RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assets

TL;DR

RigAnything is a transformer-based autoregressive model that automatically generates skeletons and skinning weights for diverse 3D assets without relying on predefined templates, enabling fast and accurate rigging across many categories.

Contribution

The paper introduces a template-free autoregressive rigging method that effectively models skeleton hierarchies using BFS order and diffusion modeling, outperforming prior auto-rigging approaches.

Findings

Achieves state-of-the-art accuracy on RigNet and Objaverse datasets.

Performs rigging in under a few seconds per shape.

Demonstrates robustness and generalizability across diverse 3D object types.

Abstract

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