Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Patrick Pérez

Patrick Pérez

LiDARTouch: Monocular metric depth estimation with a few-beam LiDAR


Sep 08, 2021
Florent Bartoccioni, Éloi Zablocki, Patrick Pérez, Matthieu Cord, Karteek Alahari

Figure 1 for LiDARTouch: Monocular metric depth estimation with a few-beam LiDAR
Figure 2 for LiDARTouch: Monocular metric depth estimation with a few-beam LiDAR
Figure 3 for LiDARTouch: Monocular metric depth estimation with a few-beam LiDAR
Figure 4 for LiDARTouch: Monocular metric depth estimation with a few-beam LiDAR
* Preprint. Under review 
  Access Paper or Ask Questions

Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic Segmentation


Aug 16, 2021
Antoine Saporta, Tuan-Hung Vu, Matthieu Cord, Patrick Pérez

Figure 1 for Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic Segmentation
Figure 2 for Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic Segmentation
Figure 3 for Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic Segmentation
Figure 4 for Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic Segmentation
* Accepted at the 2021 International Conference on Computer Vision (ICCV) 
  Access Paper or Ask Questions

Large-Scale Unsupervised Object Discovery


Jun 12, 2021
Huy V. Vo, Elena Sizikova, Cordelia Schmid, Patrick Pérez, Jean Ponce

Figure 1 for Large-Scale Unsupervised Object Discovery
Figure 2 for Large-Scale Unsupervised Object Discovery
Figure 3 for Large-Scale Unsupervised Object Discovery
Figure 4 for Large-Scale Unsupervised Object Discovery
* 16 pages 
  Access Paper or Ask Questions

Semantic Palette: Guiding Scene Generation with Class Proportions


Jun 03, 2021
Guillaume Le Moing, Tuan-Hung Vu, Himalaya Jain, Patrick Pérez, Matthieu Cord

Figure 1 for Semantic Palette: Guiding Scene Generation with Class Proportions
Figure 2 for Semantic Palette: Guiding Scene Generation with Class Proportions
Figure 3 for Semantic Palette: Guiding Scene Generation with Class Proportions
Figure 4 for Semantic Palette: Guiding Scene Generation with Class Proportions
* Accepted to IEEE CVPR 2021 
  Access Paper or Ask Questions

Neural Monocular 3D Human Motion Capture with Physical Awareness


May 03, 2021
Soshi Shimada, Vladislav Golyanik, Weipeng Xu, Patrick Pérez, Christian Theobalt

Figure 1 for Neural Monocular 3D Human Motion Capture with Physical Awareness
Figure 2 for Neural Monocular 3D Human Motion Capture with Physical Awareness
Figure 3 for Neural Monocular 3D Human Motion Capture with Physical Awareness
Figure 4 for Neural Monocular 3D Human Motion Capture with Physical Awareness

  Access Paper or Ask Questions

Multi-View Radar Semantic Segmentation


Mar 30, 2021
Arthur Ouaknine, Alasdair Newson, Patrick Pérez, Florence Tupin, Julien Rebut

Figure 1 for Multi-View Radar Semantic Segmentation
Figure 2 for Multi-View Radar Semantic Segmentation
Figure 3 for Multi-View Radar Semantic Segmentation
Figure 4 for Multi-View Radar Semantic Segmentation
* 15 pages, 8 figures. Preprint. Under review 
  Access Paper or Ask Questions

StyleLess layer: Improving robustness for real-world driving


Mar 25, 2021
Julien Rebut, Andrei Bursuc, Patrick Pérez

Figure 1 for StyleLess layer: Improving robustness for real-world driving
Figure 2 for StyleLess layer: Improving robustness for real-world driving
Figure 3 for StyleLess layer: Improving robustness for real-world driving
Figure 4 for StyleLess layer: Improving robustness for real-world driving
* 6 pages, 6 figures, 2 tables 
  Access Paper or Ask Questions

Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentation


Jan 18, 2021
Maximilian Jaritz, Tuan-Hung Vu, Raoul de Charette, Émilie Wirbel, Patrick Pérez

Figure 1 for Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentation
Figure 2 for Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentation
Figure 3 for Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentation
Figure 4 for Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentation
* arXiv admin note: text overlap with arXiv:1911.12676 
  Access Paper or Ask Questions

Explainability of vision-based autonomous driving systems: Review and challenges


Jan 13, 2021
Éloi Zablocki, Hédi Ben-Younes, Patrick Pérez, Matthieu Cord

Figure 1 for Explainability of vision-based autonomous driving systems: Review and challenges
Figure 2 for Explainability of vision-based autonomous driving systems: Review and challenges
Figure 3 for Explainability of vision-based autonomous driving systems: Review and challenges
Figure 4 for Explainability of vision-based autonomous driving systems: Review and challenges
* submitted to IJCV 
  Access Paper or Ask Questions

Online Bag-of-Visual-Words Generation for Unsupervised Representation Learning


Dec 21, 2020
Spyros Gidaris, Andrei Bursuc, Gilles Puy, Nikos Komodakis, Matthieu Cord, Patrick Pérez

Figure 1 for Online Bag-of-Visual-Words Generation for Unsupervised Representation Learning
Figure 2 for Online Bag-of-Visual-Words Generation for Unsupervised Representation Learning
Figure 3 for Online Bag-of-Visual-Words Generation for Unsupervised Representation Learning
Figure 4 for Online Bag-of-Visual-Words Generation for Unsupervised Representation Learning
* Technical report. Code at https://github.com/valeoai/obow 
  Access Paper or Ask Questions

Artificial Dummies for Urban Dataset Augmentation


Dec 15, 2020
Antonín Vobecký, David Hurych, Michal Uřičář, Patrick Pérez, Josef Šivic

Figure 1 for Artificial Dummies for Urban Dataset Augmentation
Figure 2 for Artificial Dummies for Urban Dataset Augmentation
Figure 3 for Artificial Dummies for Urban Dataset Augmentation
Figure 4 for Artificial Dummies for Urban Dataset Augmentation
* Accepted to AAAI 2021 
  Access Paper or Ask Questions

Confidence Estimation via Auxiliary Models


Dec 11, 2020
Charles Corbière, Nicolas Thome, Antoine Saporta, Tuan-Hung Vu, Matthieu Cord, Patrick Pérez

Figure 1 for Confidence Estimation via Auxiliary Models
Figure 2 for Confidence Estimation via Auxiliary Models
Figure 3 for Confidence Estimation via Auxiliary Models
Figure 4 for Confidence Estimation via Auxiliary Models
* Under review at TPAMI 
  Access Paper or Ask Questions

Driving Behavior Explanation with Multi-level Fusion


Dec 09, 2020
Hédi Ben-Younes, Éloi Zablocki, Patrick Pérez, Matthieu Cord

Figure 1 for Driving Behavior Explanation with Multi-level Fusion
Figure 2 for Driving Behavior Explanation with Multi-level Fusion
Figure 3 for Driving Behavior Explanation with Multi-level Fusion
Figure 4 for Driving Behavior Explanation with Multi-level Fusion
* Accepted at NeurIPS Workshop ML4AD 2020 
  Access Paper or Ask Questions

Detecting 32 Pedestrian Attributes for Autonomous Vehicles


Dec 04, 2020
Taylor Mordan, Matthieu Cord, Patrick Pérez, Alexandre Alahi

Figure 1 for Detecting 32 Pedestrian Attributes for Autonomous Vehicles
Figure 2 for Detecting 32 Pedestrian Attributes for Autonomous Vehicles
Figure 3 for Detecting 32 Pedestrian Attributes for Autonomous Vehicles
Figure 4 for Detecting 32 Pedestrian Attributes for Autonomous Vehicles
* Submission to IEEE Transactions on Intelligent Transportation Systems (T-ITS) 
  Access Paper or Ask Questions

PIE: Portrait Image Embedding for Semantic Control


Sep 20, 2020
Ayush Tewari, Mohamed Elgharib, Mallikarjun B R., Florian Bernard, Hans-Peter Seidel, Patrick Pérez, Michael Zollhöfer, Christian Theobalt

Figure 1 for PIE: Portrait Image Embedding for Semantic Control
Figure 2 for PIE: Portrait Image Embedding for Semantic Control
Figure 3 for PIE: Portrait Image Embedding for Semantic Control
Figure 4 for PIE: Portrait Image Embedding for Semantic Control
* To appear in SIGGRAPH Asia 2020. Project webpage: https://gvv.mpi-inf.mpg.de/projects/PIE/ 
  Access Paper or Ask Questions

VRUNet: Multi-Task Learning Model for Intent Prediction of Vulnerable Road Users


Jul 10, 2020
Adithya Ranga, Filippo Giruzzi, Jagdish Bhanushali, Emilie Wirbel, Patrick Pérez, Tuan-Hung Vu, Xavier Perrotton

Figure 1 for VRUNet: Multi-Task Learning Model for Intent Prediction of Vulnerable Road Users
Figure 2 for VRUNet: Multi-Task Learning Model for Intent Prediction of Vulnerable Road Users
Figure 3 for VRUNet: Multi-Task Learning Model for Intent Prediction of Vulnerable Road Users
Figure 4 for VRUNet: Multi-Task Learning Model for Intent Prediction of Vulnerable Road Users
* This paper is reprinted from, "VRUNet: Multi-Task Learning Model for Intent Prediction of Vulnerable Road Users, IS&T Electronic Imaging: Autonomous Vehicles and Machines 2020 Proceedings, (IS&T, Springfield, VA, 2020) page 109-1-10. DOI: 10.2352/ISSN.2470-1173.2020.16.AVM-109." Reprinted with permission of The Society for Imaging Science and Technology, holders of the 2020 copyright 
  Access Paper or Ask Questions

Toward unsupervised, multi-object discovery in large-scale image collections


Jul 06, 2020
Huy V. Vo, Patrick Pérez, Jean Ponce

Figure 1 for Toward unsupervised, multi-object discovery in large-scale image collections
Figure 2 for Toward unsupervised, multi-object discovery in large-scale image collections
Figure 3 for Toward unsupervised, multi-object discovery in large-scale image collections
Figure 4 for Toward unsupervised, multi-object discovery in large-scale image collections
* Accepted for publication in ECCV 2020 
  Access Paper or Ask Questions

Spherical Perspective on Learning with Batch Norm


Jun 23, 2020
Simon Roburin, Yann de Mont-Marin, Andrei Bursuc, Renaud Marlet, Patrick Pérez, Mathieu Aubry

Figure 1 for Spherical Perspective on Learning with Batch Norm
Figure 2 for Spherical Perspective on Learning with Batch Norm
Figure 3 for Spherical Perspective on Learning with Batch Norm
Figure 4 for Spherical Perspective on Learning with Batch Norm

  Access Paper or Ask Questions

ESL: Entropy-guided Self-supervised Learning for Domain Adaptation in Semantic Segmentation


Jun 15, 2020
Antoine Saporta, Tuan-Hung Vu, Matthieu Cord, Patrick Pérez

Figure 1 for ESL: Entropy-guided Self-supervised Learning for Domain Adaptation in Semantic Segmentation
Figure 2 for ESL: Entropy-guided Self-supervised Learning for Domain Adaptation in Semantic Segmentation
Figure 3 for ESL: Entropy-guided Self-supervised Learning for Domain Adaptation in Semantic Segmentation
Figure 4 for ESL: Entropy-guided Self-supervised Learning for Domain Adaptation in Semantic Segmentation
* Accepted at the CVPR 2020 Workshop on Scalability in Autonomous Driving 
  Access Paper or Ask Questions

Photo style transfer with consistency losses


May 09, 2020
Xu Yao, Gilles Puy, Patrick Pérez

Figure 1 for Photo style transfer with consistency losses
Figure 2 for Photo style transfer with consistency losses
Figure 3 for Photo style transfer with consistency losses
Figure 4 for Photo style transfer with consistency losses
* In 2019 IEEE International Conference on Image Processing (ICIP) (pp. 2314-2318). IEEE 
  Access Paper or Ask Questions

BUDA: Boundless Unsupervised Domain Adaptation in Semantic Segmentation


Apr 02, 2020
Maxime Bucher, Tuan-Hung Vu, Matthieu Cord, Patrick Pérez

Figure 1 for BUDA: Boundless Unsupervised Domain Adaptation in Semantic Segmentation
Figure 2 for BUDA: Boundless Unsupervised Domain Adaptation in Semantic Segmentation
Figure 3 for BUDA: Boundless Unsupervised Domain Adaptation in Semantic Segmentation
Figure 4 for BUDA: Boundless Unsupervised Domain Adaptation in Semantic Segmentation

  Access Paper or Ask Questions

StyleRig: Rigging StyleGAN for 3D Control over Portrait Images


Mar 31, 2020
Ayush Tewari, Mohamed Elgharib, Gaurav Bharaj, Florian Bernard, Hans-Peter Seidel, Patrick Pérez, Michael Zollhöfer, Christian Theobalt

Figure 1 for StyleRig: Rigging StyleGAN for 3D Control over Portrait Images
Figure 2 for StyleRig: Rigging StyleGAN for 3D Control over Portrait Images
Figure 3 for StyleRig: Rigging StyleGAN for 3D Control over Portrait Images
Figure 4 for StyleRig: Rigging StyleGAN for 3D Control over Portrait Images
* CVPR 2020 (Oral). Project page: https://gvv.mpi-inf.mpg.de/projects/StyleRig/ 
  Access Paper or Ask Questions

Learning Representations by Predicting Bags of Visual Words


Feb 27, 2020
Spyros Gidaris, Andrei Bursuc, Nikos Komodakis, Patrick Pérez, Matthieu Cord

Figure 1 for Learning Representations by Predicting Bags of Visual Words
Figure 2 for Learning Representations by Predicting Bags of Visual Words
Figure 3 for Learning Representations by Predicting Bags of Visual Words
Figure 4 for Learning Representations by Predicting Bags of Visual Words
* Accepted to CVPR2020 
  Access Paper or Ask Questions

Deep Reinforcement Learning for Autonomous Driving: A Survey


Feb 02, 2020
B Ravi Kiran, Ibrahim Sobh, Victor Talpaert, Patrick Mannion, Ahmad A. Al Sallab, Senthil Yogamani, Patrick Pérez

Figure 1 for Deep Reinforcement Learning for Autonomous Driving: A Survey
Figure 2 for Deep Reinforcement Learning for Autonomous Driving: A Survey
Figure 3 for Deep Reinforcement Learning for Autonomous Driving: A Survey
Figure 4 for Deep Reinforcement Learning for Autonomous Driving: A Survey

  Access Paper or Ask Questions

Scattering Features for Multimodal Gait Recognition


Jan 23, 2020
Srđan Kitić, Gilles Puy, Patrick Pérez, Philippe Gilberton

Figure 1 for Scattering Features for Multimodal Gait Recognition
Figure 2 for Scattering Features for Multimodal Gait Recognition
Figure 3 for Scattering Features for Multimodal Gait Recognition
Figure 4 for Scattering Features for Multimodal Gait Recognition
* Published at IEEE GlobalSIP 2017 
  Access Paper or Ask Questions

QUEST: Quantized embedding space for transferring knowledge


Dec 03, 2019
Himalaya Jain, Spyros Gidaris, Nikos Komodakis, Patrick Pérez, Matthieu Cord

Figure 1 for QUEST: Quantized embedding space for transferring knowledge
Figure 2 for QUEST: Quantized embedding space for transferring knowledge
Figure 3 for QUEST: Quantized embedding space for transferring knowledge
Figure 4 for QUEST: Quantized embedding space for transferring knowledge

  Access Paper or Ask Questions

xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation


Nov 28, 2019
Maximilian Jaritz, Tuan-Hung Vu, Raoul de Charette, Émilie Wirbel, Patrick Pérez

Figure 1 for xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation
Figure 2 for xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation
Figure 3 for xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation
Figure 4 for xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation
* For a demo video, see http://tiny.cc/xmuda 
  Access Paper or Ask Questions

This dataset does not exist: training models from generated images


Nov 07, 2019
Victor Besnier, Himalaya Jain, Andrei Bursuc, Matthieu Cord, Patrick Pérez

Figure 1 for This dataset does not exist: training models from generated images
Figure 2 for This dataset does not exist: training models from generated images
Figure 3 for This dataset does not exist: training models from generated images
Figure 4 for This dataset does not exist: training models from generated images

  Access Paper or Ask Questions

Addressing Failure Prediction by Learning Model Confidence


Oct 26, 2019
Charles Corbière, Nicolas Thome, Avner Bar-Hen, Matthieu Cord, Patrick Pérez

Figure 1 for Addressing Failure Prediction by Learning Model Confidence
Figure 2 for Addressing Failure Prediction by Learning Model Confidence
Figure 3 for Addressing Failure Prediction by Learning Model Confidence
Figure 4 for Addressing Failure Prediction by Learning Model Confidence
* NeurIPS 2019 (accepted) 
  Access Paper or Ask Questions