Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

LiDAR-HMR: 3D Human Mesh Recovery from LiDAR

About

In recent years, point cloud perception tasks have been garnering increasing attention. This paper presents the first attempt to estimate 3D human body mesh from sparse LiDAR point clouds. We found that the major challenge in estimating human pose and mesh from point clouds lies in the sparsity, noise, and incompletion of LiDAR point clouds. Facing these challenges, we propose an effective sparse-to-dense reconstruction scheme to reconstruct 3D human mesh. This involves estimating a sparse representation of a human (3D human pose) and gradually reconstructing the body mesh. To better leverage the 3D structural information of point clouds, we employ a cascaded graph transformer (graphormer) to introduce point cloud features during sparse-to-dense reconstruction. Experimental results on three publicly available databases demonstrate the effectiveness of the proposed approach. Code: https://github.com/soullessrobot/LiDAR-HMR/

Bohao Fan, Wenzhao Zheng, Jianjiang Feng, Jie Zhou• 2023

Related benchmarks

TaskDatasetResultRank
3D Human Pose EstimationLiDARHuman26M
MPJPE (mm)76.2
13
3D Human Motion CaptureSLOPER4D
JPE47.7
9
3D Human Motion CaptureNoiseMotion
JPE50.4
8
3D Human Motion CaptureFreeMotion
JPE106.7
8
3D Human Pose EstimationSLOPER4D 7
MPJPE48.76
5
3D Human Pose EstimationWaymo 31
MPJPE68.48
4
Showing 6 of 6 rows

Other info

Code

Follow for update