LiDAR-HMR: 3D Human Mesh Recovery from LiDAR
It addresses 3D human mesh recovery from LiDAR data, a domain-specific task with incremental improvements in handling sparse point clouds.
This paper tackles the problem of estimating 3D human body mesh from sparse LiDAR point clouds, which are challenging due to sparsity, noise, and incompletion, and achieves effective reconstruction as demonstrated on three public databases.
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/