融合扩散模型与图网络，提升3D人体姿态估计精度与鲁棒性
HDiffTG: A Lightweight Hybrid Diffusion-Transformer-GCN Architecture for 3D Human Pose Estimation
- 用Transformer、GCN与扩散模型协同建模时空与骨骼结构
- 在MPI-INF-3DHP上达到最新最优性能，且计算量小
- 适合需高精度与低延迟的实时动作识别场景
我们提出HDiffTG，一种新型3D人体姿态估计方法，将Transformer、图卷积网络（GCN）与扩散模型整合至统一框架。Transformer捕捉全局时空依赖，GCN建模局部骨骼结构，扩散模型通过逐步优化实现精细化调整，实现全局与局部特征的互补平衡。该设计显著提升模型在遮挡和复杂场景下的估计能力。同时，通过轻量化优化与目标函数改进，在不损失性能的前提下降低计算开销。在Human3.6M与MPI-INF-3DHP数据集上的评估表明，HDiffTG在MPI-INF-3DHP上达到当前最优（SOTA）性能，兼具高精度与高效计算特性。模型在噪声与遮挡环境下表现出色。源码与模型已开源于https://github.com/CirceJie/HDiffTG。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。