Diffusion models have demonstrated remarkable success in generative modeling. In this paper, we propose PADS (Pose Analysis by Diffusion Synthesis), a novel framework designed to address various challenges in 3D human pose analysis through a unified pipeline. Central to PADS are two distinctive strategies: i) learning a task-agnostic pose prior using a diffusion synthesis process to effectively capture the kinematic constraints in human pose data, and ii) unifying multiple pose analysis tasks like estimation, completion, denoising, etc, as instances of inverse problems. The learned pose prior will be treated as a regularization imposing on task-specific constraints, guiding the optimization process through a series of conditional denoising steps. PADS represents the first diffusion-based framework for tackling general 3D human pose analysis within the inverse problem framework. Its performance has been validated on different benchmarks, signaling the adaptability and robustness of this pipeline.

翻译：扩散模型在生成式建模中展现了卓越的成功。本文提出PADS（基于扩散合成的人体姿态分析），这是一种新颖的框架，旨在通过统一流程解决三维人体姿态分析中的多种挑战。PADS的核心包含两个独特策略：i）利用扩散合成过程学习任务无关的姿态先验，以有效捕捉人体姿态数据中的运动学约束；ii）将估计、补全、去噪等多种姿态分析任务统一为逆问题的实例。学习到的姿态先验将作为正则化项施加于任务特定约束，通过一系列条件去噪步骤指导优化过程。PADS是首个基于扩散的框架，用于在逆问题框架内解决通用的三维人体姿态分析问题。其性能已在多个基准上得到验证，彰显了该流程的适应性和鲁棒性。