DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior

TL;DR

DPoser-X is a diffusion-based model that provides a robust and versatile prior for 3D whole-body human poses, effectively handling complex articulated poses and limited data.

Contribution

We introduce DPoser-X, a novel diffusion model for expressive whole-body pose prior modeling, with a new training strategy and improved performance across multiple benchmarks.

Findings

Outperforms state-of-the-art methods on various pose benchmarks.

Effectively models interdependencies between body parts.

Demonstrates robustness and versatility in diverse pose tasks.

Abstract

We present DPoser-X, a diffusion-based prior model for 3D whole-body human poses. Building a versatile and robust full-body human pose prior remains challenging due to the inherent complexity of articulated human poses and the scarcity of high-quality whole-body pose datasets. To address these limitations, we introduce a Diffusion model as body Pose prior (DPoser) and extend it to DPoser-X for expressive whole-body human pose modeling. Our approach unifies various pose-centric tasks as inverse problems, solving them through variational diffusion sampling. To enhance performance on downstream applications, we introduce a novel truncated timestep scheduling method specifically designed for pose data characteristics. We also propose a masked training mechanism that effectively combines whole-body and part-specific datasets, enabling our model to capture interdependencies between body parts while avoiding overfitting to specific actions. Extensive experiments demonstrate DPoser-X's robustness and versatility across multiple benchmarks for body, hand, face, and full-body pose modeling. Our model consistently outperforms state-of-the-art alternatives, establishing a new benchmark for whole-body human pose prior modeling.