A Modular Multi-stage Lightweight Graph Transformer Network for Human Pose and Shape Estimation from 2D Human Pose
Year: 2023
Type: preprint
Abstract: In this research, we address the challenge faced by existing deep learning-based human mesh reconstruction methods in balancing accuracy and computational efficiency. These methods typically prioritize accuracy, resulting in large network sizes and excessive computational complexity, which may hinder their practical application in real-world scenarios, such as virtual reality systems. To address this issue, we introduce a modular multi-stage lightweight graph-based transformer network for human pose and shape estimation from 2D human pose, a pose-based human mesh reconstruction approach that prioritizes computational efficiency without sacrificing reconstruction accuracy. Our method consists of a 2D-to-3D lifter module that utilizes graph transformers to analyze structured and implicit joint correlations in 2D human poses, and a mesh regression module that combines the extracted pose features with a mesh template to produce the final human mesh parameters.
Source: arXiv (Cornell University)
Institution: University of North Carolina at Charlotte
Language: English
Subfield: Computational Mechanics
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4318904207