以动画师为中心、面向精细细节物体的骨骼生成
Animator-Centric Skeleton Generation on Objects with Fine-Grained Details
把骨骼预测建模为语义感知的自回归 token 序列生成，并用可学习的密度区间模块实现骨骼密度的软控制；这套「语义分组 tokenization + 密度控制」的思路可迁移到其他结构化 3D 输出（如关节层级、部件分解）的可控生成。
原文依据 we introduce a novel semantic-aware tokenization scheme for auto-regressive modeling
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论骨骼生成是驱动 3D 资产动画的关键，但现有深度学习方法仍存在局限：它们无法应对现代模型日益增长的结构复杂度，且可控性极低，这为实际动画工作流造成了主要瓶颈。为此，我们提出一个以动画师为中心的骨骼生成框架，在复杂输入上实现高质量骨骼预测，同时提供直观的控制手段。我们的贡献有三方面。第一，我们构建了一个大规模数据集，包含 82,633 个具有多样且复杂结构的绑定网格。第二，我们提出一种面向自回归建模的新型语义感知分词方案。该方案将骨骼细分为语义上有意义的组，从而有效补充纯几何先验方法，增强对结构复杂度的鲁棒性，并支撑一种关键的控制机制。第三，我们设计了一个可学习的密度区间模块，使动画师能够对骨骼密度施加柔性的直接控制。大量实验表明，我们的框架不仅能为具有挑战性的输入生成高质量骨骼，还成功满足了专业动画师的两项关键需求。我们的工作为更灵活、更高效的动画流程铺平了道路。
英文原文摘要 1297 字符
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. Our work paves the way for more flexible and efficient animation pipelines.