AI RESEARCH
Efficient Diffusion-Based 3D Human Pose Estimation with Hierarchical Temporal Pruning
arXiv CS.CV
•
ArXi:2508.21363v3 Announce Type: replace Diffusion models have nstrated strong capabilities in generating high-fidelity 3D human poses, yet their iterative nature and multi-hypothesis requirements incur substantial computational cost. In this paper, we propose an Efficient Diffusion-Based 3D Human Pose Estimation framework with a Hierarchical Temporal Pruning (HTP) strategy, which dynamically prunes redundant pose tokens across both frame and semantic levels while preserving critical motion dynamics.