107 citations · 288 across the 43 of their papers we have counts for
9 papers · 2 filters
ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation
Cédric Rommel, Victor Letzelter, Nermin Samet +4
We propose ManiPose, a manifold-constrained multi-hypothesis model for human-pose 2D-to-3D lifting. We provide theoretical and empirical evidence that, due to the depth ambiguity i…
BEVContrast: Self-Supervision in BEV Space for Automotive Lidar Point Clouds
Corentin Sautier, Gilles Puy, Alexandre Boulch +2
We present a surprisingly simple and efficient method for self-supervision of 3D backbone on automotive Lidar point clouds. We design a contrastive loss between features of Lidar s…
Three Pillars improving Vision Foundation Model Distillation for Lidar
Gilles Puy, Spyros Gidaris, Alexandre Boulch +5
Self-supervised image backbones can be used to address complex 2D tasks (e.g., semantic segmentation, object discovery) very efficiently and with little or no downstream supervisio…
DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusion
Cédric Rommel, Eduardo Valle, Mickaël Chen +4
We present an innovative approach to 3D Human Pose Estimation (3D-HPE) by integrating cutting-edge diffusion models, which have revolutionized diverse fields, but are relatively un…
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 +3
We propose SeedAL, a method to seed active learning for efficient annotation of 3D point clouds for semantic segmentation. Active Learning (AL) iteratively selects relevant data fr…
SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptation
Björn Michele, Alexandre Boulch, Gilles Puy +3
Learning models on one labeled dataset that generalize well on another domain is a difficult task, as several shifts might happen between the data domains. This is notably the case…