Anymate: A Dataset and Baselines for Learning 3D Object Rigging

TL;DR

This paper introduces Anymate, a large-scale dataset of 3D assets with rigging data, and proposes a learning-based framework that significantly improves automated 3D object rigging and skinning.

Contribution

The paper provides the largest dataset for 3D rigging and skinning, and develops a novel auto-rigging framework with multiple modules that outperform existing methods.

Findings

Models outperform existing methods in rigging accuracy

The dataset is 70 times larger than previous datasets

Proposed framework achieves state-of-the-art results

Abstract

Rigging and skinning are essential steps to create realistic 3D animations, often requiring significant expertise and manual effort. Traditional attempts at automating these processes rely heavily on geometric heuristics and often struggle with objects of complex geometry. Recent data-driven approaches show potential for better generality, but are often constrained by limited training data. We present the Anymate Dataset, a large-scale dataset of 230K 3D assets paired with expert-crafted rigging and skinning information -- 70 times larger than existing datasets. Using this dataset, we propose a learning-based auto-rigging framework with three sequential modules for joint, connectivity, and skinning weight prediction. We systematically design and experiment with various architectures as baselines for each module and conduct comprehensive evaluations on our dataset to compare their performance. Our models significantly outperform existing methods, providing a foundation for comparing future methods in automated rigging and skinning. Code and dataset can be found at https://anymate3d.github.io/.