PoseMaster: A Unified 3D Native Framework for Stylized Pose Generation

TL;DR

PoseMaster introduces a unified 3D framework for stylized pose generation that directly uses 3D skeletons, improving accuracy, diversity, and efficiency over traditional cascade methods, and enabling automatic rigging.

Contribution

The paper presents a novel integrated framework for 3D pose stylization that directly leverages 3D skeletons and a large-scale dataset, surpassing existing methods in quality and applicability.

Findings

Outperforms state-of-the-art in qualitative and quantitative metrics.

Enables direct creation of animatable assets with automated skinning.

Improves pose stylization accuracy and diversity.

Abstract

Pose stylization, which aims to synthesize stylized content aligning with target poses, serves as a fundamental task across 2D, 3D, and video domains. In the 3D realm, prevailing approaches typically rely on a cascade pipeline: first manipulating the image pose via 2D foundation models and subsequently lifting it into 3D representations. However, this paradigm limits the precision and diversity of the 3d pose stylization. To this end, we propose a novel paradigm for 3D pose stylization that unifies pose stylization and 3D generation within a cohesive framework. This integration minimizes the risk of cumulative errors and enhances the model's efficiency and effectiveness. In addition, diverging from previous works that typically utilize 2D skeleton images as guidance, we directly utilize the 3D skeleton because it can provide a more accurate representation of 3D spatial and topological relationships, which significantly enhances the model's capacity to achieve richer and more precise pose stylization. Moreover, we develop a scalable data engine to construct a large-scale dataset of ''Image-Skeleton-Mesh'' triplets, enabling the model to jointly learn identity preservation and geometric alignment. Extensive experiments demonstrate that PoseMaster significantly outperforms state-of-the-art methods in both qualitative and quantitative metrics. Owing to the strict spatial alignment between the generated 3D meshes and the conditioning skeletons, PoseMaster enables the direct creation of animatable assets when coupled with automated skinning models, highlighting its compelling potential for automated character rigging.