Mesh Graphormer

Kevin Lin, Lijuan Wang, Zicheng Liu
4/1/2021
cs.CV

Official code: microsoft/MeshGraphormer (427 stars, last commit 2023-07-06).

Abstract

We present a graph-convolution-reinforced transformer, named Mesh Graphormer, for 3D human pose and mesh reconstruction from a single image. Recently both transformers and graph convolutional neural networks (GCNNs) have shown promising progress in human mesh reconstruction. Transformer-based approaches are effective in modeling non-local interactions among 3D mesh vertices and body joints, whereas GCNNs are good at exploiting neighborhood vertex interactions based on a pre-specified mesh topology. In this paper, we study how to combine graph convolutions and self-attentions in a transformer to model both local and global interactions. Experimental results show that our proposed method, Mesh Graphormer, significantly outperforms the previous state-of-the-art methods on multiple benchmarks, including Human3.6M, 3DPW, and FreiHAND datasets. Code and pre-trained models are available at https://github.com/microsoft/MeshGraphormer

View on arXivView PDF

Code Implementations(1)

microsoft/MeshGraphormerOfficial100%

Research code of ICCV 2021 paper "Mesh Graphormer"

42756Shell, PythonAug 1, 20213 years ago

Similar Papers

Multi-hop graph transformer network for 3D human pose estimation

87% match1 repo32024

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

87% match1 repo752023

A Modular Multi-stage Lightweight Graph Transformer Network for Human Pose and Shape Estimation from 2D Human Pose

86% match2023

GATOR: Graph-Aware Transformer with Motion-Disentangled Regression for Human Mesh Recovery from a 2D Pose

85% match1 repo272023

Adaptive graph Kolmogorov-Arnold network for 3D human pose estimation

85% match1 repo52025

Flexible graph convolutional network for 3D human pose estimation

84% match1 repo72024

Cite this paper

@article{lin2021mesh,
  title  = {Mesh Graphormer},
  author = {Kevin Lin and Lijuan Wang and Zicheng Liu},
  year   = {2021},
  eprint = {2104.00272},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2104.00272}
}

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/2104.00272.svg)](https://codeofpaper.com/paper/2104.00272)

Discussion