Animator-Centric Skeleton Generation on Objects with Fine-Grained Details

TL;DR

This paper presents an animator-centric skeleton generation framework that handles complex 3D models, offers intuitive control, and introduces a semantic-aware tokenization scheme and a density control module.

Contribution

It introduces a large-scale dataset, a novel semantic-aware tokenization scheme, and a learnable density control module for improved skeleton generation and animator control.

Findings

Successfully generates high-quality skeletons for complex models.

Provides intuitive control handles for animators.

Enhances robustness to structural complexity.

Abstract

Skeleton generation is essential for animating 3D assets, but current deep learning methods remain limited: they cannot handle the growing structural complexity of modern models and offer minimal controllability, creating a major bottleneck for real-world animation workflows. To address this, we propose an animator-centric SG framework that achieves high-quality skeleton prediction on complex inputs while providing intuitive control handles. Our contributions are threefold. First, we curate a large-scale dataset of 82,633 rigged meshes with diverse and complicated structures. Second, we introduce a novel semantic-aware tokenization scheme for auto-regressive modeling. This scheme effectively complements purely geometric prior methods by subdividing bones into semantically meaningful groups, thereby enhancing robustness to structural complexity and enabling a key control mechanism. Third, we design a learnable density interval module that allows animators to exert soft, direct control over bone density. Extensive experiments demonstrate that our framework not only generates high-quality skeletons for challenging inputs but also successfully fulfills two critical requirements from professional animators.