| 2025 | AAAI | CAGE: Unsupervised Visual Composition and Animation for Controllable Video Generation. | Aram Davtyan, Sepehr Sameni, Bjrn Ommer, Paolo Favaro |
| 2025 | CVPR | GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control. | Mariam Hassan, Sebastian Stapf, Ahmad Rahimi, Pedro M. B. Rezende, Yasaman Haghighi, David Brggemann, Isinsu Katircioglu, Lin Zhang, Xiaoran Chen, Suman Saha, Marco Cannici, Elie Aljalbout, Botao Ye, Xi Wang, Aram Davtyan, Mathieu Salzmann, Davide Scaramuzza, Marc Pollefeys, Paolo Favaro, Alexandre Alahi |
| 2025 | CVPR | ViDROP: Video Dense Representation through Spatio-Temporal Sparsity. | Sepehr Sameni, Simon Jenni, Paolo Favaro |
| 2025 | CVPR | Adapting Dense Matching for Homography Estimation with Grid-based Acceleration. | Kaining Zhang, Yuxin Deng, Jiayi Ma, Paolo Favaro |
| 2025 | ICCV | MIRAGE: Unsupervised Single Image to Novel View Generation with Cross Attention Guidance. | Llukman Cerkezi, Aram Davtyan, Sepehr Sameni, Paolo Favaro |
| 2025 | ICCV | Diffusion Image Prior. | Hamadi Chihaoui, Paolo Favaro |
| 2025 | ICLR | Faster Inference of Flow-Based Generative Models via Improved Data-Noise Coupling. | Aram Davtyan, Leello Tadesse Dadi, Volkan Cevher, Paolo Favaro |
| 2024 | AAAI | Learn the Force We Can: Enabling Sparse Motion Control in Multi-Object Video Generation. | Aram Davtyan, Paolo Favaro |
| 2024 | CVPR | Masked and Shuffled Blind Spot Denoising for Real-World Images. | Hamadi Chihaoui, Paolo Favaro |
| 2024 | CVPR | SemiGPC: Distribution-Aware Label Refinement for Imbalanced Semi-Supervised Learning Using Gaussian Processes. | Abdelhak Lemkhenter, Manchen Wang, Luca Zancato, Gurumurthy Swaminathan, Paolo Favaro, Davide Modolo |
| 2024 | CVPR | 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 |
| 2024 | ICIP | When Self-Supervised Pre-Training Meets Single Image Denoising. | Hamadi Chihaoui, Paolo Favaro |
| 2024 | WACV | Denoising and Selecting Pseudo-Heatmaps for Semi-Supervised Human Pose Estimation. | Zhuoran Yu, Manchen Wang, Yanbei Chen, Paolo Favaro, Davide Modolo |
| 2023 | AAAI | Representation Learning by Detecting Incorrect Location Embeddings. | Sepehr Sameni, Simon Jenni, Paolo Favaro |
| 2023 | CVPR | ScaleDet: A Scalable Multi-Dataset Object Detector. | Yanbei Chen, Manchen Wang, Abhay Mittal, Zhenlin Xu, Paolo Favaro, Joseph Tighe, Davide Modolo |
| 2023 | CVPR | 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 |
| 2023 | ICCV | Efficient Video Prediction via Sparsely Conditioned Flow Matching. | Aram Davtyan, Sepehr Sameni, Paolo Favaro |
| 2023 | ICCV | Spatio-Temporal Crop Aggregation for Video Representation Learning. | Sepehr Sameni, Simon Jenni, Paolo Favaro |
| 2022 | AAAI | KOALA: A Kalman Optimization Algorithm with Loss Adaptivity. | Aram Davtyan, Sepehr Sameni, Llukman Cerkezi, Givi Meishvili, Adam Bielski, Paolo Favaro |
| 2022 | ECCV | Controllable Video Generation Through Global and Local Motion Dynamics. | Aram Davtyan, Paolo Favaro |
| 2021 | BMVC | Learning to Deblur and Rotate Motion-Blurred Faces. | Givi Meishvili, Attila Szab, Simon Jenni, Paolo Favaro |
| 2021 | ICCP | Real-Time Light Field 3D Microscopy via Sparsity-Driven Learned Deconvolution. | Josu Page Vizcano, Zeguan Wang, Panagiotis Symvoulidis, Paolo Favaro, Burcu Guner-Ataman, Edward S. Boyden, Tobias Lasser |
| 2021 | ICCV | ISD: Self-Supervised Learning by Iterative Similarity Distillation. | Ajinkya Tejankar, Soroush Abbasi Koohpayegani, Vipin Pillai, Paolo Favaro, Hamed Pirsiavash |
| 2021 | ICML | A Unified Generative Adversarial Network Training via Self-Labeling and Self-Attention. | Tomoki Watanabe, Paolo Favaro |
| 2020 | ACCV | Self-supervised Multi-view Synchronization Learning for 3D Pose Estimation. | Simon Jenni, Paolo Favaro |
| 2020 | CVPR | Steering Self-Supervised Feature Learning Beyond Local Pixel Statistics. | Simon Jenni, Hailin Jin, Paolo Favaro |
| 2020 | CVPR | Learning to Have an Ear for Face Super-Resolution. | Givi Meishvili, Simon Jenni, Paolo Favaro |
| 2020 | ECCV | Video Representation Learning by Recognizing Temporal Transformations. | Simon Jenni, Givi Meishvili, Paolo Favaro |
| 2020 | ICIP | Learning to Model and Calibrate Optics Via a Differentiable Wave Optics Simulator. | Josu Page, Paolo Favaro |
| 2020 | ICPR | Learning to Take Directions One Step at a Time. | Qiyang Hu, Adrian Wlchli, Tiziano Portenier, Matthias Zwicker, Paolo Favaro |
| 2019 | CVPR | On Stabilizing Generative Adversarial Training With Noise. | Simon Jenni, Paolo Favaro |
| 2019 | CVPR | Learning to Extract Flawless Slow Motion From Blurry Videos. | Meiguang Jin, Zhe Hu, Paolo Favaro |
| 2018 | CVPR | Disentangling Factors of Variation by Mixing Them. | Qiyang Hu, Attila Szab, Tiziano Portenier, Paolo Favaro, Matthias Zwicker |
| 2018 | CVPR | Self-Supervised Feature Learning by Learning to Spot Artifacts. | Simon Jenni, Paolo Favaro |
| 2018 | CVPR | Learning Face Deblurring Fast and Wide. | Meiguang Jin, Michael Hirsch, Paolo Favaro |
| 2018 | CVPR | Learning to Extract a Video Sequence From a Single Motion-Blurred Image. | Meiguang Jin, Givi Meishvili, Paolo Favaro |
| 2018 | CVPR | Boosting Self-Supervised Learning via Knowledge Transfer. | Mehdi Noroozi, Ananth Vinjimoor, Paolo Favaro, Hamed Pirsiavash |
| 2018 | ECCV | Deep Bilevel Learning. | Simon Jenni, Paolo Favaro |
| 2018 | ECCV | Normalized Blind Deconvolution. | Meiguang Jin, Stefan Roth, Paolo Favaro |
| 2018 | ECCV | Understanding Degeneracies and Ambiguities in Attribute Transfer. | Attila Szab, Qiyang Hu, Tiziano Portenier, Matthias Zwicker, Paolo Favaro |
| 2018 | ICCP | Learning to see through reflections. | Meiguang Jin, Sabine Ssstrunk, Paolo Favaro |
| 2018 | ICLR | Challenges in Disentangling Independent Factors of Variation. | Attila Szab, Qiyang Hu, Tiziano Portenier, Matthias Zwicker, Paolo Favaro |
| 2017 | CVPR | Noise-Blind Image Deblurring. | Meiguang Jin, Stefan Roth, Paolo Favaro |
| 2017 | ICCV | Representation Learning by Learning to Count. | Mehdi Noroozi, Hamed Pirsiavash, Paolo Favaro |
| 2016 | ACCV | ConvNet-Based Depth Estimation, Reflection Separation and Deblurring of Plenoptic Images. | Paramanand Chandramouli, Mehdi Noroozi, Paolo Favaro |
| 2016 | ECCV | Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles. | Mehdi Noroozi, Paolo Favaro |
| 2014 | BMVC | Uncalibrated Near-Light Photometric Stereo. | Thoma Papadhimitri, Paolo Favaro |
| 2014 | CVPR | Total Variation Blind Deconvolution: The Devil Is in the Details. | Daniele Perrone, Paolo Favaro |
| 2014 | ECCV | Synchronization of Two Independently Moving Cameras without Feature Correspondences. | Tiago Gaspar, Paulo Jorge Ramalho Oliveira, Paolo Favaro |
| 2014 | ICCP | Anamorphic pixels for multi-channel superresolution. | Alexander Oberdrster, Paolo Favaro, Hendrik P. A. Lensch |
| 2014 | ICCP | Which side of the focal plane are you on? | Anita Sellent, Paolo Favaro |
| 2013 | CVPR | A New Perspective on Uncalibrated Photometric Stereo. | Thoma Papadhimitri, Paolo Favaro |
| 2013 | ICIP | Sparse representation based action and gesture recognition. | Sushma Bomma, Paolo Favaro, Neil M. Robertson |
| 2012 | BMVC | Image Priors for Image Deblurring with Uncertain Blur. | Daniele Perrone, Avinash Ravichandran, Ren Vidal, Paolo Favaro |
| 2012 | CVPR | A closed-form solution to uncalibrated photometric stereo via diffuse maxima. | Paolo Favaro, Thoma Papadhimitri |
| 2011 | CVPR | A closed form solution to robust subspace estimation and clustering. | Paolo Favaro, Ren Vidal, Avinash Ravichandran |
| 2011 | ICIP | Fragmented aperture imaging for motion and defocus deblurring. | Manuel Martinello, Paolo Favaro |
| 2010 | ACCV | Full-Resolution Depth Map Estimation from an Aliased Plenoptic Light Field. | Tom E. Bishop, Paolo Favaro |
| 2010 | ACCV | A Unified Approach to Segmentation and Categorization of Dynamic Textures. | Avinash Ravichandran, Paolo Favaro, Ren Vidal |
| 2010 | CVPR | Recovering thin structures via nonlocal-means regularization with application to depth from defocus. | Paolo Favaro |
| 2010 | ICIP | A Bayesian approach to shape from coded aperture. | Manuel Martinello, Tom E. Bishop, Paolo Favaro |
| 2009 | ICIAP | Nonlocal Similarity Image Filtering. | Yifei Lou, Paolo Favaro, Stefano Soatto, Andrea L. Bertozzi |
| 2008 | CVPR | Off-axis aperture camera: 3D shape reconstruction and image restoration. | Qingxu Dou, Paolo Favaro |
| 2008 | CVPR | A theory of defocus via Fourier analysis. | Paolo Favaro, Alessandro Duci |
| 2007 | CVPR | Autocalibration and Uncalibrated Reconstruction of Shape from Defocus. | Yifei Lou, Paolo Favaro, Andrea L. Bertozzi, Stefano Soatto |
| 2007 | ICCV | Shape from Focus and Defocus: Convexity, Quasiconvexity and Defocus-Invariant Textures. | Paolo Favaro |
| 2007 | ICCV | Boosting Invariance and Efficiency in Supervised Learning. | Andrea Vedaldi, Paolo Favaro, Enrico Grisan |
| 2007 | ICCV | DynamicBoost: Boosting Time Series Generated by Dynamical Systems. | Ren Vidal, Paolo Favaro |
| 2006 | ECCV | Defocus Inpainting. | Paolo Favaro, Enrico Grisan |
| 2005 | CVPR | Visual Tracking in the Presence of Motion Blur. | Hailin Jin, Paolo Favaro, Roberto Cipolla |
| 2005 | ICCV | KALMANSAC: Robust Filtering by Consensus. | Andrea Vedaldi, Hailin Jin, Paolo Favaro, Stefano Soatto |
| 2005 | ICCV | Using Frontier Points to Recover Shape, Reflectance and Illumunation. | George Vogiatzis, Paolo Favaro, Roberto Cipolla |
| 2004 | CVPR | A Variational Approach to Scene Reconstruction and Image Segmentation from Motion-Blur Cues. | Paolo Favaro, Stefano Soatto |
| 2004 | ECCV | Scene and Motion Reconstruction from Defocused and Motion-Blurred Images via Anisotropic Diffusion. | Paolo Favaro, Martin Burger, Stefano Soatto |
| 2003 | CVPR | 3D Shape from Anisotropic Diffusion. | Paolo Favaro, Stanley J. Osher, Stefano Soatto, Luminita A. Vese |
| 2003 | CVPR | Seeing Beyond Occlusions (and other marvels of a finite lens aperture). | Paolo Favaro, Stefano Soatto |
| 2003 | ICCV | Dynamic Texture Segmentation. | Gianfranco Doretto, Daniel Cremers, Paolo Favaro, Stefano Soatto |
| 2003 | ICCV | On Exploiting Occlusions in Multiple-view Geometry. | Paolo Favaro, Alessandro Duci, Yi Ma, Stefano Soatto |
| 2002 | ECCV | Learning Shape from Defocus. | Paolo Favaro, Stefano Soatto |
| 2002 | ECCV | A Variational Approach to Shape from Defocus. | Hailin Jin, Paolo Favaro |
| 2001 | ICCV | Real-time Virtual Object Insertion. | Paolo Favaro, Hailin Jin, Stefano Soatto |
| 2001 | ICCV | Real-Time Feature Tracking and Outlier Rejection with Changes in Illumination. | Hailin Jin, Paolo Favaro, Stefano Soatto |
| 2001 | ICIAP | A Semi-direct Approach to Structure from Motion. | Paolo Favaro, Hailin Jin, Stefano Soatto |
| 2000 | CVPR | Real-Time 3-D Motion and Structure of Point-Features: A Front-End for Vision-Based Control and Interaction. | Hailin Jin, Paolo Favaro, Stefano Soatto |
| 2000 | CVPR | A Geometric Approach to Blind Deconvolution with Application to Shape from Defocu. | Stefano Soatto, Paolo Favaro |
| 2000 | ECCV | 3-D Motion and Structure from 2-D Motion Causally Integrated over Time: Implementation. | Alessandro Chiuso, Paolo Favaro, Hailin Jin, Stefano Soatto |
| 2000 | ECCV | Shape and Radiance Estimation from the Information-Divergence of Blurred Images. | Paolo Favaro, Stefano Soatto |