HDiffTG: A Lightweight Hybrid Diffusion-Transformer-GCN Architecture for 3D Human Pose Estimation

TL;DR

HDiffTG is a lightweight hybrid model combining Transformer, GCN, and diffusion techniques to improve 3D human pose estimation accuracy, robustness, and efficiency, especially under occlusions and complex scenarios.

Contribution

It introduces a novel integrated framework that leverages global, local, and optimization techniques for enhanced 3D pose estimation performance.

Findings

Achieves state-of-the-art results on MPI-INF-3DHP dataset.

Demonstrates robustness in noisy and occluded environments.

Maintains computational efficiency with lightweight optimizations.

Abstract

We propose HDiffTG, a novel 3D Human Pose Estimation (3DHPE) method that integrates Transformer, Graph Convolutional Network (GCN), and diffusion model into a unified framework. HDiffTG leverages the strengths of these techniques to significantly improve pose estimation accuracy and robustness while maintaining a lightweight design. The Transformer captures global spatiotemporal dependencies, the GCN models local skeletal structures, and the diffusion model provides step-by-step optimization for fine-tuning, achieving a complementary balance between global and local features. This integration enhances the model's ability to handle pose estimation under occlusions and in complex scenarios. Furthermore, we introduce lightweight optimizations to the integrated model and refine the objective function design to reduce computational overhead without compromising performance. Evaluation results on the Human3.6M and MPI-INF-3DHP datasets demonstrate that HDiffTG achieves state-of-the-art (SOTA) performance on the MPI-INF-3DHP dataset while excelling in both accuracy and computational efficiency. Additionally, the model exhibits exceptional robustness in noisy and occluded environments. Source codes and models are available at https://github.com/CirceJie/HDiffTG