SkinTokens : A Learned Compact Representation for Unified Autoregressive Rigging
Open Access
- 21 October 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
Abstract
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% relative improvement in skinning-weight L 1 error over state-of-the-art methods, while the full TokenRig framework, refined with RL, improves the skeletal Chamfer distance 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.Keywords
This publication has 33 references indexed in Scilit:
- MagicArticulate: Make Your 3D Models Articulation-Ready2025
- HumanRig: Learning Automatic Rigging for Humanoid Character in a Large Scale Dataset2025
- DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters2025
- TransFusion: Generating long, high fidelity time series using diffusion models with transformersMachine Learning with Applications, 2025
- CTSN: Predicting cloth deformation for skeleton-based characters with a two-stream skinning networkComputational Visual Media, 2024
- Generating diverse clothed 3D human animations via a generative modelComputational Visual Media, 2024
- RoFormer: Enhanced transformer with Rotary Position EmbeddingNeurocomputing, 2023
- TARig: Adaptive template-aware neural rigging for humanoid charactersComputers & Graphics, 2023
- Generalised Dice Overlap as a Deep Learning Loss Function for Highly Unbalanced Segmentations2017
- Rigging with Mixamo2014