    PDF 
    @inproceedings{Bishop2009,
  doi = {10.1109/iccvw.2009.5457420},
  url = {https://doi.org/10.1109/iccvw.2009.5457420},
  year  = {2009},
  month = {sep},
  publisher = {{IEEE}},
  author = {Tom E. Bishop and Paolo Favaro},
  title = {Plenoptic depth estimation from multiple aliased views},
  booktitle = {2009 {IEEE} 12th International Conference on Computer Vision Workshops,  {ICCV} Workshops}
}
  • Nonlocal Similarity Image Filtering

    Y. Lou, P. Favaro, S. Soatto, and A. Bertozzi, in Image Analysis and Processing (ICIAP), pp. 62-71, 2009.

    PDF 
    @inproceedings{Lou:2009:NSI:1618083.1618096,
 author = {Lou, Yifei and Favaro, Paolo and Soatto, Stefano and Bertozzi, Andrea},
 title = {Nonlocal Similarity Image Filtering},
 booktitle = {Proceedings of the 15th International Conference on Image Analysis and Processing},
 series = {ICIAP '09},
 year = {2009},
 isbn = {978-3-642-04145-7},
 location = {Vietri sul Mare, Italy},
 pages = {62--71},
 numpages = {10},
 url = {http://dx.doi.org/10.1007/978-3-642-04146-4_9},
 doi = {10.1007/978-3-642-04146-4_9},
 acmid = {1618096},
 publisher = {Springer-Verlag},
 address = {Berlin, Heidelberg},
}
  • Light Field Superresolution

    T. E. Bishop, S. Zanetti, and P. Favaro, in IEEE International Conference on Computational Photography (ICCP), 2009.

    PDF 
    @inproceedings{bishop2009light,
  title={Light field superresolution},
  author={Bishop, Tom E and Zanetti, Sara and Favaro, Paolo},
  booktitle={2009 IEEE International Conference on Computational Photography (ICCP)},
  pages={1--9},
  year={2009},
  organization={IEEE}
}
2008
  • Shape from Defocus via Diffusion

    P. Favaro, S. Soatto, M. Burger and S. Osher, in IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 30, no. 3, pp. 518-531, 2008.

    PDF 
    @article{favaro2008shape,
  title={Shape from defocus via diffusion},
  author={Favaro, Paolo and Soatto, Stefano and Burger, Martin and Osher, Stanley J},
  journal={IEEE transactions on pattern analysis and machine intelligence},
  volume={30},
  number={3},
  pages={518--531},
  year={2008},
  publisher={IEEE}
}
  • A Theory of Defocus via Fourier Analysis

    P. Favaro and A. Duci, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1-8, 2008.

    PDF 
    @inproceedings{favaro2008theory,
  title={A theory of defocus via Fourier analysis},
  author={Favaro, Paolo and Duci, Alessandro},
  booktitle={2008 IEEE Conference on Computer Vision and Pattern Recognition},
  pages={1--8},
  year={2008},
  organization={IEEE}
}
  • Off-Axis Aperture Camera: 3D Shape Reconstruction and Image Restoration

    Q. Dou and P. Favaro, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1-7, 2008.

    PDF 
    @inproceedings{dou2008off,
  title={Off-axis aperture camera: 3d shape reconstruction and image restoration},
  author={Dou, Qingxu and Favaro, Paolo},
  booktitle={2008 IEEE Conference on Computer Vision and Pattern Recognition},
  pages={1--7},
  year={2008},
  organization={IEEE}
}
2007
  • Shape from Focus and Defocus: Convexity, Quasiconvexity, and Defocus-Invariant Textures

    P. Favaro, in IEEE International Conference on Computer Vision (ICCV), pp. 1-7, 2007.

    PDF 
    @inproceedings{favaro2007shape,
  title={Shape from focus and defocus: Convexity, quasiconvexity and defocus-invariant textures},
  author={Favaro, Paolo},
  booktitle={2007 IEEE 11th International Conference on Computer Vision},
  pages={1--7},
  year={2007},
  organization={IEEE}
}
  • Boosting Invariance and Efficiency in Supervised Learning

    A. Vedaldi, P. Favaro, E. Grisan, in IEEE International Conference on Computer Vision (ICCV), pp. 1-8, 2007.

    PDF 
    @inproceedings{vedaldi2007boosting,
  title={Boosting invariance and efficiency in supervised learning},
  author={Vedaldi, Andrea and Favaro, Paolo and Grisan, Enrico},
  booktitle={2007 IEEE 11th International Conference on Computer Vision},
  pages={1--8},
  year={2007},
  organization={IEEE}
}
  • Autocalibration and Uncalibrated Reconstruction of Shape from Defocus

    Y. Lou, P. Favaro, A. Bertozzi and S. Soatto, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1-8, 2007.

    PDF 
    @inproceedings{lou2007autocalibration,
  title={Autocalibration and uncalibrated reconstruction of shape from defocus},
  author={Lou, Yifei and Favaro, Paolo and Bertozzi, Andrea L and Soatto, Stefano},
  booktitle={2007 IEEE Conference on Computer Vision and Pattern Recognition},
  pages={1--8},
  year={2007},
  organization={IEEE}
}
  • 3-D Retinal Surface Inference: Stereo or Monocular Fundus Camera?

    M. Martinello, P. Favaro, G. M. Nieto, A. Harvey, E. Grisan, F. Scarpa and A. Ruggeri, in Proc. of the IEEE Engineering in Medicine and Biology Society, pp. 896-899, 2007.

    PDF 
    @inproceedings{martinello20073,
  title={3-D retinal surface inference: stereo or monocular fundus camera?},
  author={Martinello, Manuel and Favaro, Paolo and Nieto, GD Muyo and Harvey, AR and Grisan, Enrico and Scarpa, Fabio and Ruggeri, Alfredo},
  booktitle={2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society},
  pages={896--899},
  year={2007},
  organization={IEEE}
}
  • DynamicBoost: Boosting Time Series Generated by Dynamical Systems

    R. Vidal and P. Favaro, in IEEE International Conference on Computer Vision (ICCV), pp. 1-6, 2007.

    PDF 
    @inproceedings{vidal2007dynamicboost,
  title={Dynamicboost: Boosting time series generated by dynamical systems},
  author={Vidal, Ren{\'e} and Favaro, Paolo},
  booktitle={2007 IEEE 11th International Conference on Computer Vision},
  pages={1--6},
  year={2007},
  organization={IEEE}
}
2006
  • Defocus Inpainting

    P. Favaro and E. Grisan, in European Conference on Computer Vision (ECCV), pp. 349-359, 2006.

    PDF 
    @inproceedings{favaro2006defocus,
  title={Defocus inpainting},
  author={Favaro, Paolo and Grisan, Enrico},
  booktitle={European Conference on Computer Vision},
  pages={349--359},
  year={2006},
  organization={Springer}
}
2005
  • A Geometric Approach to Shape from Defocus

    P. Favaro and S. Soatto, in IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 27, no. 3, pp. 406-417, 2005.

    PDF arXiv 
    @article{favaro2005geometric,
  title={A geometric approach to shape from defocus},
  author={Favaro, Paolo and Soatto, Stefano},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  volume={27},
  number={3},
  pages={406--417},
  year={2005},
  publisher={IEEE}
}
  • Using Frontier Points to Recover Shape, Reflectance and Illumination

    G. Vogiatzis, P. Favaro and R. Cipolla, in IEEE International Conference on Computer Vision (ICCV), pp. 228-235, 2005.

    PDF 
    @inproceedings{vogiatzis2005using,
  title={Using frontier points to recover shape, reflectance and illumination},
  author={Vogiatzis, George and Favaro, Paolo and Cipolla, Roberto},
  booktitle={Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1},
  volume={1},
  pages={228--235},
  year={2005},
  organization={IEEE}
}
  • KALMANSAC: Causal Inference of Dynamic Processes in the Presence of Outliers

    A. Vedaldi, H. Jin, P. Favaro and S. Soatto, in IEEE International Conference on Computer Vision (ICCV), pp. 633-640, 2005.

    PDF 
    @inproceedings{vedaldi2005kalmansac,
  title={Kalmansac: Causal inference of dynamical processes in the presence of outliers},
  author={Vedaldi, A and Jin, H and Favaro, P and Soatto, S},
  booktitle={Proc. of the Intl. Conf. on Comp. Vision},
  year={2005}
}
  • Visual Tracking in the Presence of Motion Blur

    H. Jin, P. Favaro and R. Cipolla, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18-25, 2005.

    PDF 
    @inproceedings{jin2005visual,
  title={Visual tracking in the presence of motion blur},
  author={Jin, Hailin and Favaro, Paolo and Cipolla, Roberto},
  booktitle={2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)},
  volume={2},
  pages={18--25},
  year={2005},
  organization={IEEE}
}
2004
  • A Variational Approach to Scene Reconstruction and Image Segmentation from Motion-Blur Cues

    P. Favaro and S. Soatto, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 631-637, 2004.

    PDF 
    @inproceedings{favaro2004variational,
  title={A variational approach to scene reconstruction and image segmentation from motion-blur cues},
  author={Favaro, Paolo and Soatto, Stefano},
  booktitle={Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.},
  volume={1},
  pages={I--I},
  year={2004},
  organization={IEEE}
}
  • Scene and Motion Reconstruction from Defocused and Motion-Blurred Images via Anisotropic Diffusion

    P. Favaro, M. Burger, and S. Soatto, in European Conference on Computer Vision (ECCV), pp. 257-269, 2004.

    PDF 
    @INPROCEEDINGS{Favaro04sceneand,
    author = {Paolo Favaro and Martin Burger and Stefano Soatto},
    title = {Scene and Motion Reconstruction from Defocused and Motion-Blurred Images via Anisotropic Diffusion},
    booktitle = {In Computer Vision - ECCV 2004, 8th European Conference on Computer Vision},
    year = {2004},
    pages = {11--14},
    publisher = {Springer Verlag}
}
2003
  • Observing Shape from Defocused Images

    P. Favaro, A. Mennucci and S. Soatto, in International Journal of Computer Vision, vol. 52, no. 1, pp. 25-43, 2003.

    PDF 
    @article{Favaro:2003:OSD:633020.633023,
 author = {Favaro, Paolo and Mennucci, Andrea and Soatto, Stefano},
 title = {Observing Shape from Defocused Images},
 journal = {Int. J. Comput. Vision},
 issue_date = {April 2003},
 volume = {52},
 number = {1},
 month = apr,
 year = {2003},
 issn = {0920-5691},
 pages = {25--43},
 numpages = {19},
 url = {https://doi.org/10.1023/A:1022366408068},
 doi = {10.1023/A:1022366408068},
 acmid = {633023},
 publisher = {Kluwer Academic Publishers},
 address = {Hingham, MA, USA},
 keywords = {low-level vision, shape, shape from defocus, shape from focus, surface geometry},
}
  • A Semi-direct Approach to Structure From Motion

    H. Jin, P. Favaro and S. Soatto, in The Visual Computer, vol. 19, pp. 1-18, 2003.

    PDF 
    @article{jin2003semi,
  title={A semi-direct approach to structure from motion},
  author={Jin, Hailin and Favaro, Paolo and Soatto, Stefano},
  journal={The Visual Computer},
  volume={19},
  number={6},
  pages={377--394},
  year={2003},
  publisher={Springer}
}
  • On Exploiting Occlusions in Multiple-view Geometry

    P. Favaro, A. Duci, Y. Ma, and S. Soatto, in IEEE International Conference on Computer Vision (ICCV), pp. 479-486, 2003.

    PDF 
    @inproceedings{Favaro2003,
  doi = {10.1109/iccv.2003.1238386},
  url = {https://doi.org/10.1109/iccv.2003.1238386},
  year  = {2003},
  publisher = {{IEEE}},
  author = {Favaro and  Duci and  Ma and  Soatto},
  title = {On exploiting occlusions in multiple-view geometry},
  booktitle = {Proceedings Ninth {IEEE} International Conference on Computer Vision}
}
  • Dynamic texture segmentation

    G. Doretto, D. Cremers, P. Favaro, and S. Soatto, in IEEE International Conference on Computer Vision (ICCV), pp. 1236-1242, 2003.

    PDF 
    @inproceedings{Doretto:2003:DTS:946247.946746,
 author = {Doretto, Gianfranco and Cremers, Daniel and Favaro, Paolo and Soatto, Stefano},
 title = {Dynamic Texture Segmentation},
 booktitle = {Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2},
 series = {ICCV '03},
 year = {2003},
 isbn = {0-7695-1950-4},
 pages = {1236--},
 url = {http://dl.acm.org/citation.cfm?id=946247.946746},
 acmid = {946746},
 publisher = {IEEE Computer Society},
 address = {Washington, DC, USA},
}
  • 3D Shape from Anisotropic Diffusion

    P. Favaro, S. J. Osher, S. Soatto and L. A. Vese, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 179-186, 2003.

    PDF 
    @inproceedings{Favaro:2003:SAD:1965841.1965863,
 author = {Favaro, P. and Osher, S. and Soatto, S. and Vese, L.},
 title = {3D Shape from Anisotropic Diffusion},
 booktitle = {Proceedings of the 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition},
 series = {CVPR'03},
 year = {2003},
 isbn = {0-7695-1900-8, 978-0-7695-1900-5},
 location = {Madison, Wisconsin},
 pages = {179--186},
 numpages = {8},
 url = {http://dl.acm.org/citation.cfm?id=1965841.1965863},
 acmid = {1965863},
 publisher = {IEEE Computer Society},
 address = {Washington, DC, USA},
 keywords = {anisotropic diffusion, depth from defocus, early vision, image-based modeling, shape from defocus, shape representation},
}
  • Seeing Beyond Occlusions (and other marvels of a finite lens aperture)

    P. Favaro and S. Soatto, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 579-586, 2003.

    PDF 
    @inproceedings{Favaro2003SeeingBO,
  title={Seeing Beyond Occlusions (and other marvels of a finite lens aperture)},
  author={Paolo Favaro and Stefano Soatto},
  booktitle={CVPR},
  year={2003}
}
2002
  • Structure from Motion Causally Integrated over Time

    A. Chiuso, P. Favaro, H. Jin and S. Soatto, in IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 24, no. 4, pp. 523-535, 2002.

    PDF 
    @article{chiuso2002structure,
  title={Structure from motion causally integrated over time},
  author={Chiuso, Alessandro and Favaro, Paolo and Jin, Hailin and Soatto, Stefano},
  journal={IEEE Transactions on Pattern Analysis \& Machine Intelligence},
  number={4},
  pages={523--535},
  year={2002},
  publisher={IEEE}
}
  • Learning shape from defocus

    P. Favaro and S. Soatto, in European Conference on Computer Vision (ECCV), pp. 735-745, 2002.

    PDF 
    @inproceedings{favaro2002learning,
  title={Learning shape from defocus},
  author={Favaro, Paolo and Soatto, Stefano},
  booktitle={European Conference on Computer Vision},
  pages={735--745},
  year={2002},
  organization={Springer}
}
  • A Variational Approach to Shape from Defocus

    H. Jin and P. Favaro, in European Conference on Computer Vision (ECCV), pp. 18-30, 2002.

    PDF 
    @INPROCEEDINGS{Jin02avariational,
    author = {Hailin Jin and Paolo Favaro},
    title = {A Variational Approach to Shape from Defocus},
    booktitle = {In Proc. European Conference on Computer Vision},
    year = {2002},
    pages = {18--30}
}
2001
  • A Semi-direct Approach to Structure from Motion

    P. Favaro, H. Jin and S. Soatto, in IEEE International Conference on Image Analysis and Processing, pp. 250-255, 2001.

    PDF 
    @inproceedings{favaro2001semi,
  title={A semi-direct approach to structure from motion},
  author={Favaro, Paolo and Jin, Hailin and Soatto, Stefano},
  booktitle={Proceedings 11th International Conference on Image Analysis and Processing},
  pages={250--255},
  year={2001},
  organization={IEEE}
}
  • Real-time Virtual Object Insertion

    P. Favaro, H. Jin and S. Soatto, in IEEE International Conference on Computer Vision (ICCV) - Demo Session, pp. 749, 2001.

    PDF 
    @INPROCEEDINGS{937711,
    author={P. {Favaro} and H. {Jin} and S. {Soatto}},
    booktitle={Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001},
    title={Real-time virtual object insertion},
    year={2001},
    volume={2},
    number={},
    pages={749-749},
    keywords={Layout;Cameras;Lighting;Tracking;Hardware;Humans;Motion estimation;Mathematical model;Computer science;Image sequences},
    doi={10.1109/ICCV.2001.937711},
    ISSN={},
    month={July},
}
  • Real-time Feature Tracking and Outlier Rejection with Changes in Illumination

    H. Jin, P. Favaro and S. Soatto, in IEEE International Conference on Computer Vision (ICCV), pp. 684-689, 2001.

    PDF 
    @INPROCEEDINGS{937588,
    author={ and P. {Favaro} and S. {Soatto}},
    booktitle={Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001},
    title={Real-time feature tracking and outlier rejection with changes in illumination},
    year={2001},
    volume={1},
    number={},
    pages={684-689 vol.1},
    keywords={real-time systems;computer vision;computational geometry;real-time feature tracking;outlier rejection;point features;image patches;affine deformations;geometry;photometry;Lighting;Layout;Robustness;Target tracking;Real time systems;Application software;Computer science;Photometry;Testing;Microcomputers},
    doi={10.1109/ICCV.2001.937588},
    ISSN={},
    month={July},
}
2000
  • Real-time 3-D Motion and Structure from Point Features: a Front-end System for Vision-based Control and Interaction

    H. Jin, P. Favaro and S. Soatto, in IEEE Conference on Computer Vision and Pattern Recognition - Demo Session (CVPR), pp. 778, 2000.

    PDF 
    @INPROCEEDINGS{Jin00real-time3-d,
    author = {Hailin Jin and Paolo Favaro and Stefano Soatto},
    title = {Real-time 3-d motion and structure of point features: Front-end system for vision-based control and interaction},
    booktitle = {In IEEE Computer Vision and Pattern Recognition},
    year = {2000},
    pages = {778--779}
}
  • A Geometric Approach to Blind Deconvolution with Application to Shape from Defocus

    S. Soatto and P. Favaro, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10-17, 2000.

    PDF 
    @INPROCEEDINGS{Soatto00ageometric,
    author = {Stefano Soatto and Paolo Favaro},
    title = {A Geometric Approach to Blind Deconvolution with Application to Shape from Defocus},
    booktitle = {Proc. IEEE Computer Vision and Pattern Recognition},
    year = {2000},
    pages = {10--17}
}
  • Shape and Radiance Estimation under Positivity Constraints From the Information Divergence of Blurred Images

    P. Favaro and S. Soatto, in European Conference on Computer Vision (ECCV), pp. 755-768, 2000.

    PDF 
    @INPROCEEDINGS{Favaro00shapeand,
    author = {Paolo Favaro and Stefano Soatto},
    title = {Shape and radiance estimation from the information divergence of blurred images},
    booktitle = {of Blurred Images,” Proc. European Conf. Computer Vision},
    year = {2000},
    pages = {755--768}
}
  • Mfm: 3-D Motion and Structure Causally Integrated over Time Part II: Implementation

    A. Chiuso, P. Favaro, H. Jin and S. Soatto, in European Conference on Computer Vision (ECCV), pp. 734-750, 2000.

    PDF 
    @INPROCEEDINGS{Chiuso00mfm:3-d,
    author = {Alessandro Chiuso and Paolo Favaro and Hailin Jin and Stefano Soatto},
    title = {MFm: 3-D Motion From 2-D Motion Causally Integrated Over Time - Part II: Implementation},
    booktitle = {In European Conference on Computer Vision},
    year = {2000},
    pages = {735--750}
}

PhD Theses

  • Efficient Self-Supervised Visual Representation Learning via Sparsity

    Sepehr Sameni, Sept. 2024.

    PDF
  • Unsupervised Object Segmentation with Generative Models

    Adam Jakub Bielski, April 2024.

    PDF
  • Novel Techniques for Robust and Generalizable Machine Learning

    Abdelhak Lemkhenter, Sept. 2023.

    PDF
  • Automated Sleep Scoring, Deep Learning and Physician Supervision

    Luigi Fiorillo, Oct. 2022.

    PDF
  • Learning Representations for Controllable Image Restoration

    Givi Meishvili, March 2022.

    PDF
  • Learning Generalizable Visual Patterns Without Human Supervision

    Simon Jenni, Oct. 2021.

    PDF
  • Learning Interpretable Representations of Images

    Attila Szabó, June 2019.

    PDF Slides 
    @phdthesis{szabo_2019, 
    title={Learning Interpretable Representations of Images}, 
    author={Szab{\'o}, Attila}, 
    year={2019}
}
  • Learning Controllable Representations for Image Synthesis

    Qiyang Hu, June 2019.

    PDF 
    @phdthesis{hu_2019, 
    title={Learning Controllable Representations for Image Synthesis}, 
    author={Hu, Qiyang}, 
    year={2019}
}
  • Beyond Supervised Representation Learning

    Mehdi Noroozi, Jan. 2019.

    PDF 
    @phdthesis{noroozi_2019, 
    title={Beyond Supervised Representation Learning}, 
    author={Noroozi, Mehdi}, 
    year={2019}
}
  • Motion Deblurring from a Single Image

    Meiguang Jin, Dec. 2018.

    PDF 
    @phdthesis{jin_2018, 
    title={Motion Deblurring from a Single Image}, 
    author={Jin, Meiguang}, 
    year={2018}
}
  • Towards a Novel Paradigm in Blind Deconvolution: From Natural to Cartooned Image Statistics

    Daniele Perrone, July 2015.

    PDF 
    @phdthesis{perrone_2015, 
    title={Towards a Novel Paradigm in Blind Deconvolution: From Natural to Cartooned Image Statistics}, 
    author={Perrone, Daniele}, 
    year={2015}
}
  • New Perspectives on Uncalibrated Photometric Stereo

    Thoma Papadhimitri, June 2014.

    PDF 
    @phdthesis{papadhimitri_2014, 
    title={New Perspectives on Uncalibrated Photometric Stereo}, 
    author={Papadhimitri, Thoma}, 
    year={2014}
}

    • Books

    • 3-D Shape Estimation and Image Restoration Exploiting Defocus and Motion-blur

      P. Favaro and S. Soatto, Springer-Verlag, 2006.

      Read 
      @misc{favoro20073d,
  title={3D-Shape Estimation and Image Restoration},
  author={Favoro, Paolo and Soatto, Stefano},
  year={2007},
  publisher={Springer: Berlin}
}

    Patents

    • System and Method for Semantic Indexing and Navigation of Volumetric Images

      A. Chackraborty, B. Georgescu, N. Petrovich, P. Favaro, and D. Comaniciu, US Docket 2005P16866US01, 2005. (Provisional Patent)

      View
    • System and Method for Fetal Biometric Measurements from Ultrasound Data and Fusion of Same for Estimation of Fetal Gestational Age

      G. Carneiro, S. Good, B. Georgescu, P. Favaro, and D. Comaniciu, US Docket 2005P14550US01, 2005. (Provisional Patent)

      View
    • Image Processing Methods and Apparatus

      R. Cipolla, G. Vogiatzis, and P. Favaro, UK Patent Application No. 0520829.3, PCT/GB2006/050325, 2005. (Provisional Patent)

      View