RigAnything：面向多样3D资产的免模板自回归绑定
RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assets
AI总结：
RigAnything提出免模板自回归绑定方法，通过BFS顺序和扩散建模生成骨架与蒙皮权重，在多样3D资产上实现快速、高质量且泛化的自动绑定。
摘要：
我们提出了RigAnything，一种新颖的基于自回归Transformer的模型，它通过概率生成关节和骨架拓扑结构，并以免模板的方式分配蒙皮权重，从而使3D资产具备绑定就绪状态。与大多数现有的自动绑定方法不同，这些方法依赖预定义的骨架模板，且仅限于人形等特定类别，RigAnything以自回归方式处理绑定问题，基于全局输入形状和先前预测迭代地预测下一个关节。虽然自回归模型通常用于生成序列数据，但RigAnything扩展了其应用，以有效学习和表示骨架，而骨架本质上是树结构。为实现这一点，我们按广度优先搜索（BFS）顺序组织关节，使骨架能够被定义为3D位置序列和父索引。此外，我们的模型通过利用扩散建模提高了位置预测的准确性，确保关节在层级结构中精确且一致地放置。这种公式化使自回归模型能够高效地捕获骨架内的空间和层级关系。在RigNet和Objaverse数据集上进行端到端训练，RigAnything在包括人形、四足动物、海洋生物、昆虫等多样对象类型上展示了最先进的性能，在质量、鲁棒性、泛化能力和效率方面超越了先前方法。它比现有自动绑定方法实现显著更快的性能，每个形状的绑定在几秒内完成。更多详情请访问我们的网站：https://www.liuisabella.com/RigAnything
英文摘要：
We present RigAnything, a novel autoregressive transformer-based model, which makes 3D assets rig-ready by probabilistically generating joints and skeleton topologies and assigning skinning weights in a template-free manner. Unlike most existing auto-rigging methods, which rely on predefined skeleton templates and are limited to specific categories like humanoid, RigAnything approaches the rigging problem in an autoregressive manner, iteratively predicting the next joint based on the global input shape and the previous prediction. While autoregressive models are typically used to generate sequential data, RigAnything extends its application to effectively learn and represent skeletons, which are inherently tree structures. To achieve this, we organize the joints in a breadth-first search (BFS) order, enabling the skeleton to be defined as a sequence of 3D locations and the parent index. Furthermore, our model improves the accuracy of position prediction by leveraging diffusion modeling, ensuring precise and consistent placement of joints within the hierarchy. This formulation allows the autoregressive model to efficiently capture both spatial and hierarchical relationships within the skeleton. Trained end-to-end on both RigNet and Objaverse datasets, RigAnything demonstrates state-of-the-art performance across diverse object types, including humanoids, quadrupeds, marine creatures, insects, and many more, surpassing prior methods in quality, robustness, generalizability, and efficiency. It achieves significantly faster performance than existing auto-rigging methods, completing rigging in under a few seconds per shape. Please check our website for more details: https://www.liuisabella.com/RigAnything
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。
