A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Pose

TL;DR

This paper introduces GTRS, a lightweight graph transformer-based method for human mesh reconstruction from 2D pose, achieving high accuracy with significantly reduced model size and computational complexity.

Contribution

The paper proposes a novel pose analysis module using graph transformers and a mesh regression approach, enabling efficient and accurate human mesh reconstruction.

Findings

GTRS outperforms state-of-the-art pose-based methods on Human3.6M and 3DPW datasets.

GTRS uses only 10.2% of parameters and 2.5% of FLOPs compared to previous methods.

GTRS demonstrates strong generalization in in-the-wild scenarios.

Abstract

Existing deep learning-based human mesh reconstruction approaches have a tendency to build larger networks in order to achieve higher accuracy. Computational complexity and model size are often neglected, despite being key characteristics for practical use of human mesh reconstruction models (e.g. virtual try-on systems). In this paper, we present GTRS, a lightweight pose-based method that can reconstruct human mesh from 2D human pose. We propose a pose analysis module that uses graph transformers to exploit structured and implicit joint correlations, and a mesh regression module that combines the extracted pose feature with the mesh template to reconstruct the final human mesh. We demonstrate the efficiency and generalization of GTRS by extensive evaluations on the Human3.6M and 3DPW datasets. In particular, GTRS achieves better accuracy than the SOTA pose-based method Pose2Mesh while only using 10.2% of the parameters (Params) and 2.5% of the FLOPs on the challenging in-the-wild 3DPW dataset. Code will be publicly available.