MeshPose: Unifying DensePose and 3D Body Mesh reconstruction

Eric-Tuan Lê, Antonis Kakolyris, Petros Koutras, Himmy Tam, Efstratios Skordos +3 more
2/9/2026

No official code found. Best implementation: Snapchat/MeshPose (27 stars, last commit 2024-10-21).

Abstract

DensePose provides a pixel-accurate association of images with 3D mesh coordinates, but does not provide a 3D mesh, while Human Mesh Reconstruction (HMR) systems have high 2D reprojection error, as measured by DensePose localization metrics. In this work we introduce MeshPose to jointly tackle DensePose and HMR. For this we first introduce new losses that allow us to use weak DensePose supervision to accurately localize in 2D a subset of the mesh vertices (‘VertexPose’). We then lift these vertices to 3D, yielding a low-poly body mesh (‘MeshPose’). Our system is trained in an end -to-end manner and is the first HMR method to attain competitive DensePose accuracy, while also being lightweight and amenable to efficient inference, making it suitable for real-time AR applications.

View on arXivView PDF

Code Implementations(1)

Snapchat/MeshPoseCommunity100%
276PythonOct 1, 20242 years agoNOASSERTION

Similar Papers

PoI: A Filter to Extract Pixel of Interest from Novel Views for Scene Coordinate Regression

82% match2025

Rethinking Pose Refinement in 3D Gaussian Splatting under Pose Prior and Geometric Uncertainty

82% match1 repo342026

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

82% match1 repo752026

GeomGS: LiDAR-Guided Geometry-Aware Gaussian Splatting for Robot Localization

82% match2025

HS-SLAM: Hybrid Representation with Structural Supervision for Improved Dense SLAM

82% match2025

Latent-Info and Low-Dimensional Learning for Human Mesh Recovery and Parallel Optimization

81% match2025

Cite this paper

@article{l2026meshpose,
  title  = {MeshPose: Unifying DensePose and 3D Body Mesh reconstruction},
  author = {Eric-Tuan Lê and Antonis Kakolyris and Petros Koutras and Himmy Tam and Efstratios Skordos and George Papandreou and R. A. Guler and Iasonas Kokkinos},
  year   = {2026},
  eprint = {2406.10180},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/pdf/2406.10180},
  journal = {CVPR 2024 2024}
}

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/2406.10180.svg)](https://codeofpaper.com/paper/2406.10180)

Discussion