LiDAR-HMR: 3D Human Mesh Recovery from LiDAR

Bohao Fan, Wenzhao Zheng, Jianjiang Feng, Jie Zhou
11/20/2023
cs.CV

Official code: soullessrobot/LiDAR-HMR (61 stars, last commit 2025-03-02).

Abstract

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/

View on arXivView PDF

Code Implementations(1)

soullessrobot/LiDAR-HMROfficial100%

Code and data for LiDAR-HMR: 3D Human Mesh Recovery from LiDAR

614C, C++Nov 20, 20231 years ago

Similar Papers

HART: Human Aligned Reconstruction Transformer

86% match1 repo172025

Sampling is Matter: Point-Guided 3D Human Mesh Reconstruction

85% match1 repo752026

Human as Points: Explicit Point-based 3D Human Reconstruction from Single-view RGB Images

84% match1 repo472023

3D Human Pose and Shape Estimation from LiDAR Point Clouds: A Review

84% match1 repo262025

Robust Human Registration with Body Part Segmentation on Noisy Point Clouds

84% match2025

PointHPS: Cascaded 3D Human Pose and Shape Estimation from Point Clouds

83% match1 repo712023

Cite this paper

@article{fan2023lidarhmr,
  title  = {LiDAR-HMR: 3D Human Mesh Recovery from LiDAR},
  author = {Bohao Fan and Wenzhao Zheng and Jianjiang Feng and Jie Zhou},
  year   = {2023},
  eprint = {2311.11971},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2311.11971v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2311.11971.svg)](https://codeofpaper.com/paper/2311.11971)

Discussion