Mesh Graphormer

TL;DR

Mesh Graphormer is a novel model combining graph convolutions and transformers to improve 3D human pose and mesh reconstruction accuracy from single images, outperforming previous methods on multiple benchmarks.

Contribution

The paper introduces Mesh Graphormer, a new approach that integrates graph convolutions with self-attention mechanisms to model both local and global interactions in 3D human mesh reconstruction.

Findings

Outperforms previous state-of-the-art on Human3.6M, 3DPW, and FreiHAND datasets.

Effectively models local and global interactions in 3D mesh reconstruction.

Demonstrates significant accuracy improvements over existing methods.

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