Part Segmentation and Motion Estimation for Articulated Objects with Dynamic 3D Gaussians


Jun-Jee Chao (University of Minnesota), Qingyuan Jiang (University of Minnesota), Volkan Isler (University of Texas at Austin)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)Supplementary

Abstract

Part segmentation and motion estimation are two fundamental problems for articulated object modeling. In this paper, we present a method to solve these two problems jointly from a sequence of observed point clouds of a single articulated object. The main challenge in our problem setting is that the point clouds are not assumed to be generated by a fixed set of moving points. Instead, each point cloud in the sequence could be an arbitrary sampling of the object surface at that particular time step. Such scenarios occur when the object undergoes major occlusions, or if the dataset is collected using measurements from multiple sensors asynchronously. In these scenarios, methods that rely on tracking point correspondences are not appropriate. We present an alternative approach by representing the object as a collection of simple building blocks modeled as 3D Gaussians. With our representation, part segmentation is achieved by assigning the observed points to the Gaussians. Moreover, the transformation of each point across time can be obtained by following the poses of the assigned Gaussian. Experiments show that our method outperforms existing methods that solely rely on finding point correspondences. Additionally, we extend existing datasets to emulate real-world scenarios by considering viewpoint occlusions. We demonstrate that our method is more robust to missing points as compared to existing approaches on these challenging datasets, even when some parts are completely occluded in some time-steps. Notably, our part segmentation outperforms the state-of-the-art method by 13% on occluded point clouds. Project page: https://giles200619.github.io/gsart_website/

Citation

@inproceedings{Chao_2025_BMVC,
author    = {Jun-Jee Chao and Qingyuan Jiang and Volkan Isler},
title     = {Part Segmentation and Motion Estimation for Articulated Objects with Dynamic 3D Gaussians},
booktitle = {36th British Machine Vision Conference 2025, {BMVC} 2025, Sheffield, UK, November 24-27, 2025},
publisher = {BMVA},
year      = {2025},
url       = {https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_12/paper.pdf}
}


Copyright © 2025 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection