FastDDHPose: Towards Unified, Efficient, and Disentangled 3D Human Pose Estimation

TL;DR

FastDDHPose introduces a disentangled diffusion-based approach within a unified, efficient framework for 3D human pose estimation, achieving state-of-the-art results and enabling fair comparison and rapid development.

Contribution

The paper proposes Fast3DHPE, a modular framework for 3D HPE, and introduces FastDDHPose, a novel diffusion-based method that models bone distributions explicitly and improves robustness.

Findings

FastDDHPose achieves state-of-the-art performance on Human3.6M and MPI-INF-3DHP.

The Fast3DHPE framework enables fair comparison and significantly improves training efficiency.

FastDDHPose demonstrates strong generalization and robustness in in-the-wild scenarios.

Abstract

Recent approaches for monocular 3D human pose estimation (3D HPE) have achieved leading performance by directly regressing 3D poses from 2D keypoint sequences. Despite the rapid progress in 3D HPE, existing methods are typically trained and evaluated under disparate frameworks, lacking a unified framework for fair comparison. To address these limitations, we propose Fast3DHPE, a modular framework that facilitates rapid reproduction and flexible development of new methods. By standardizing training and evaluation protocols, Fast3DHPE enables fair comparison across 3D human pose estimation methods while significantly improving training efficiency. Within this framework, we introduce FastDDHPose, a Disentangled Diffusion-based 3D Human Pose Estimation method which leverages the strong latent distribution modeling capability of diffusion models to explicitly model the distributions of bone length and bone direction while avoiding further amplification of hierarchical error accumulation. Moreover, we design an efficient Kinematic-Hierarchical Spatial and Temporal Denoiser that encourages the model to focus on kinematic joint hierarchies while avoiding unnecessary modeling of overly complex joint topologies. Extensive experiments on Human3.6M and MPI-INF-3DHP show that the Fast3DHPE framework enables fair comparison of all methods while significantly improving training efficiency. Within this unified framework, FastDDHPose achieves state-of-the-art performance with strong generalization and robustness in in-the-wild scenarios. The framework and models will be released at: https://github.com/Andyen512/Fast3DHPE