kevinqu7/famos-model

FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations

Kevin Qu^1,2, Tao Sun¹, Massimiliano Viola¹, Liyuan Zhu¹, Zhizhuo Zhou¹, Sayan Deb Sarkar¹, Konrad Schindler², Iro Armeni¹

¹Stanford University          ²ETH Zurich

We present FAMOS, a feed-forward model that predicts movable-part segmentation and joint parameters from a sparse, unordered set of partial point clouds.

This repository hosts the released FAMOS checkpoint. It contains the weights of the Multi-state Articulation Transformer. FAMOS additionally requires the frozen PartField backbone, whose checkpoint is distributed separately under NVIDIA's license.

More details can be found in our GitHub repository.

Citation

@article{qu2026famos,
    title={FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations},
    author={Kevin Qu and Tao Sun and Massimiliano Viola and Liyuan Zhu and Zhizhuo Zhou and Sayan Deb Sarkar and Konrad Schindler and Iro Armeni},
    journal={arXiv preprint arXiv:2609.20817},
    year={2026}
}