3D perception

LiDAR scanners and other sensors deliver information about the 3D world around the vehicle. Making sense of this information in terms of drivable space and important objects in 3D is required to develop robust driving system that plan and act safely.

Selected publications

  1. ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation
    Cédric Rommel, Victor Letzelter, Nermin Samet, Renaud Marlet, Matthieu Cord, Patrick Pérez, Eduardo Valle
    Advances in Neural Information Processing Systems (NeurIPS), 2024
    pdf
  2. Train Till You Drop: Towards Stable and Robust Source-free Unsupervised 3D Domain Adaptation
    Bjoern Michele, Alexandre Boulch, Tuan-Hung Vu, Gilles Puy, Renaud Marlet, Nicolas Courty
    European Conference on Computer Vision, 2024
    Project page pdf Code
  3. PAFUSE: Part-based Diffusion for 3D Whole-Body Pose Estimation
    Nermin Samet, Cédric Rommel, David Picard, Eduardo Valle
    ECCV Workshop Towards a Complete Analysis of People Fine-grained Understanding for Real-World Applications (T-CAP), 2024
    pdf Code
  4. Learning Kernel-Modulated Neural Representation for Efficient Light Field Compression
    Jinglei Shi, Yihong Xu, Christine Guillemot
    IEEE Transactions on Image Processing, 2024
    pdf
  5. OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks
    Sophia Sirko-Galouchenko, Alexandre Boulch, Spyros Gidaris, Andrei Bursuc, Antonin Vobecky, Patrick Pérez, Renaud Marlet
    CVPR Workshop on Autonomous Driving (WAD), 2024
    pdf Code
  6. PointBeV: A Sparse Approach to BeV Predictions
    Loïck Chambon, Éloi Zablocki, Mickaël Chen, Florent Bartoccioni, Patrick Pérez, Matthieu Cord
    Computer Vision and Pattern Recognition, 2024
    pdf Code
  7. Three Pillars improving Vision Foundation Model Distillation for Lidar
    Gilles Puy, Spyros Gidaris, Alexandre Boulch, Oriane Siméoni, Corentin Sautier, Patrick Pérez, Andrei Bursuc, Renaud Marlet
    Computer Vision and Pattern Recognition, 2024
    pdf Code
  8. BEVContrast: Self-Supervision in BEV Space for Automotive Lidar Point Clouds
    Corentin Sautier, Gilles Puy, Alexandre Boulch, Renaud Marlet, Vincent Lepetit
    International Conference on 3D Vision (3DV), 2024
    pdf Code
  9. SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptation
    Bjoern Michele, Alexandre Boulch, Gilles Puy, Tuan-Hung Vu, Renaud Marlet and Nicolas Courty
    International Conference on 3D Vision (3DV), 2024
    Project page pdf Code Slides
  10. UNIT: unsupervised Online Instance Segmentation through Time
    Corentin Sautier, Gilles Puy, Alexandre Boulch, Renaud Marlet, Vincent Lepetit
    arXiv, 2024
    pdf Code
  11. POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images
    Antonin Vobecky, Oriane Siméoni, David Hurych, Spyros Gidaris, Andrei Bursuc, Patrick Pérez, Josef Sivic
    Advances in Neural Information Processing Systems (NeurIPS), 2023
    pdf Code
  12. DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusion
    Cédric Rommel, Eduardo Valle, Mickaël Chen, Souhaiel Khalfaoui, Renaud Marlet, Matthieu Cord, Patrick Pérez
    International Conference on Computer Vision (ICCV) Workshop, 2023
    pdf Code
  13. You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentation
    Nermin Samet, Oriane Siméoni, Gilles Puy, Georgy Ponimatkin, Renaud Marlet, and Vincent Lepetit
    International Conference on Computer Vision (ICCV), 2023
    pdf Code
  14. Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation
    Gilles Puy, Alexandre Boulch, and Renaud Marlet
    International Conference on Computer Vision (ICCV), 2023
    pdf Code
  15. ALSO: Automotive Lidar Self-supervision by Occupancy estimation
    Alexandre Boulch, Corentin Sautier, Björn Michele, Gilles Puy, Renaud Marlet
    Computer Vision and Pattern Recognition, 2023
    pdf Code
  16. RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving
    Angelika Ando, Spyros Gidaris, Andrei Bursuc, Gilles Puy, Alexandre Boulch, and Renaud Marlet
    Computer Vision and Pattern Recognition, 2023
    pdf Code
  17. LaRa: Latents and Rays for Multi-Camera Bird's-Eye-View Semantic Segmentation
    Florent Bartoccioni, Éloi Zablocki, Andrei Bursuc, Patrick Pérez, Matthieu Cord, Karteek Alahari
    Conference on Robot Learning, 2022
    pdf Code
  18. LiDARTouch: Monocular metric depth estimation with a few-beam LiDAR
    Florent Bartoccioni, Éloi Zablocki, Patrick Pérez, Matthieu Cord, Karteek Alahari
    Computer Vision and Image Understanding (CVIU), 2022
    pdf Code
  19. Multi-Modal 3D GAN for Urban Scenes
    Loïck Chambon, Mickaël Chen, Tuan-Hung Vu, Alexandre Boulch, Andrei Bursuc, Matthieu Cord, Patrick Pérez
    NeurIPS Machine Learning for Autonomous Driving Workshop, 2022
    pdf Slides
  20. Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation
    Antonin Vobecky, Oriane Siméoni, David Hurych, Spyros Gidaris, Andrei Bursuc, Patrick Pérez, Josef Sivic
    European Conference on Computer Vision (ECCV), 2022oral
    pdf Code
  21. POCO: Point Convolution for Surface Reconstruction
    Alexandre Boulch and Renaud Marlet
    Computer Vision and Pattern Recognition, 2022
    pdf Code
  22. Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data
    Corentin Sautier, Gilles Puy, Spyros Gidaris, Alexandre Boulch, Andrei Bursuc, and Renaud Marlet
    Computer Vision and Pattern Recognition, 2022
    pdf Code
  23. Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentation
    Maximilian Jaritz, Tuan-Hung Vu, Raoul de Charette, Émilie Wirbel, and Patrick Pérez
    IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
    pdf Code
  24. Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Clouds
    Bjoern Michele, Alexandre Boulch, Gilles Puy, Maxime Bucher, and Renaud Marlet
    International Conference on 3D Vision (3DV), 2021
    pdf Code Slides
  25. NeeDrop: Unsupervised Shape Representation from Sparse Point Clouds using Needle Dropping
    Alexandre Boulch, Pierre-Alain Langlois, Gilles Puy, and Renaud Marlet
    International Conference on 3D Vision (3DV), 2021
    pdf Code
  26. PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learning
    Yang Xiao, Yuming Du, Renaud Marlet
    International Conference on 3D Vision (3DV), 2021oral
    Project page pdf Code
  27. PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Clouds
    Anh-Quan Cao, Gilles Puy, Alexandre Boulch, and Renaud Marlet
    International Conference on Computer Vision (ICCV), 2021
    pdf Code
  28. STaRFlow: A SpatioTemporal Recurrent Cell for Lightweight Multi-Frame Optical Flow Estimation
    Pierre Godet, Alexandre Boulch, Aurelien Plyer and Guy Le Besnerais
    International Conference on Pattern Recognition (ICPR), 2020
    pdf Code
  29. FKAConv: Feature-Kernel Alignment for Point Cloud Convolution
    Alexandre Boulch, Gilles Puy, and Renaud Marlet
    Asian Conference on Computer Vision (ACCV), 2020
    pdf Code
  30. FLOT: Scene Flow on Point Clouds guided by Optimal Transport
    Gilles Puy, Alexandre Boulch, and Renaud Marlet
    European Conference on Computer Vision (ECCV), 2020
    pdf Code
  31. ConvPoint: Continuous Convolutions for Point Cloud Processing
    Alexandre Boulch
    Computers & Graphics Journal, 2020
    pdf Code Slides