arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.04805cs.GRcs.AI
收藏

Skin Tokens: 一种学习得到的紧凑表示用于统一的自回归 rigging

Skin Tokens: A Learned Compact Representation for Unified Autoregressive Rigging

BNRist, Department of Computer Science and Technology, Tsinghua University(BNRist,计算机科学与技术系,清华大学);Zhili College, Tsinghua University(知礼学院,清华大学)

Jia-peng Zhang, Cheng-Feng Pu, Meng-Hao Guo, Yan-Pei Cao, Shi-Min Hu

AI总结:

SkinTokens通过学习紧凑表示提升皮肤权重准确性,结合自回归框架和强化学习优化骨骼预测,实现更高效的rigging方法。

摘要:

生成3D模型的快速普及在动画管线中创造了一个关键瓶颈:rigging。现有的自动化方法从根本上受到其对skinning方法的限制,将其视为一个不明确的、高维回归任务,这种任务在优化上效率低下且通常与骨骼生成解耦。我们提出这是一个表示问题,并引入SkinTokens:一种学习得到的、紧凑的、离散的表示方法用于skinning权重。通过利用FSQ-CVAE来捕捉skinning的内在稀疏性,我们将任务从连续回归重新表述为一个更具可操作性的token序列预测问题。这种表示方法使TokenRig成为一种统一的自回归框架,该框架将整个rig建模为一个单一的骨骼参数序列和SkinTokens序列,学习骨骼和皮肤变形之间的复杂依赖关系。统一的模型随后可以应用于强化学习阶段,其中定制的几何和语义奖励提高对复杂、非分布资产的泛化能力。定量上,SkinTokens表示在皮肤权重准确性方面比最先进的方法提高了98%-133%,而经过强化学习优化的完整TokenRig框架在骨骼预测方面提高了17%-22%。我们的工作提出了一个统一的生成方法用于rigging,产生了更高的保真度和鲁棒性,为3D内容创作中长期存在的挑战提供了可扩展的解决方案。

英文摘要:

The rapid proliferation of generative 3D models has created a critical bottleneck in animation pipelines: rigging. Existing automated methods are fundamentally limited by their approach to skinning, treating it as an ill-posed, high-dimensional regression task that is inefficient to optimize and is typically decoupled from skeleton generation. We posit this is a representation problem and introduce SkinTokens: a learned, compact, and discrete representation for skinning weights. By leveraging an FSQ-CVAE to capture the intrinsic sparsity of skinning, we reframe the task from continuous regression to a more tractable token sequence prediction problem. This representation enables TokenRig, a unified autoregressive framework that models the entire rig as a single sequence of skeletal parameters and SkinTokens, learning the complicated dependencies between skeletons and skin deformations. The unified model is then amenable to a reinforcement learning stage, where tailored geometric and semantic rewards improve generalization to complex, out-of-distribution assets. Quantitatively, the SkinTokens representation leads to a 98%-133% percents improvement in skinning accuracy over state-of-the-art methods, while the full TokenRig framework, refined with RL, enhances bone prediction by 17%-22%. Our work presents a unified, generative approach to rigging that yields higher fidelity and robustness, offering a scalable solution to a long-standing challenge in 3D content creation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑