Anymate: A Dataset and Baselines for Learning 3D Object Rigging
This work addresses the need for efficient 3D animation creation for animators and developers, though it is incremental as it builds on data-driven approaches with a larger dataset.
The authors tackled the problem of automating 3D object rigging and skinning, which is labor-intensive and challenging for complex geometries, by introducing the Anymate Dataset with 230K assets and a learning-based framework that significantly outperforms existing methods.
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/.