HEIR: Learning Graph-Based Motion Hierarchies

We propose a general hierarchical motion modeling method that learns structured, interpretable motion relationships directly from data. Our method represents observed motions using graph-based hierarchies, explicitly decomposing global absolute motions into parent-inherited patterns and local motion residuals. We formulate hierarchy inference as a differentiable graph learning problem, where vertices represent elemental motions and directed edges capture learned parent-child dependencies through graph neural networks. We evaluate our hierarchical reconstruction approach on three examples: 1D translational motion, 2D rotational motion, and dynamic 3D scene deformation via Gaussian splatting. Experimental results show that our method reconstructs the intrinsic motion hierarchy in 1D and 2D cases, and produces more realistic and interpretable deformations compared to the baseline on dynamic 3D Gaussian splatting scenes.

First authors with equal contribution. Please cite as

@inproceedings{zheng2025heir,
    author = {Zheng, Cheng and Koch, William and Li, Baiang and Heide, Felix},
    title = {HEIR: Learning Graph-Based Motion Hierarchies},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    year = {2025},
}

William Koch*, Cheng Zheng*, Baiang Li, Felix Heide. 2025. "HEIR: Learning Graph-Based Motion Hierarchies". NeurIPS. https://arxiv.org/pdf/2510.26786