Mesh Graphormer

04/01/2021
by   Kevin Lin, et al.
0

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

READ FULL TEXT

page 5

page 6

page 8

page 11

page 12

page 13

research
12/17/2020

End-to-End Human Pose and Mesh Reconstruction with Transformers

We present a new method, called MEsh TRansfOrmer (METRO), to reconstruct...
research
04/19/2023

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

This paper presents a simple yet powerful method for 3D human mesh recon...
research
06/11/2021

Bridge the Gap Between Model-based and Model-free Human Reconstruction

It is challenging to directly estimate the geometry of human from a sing...
research
01/31/2019

GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects

Mesh models are a promising approach for encoding the structure of 3D ob...
research
11/24/2022

MPT: Mesh Pre-Training with Transformers for Human Pose and Mesh Reconstruction

We present Mesh Pre-Training (MPT), a new pre-training framework that le...
research
02/15/2022

MeshLeTemp: Leveraging the Learnable Vertex-Vertex Relationship to Generalize Human Pose and Mesh Reconstruction for In-the-Wild Scenes

We present MeshLeTemp, a powerful method for 3D human pose and mesh reco...
research
07/27/2022

Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers

Transformer encoder architectures have recently achieved state-of-the-ar...

Please sign up or login with your details

Forgot password? Click here to reset