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

2026-04-22

AI Summary

Existing deep learning approaches struggle to simultaneously achieve high-quality and controllable skeleton generation for structurally complex 3D models, limiting their applicability in animation production. To address this challenge, this work proposes an animator-oriented skeleton generation framework featuring three key innovations: the construction of a large-scale dataset comprising 82,633 rigged mesh models; a semantic-aware autoregressive tokenization scheme; and a learnable density interval module that enables intuitive soft control over bone density. By jointly modeling geometric and semantic priors, the method generates skeletons of both high quality and high controllability on complex 3D assets, effectively meeting the core demands of professional animation pipelines for generation fidelity and user-guided intervention.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation
• Humans and AI: Game Design — Procedural Content Generation & Storytelling

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Web data generation and simulation
• Search and Retrieval-Augmented AI: Agentic search

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.

Problem

• skeleton generation
• structural complexity
• controllability
• 3D animation
• animator-centric

Innovation

• animator-centric
• semantic-aware tokenization
• skeleton generation
• bone density control
• auto-regressive modeling