StarPose: 3D Human Pose Estimation via Spatial-Temporal Autoregressive Diffusion

作者：Haoxin Yang, Weihong Chen, Xuemiao Xu, Cheng Xu, Peng Xiao, Cuifeng Sun, Shaoyu Huang, Shengfeng He · 发表于：IEEE Transactions on Circuits and Systems for Video Technology · 年份：2025 · DOI：10.1109/tcsvt.2025.3595900 · 被引用次数：3 · 研究领域：Human Pose and Action Recognition、Gait Recognition and Analysis、Video Surveillance and Tracking Methods

Monocular 3D human pose estimation remains a challenging task due to inherent depth ambiguities and occlusions. Compared to traditional methods based on Transformers or Convolutional Neural Networks (CNNs), recent diffusion-based approaches have shown superior performance, leveraging their probabilistic nature and high-fidelity generation capabilities. However, these methods often fail to account for the spatial and temporal correlations across predicted frames, resulting in limited temporal consistency and inferior accuracy in predicted 3D pose sequences. To address these shortcomings, this paper proposesStarPose, an autoregressive diffusion framework that effectively incorporates historical 3D pose predictions and spatial-temporal physical guidance to significantly enhance both the accuracy and temporal coherence of pose predictions. Unlike existing approaches,StarPosemodels the 2D-to-3D pose mapping as an autoregressive diffusion process. By synergically integrating previously predicted 3D poses with 2D pose inputs via a Historical Pose Integration Module (HPIM), the framework generates rich and informative historical pose embeddings that guide subsequent denoising steps, ensuring temporally consistent predictions. In addition, a fully plug-and-play Spatial-Temporal Physical Guidance (STPG) mechanism is tailored to refine the denoising process in an iterative manner, which further enforces spatial anatomical plausibility and temporal motion dynamics, rendering robust and r...