Utonia: Toward One Encoder for All Point Clouds
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912940525879296 |
|---|---|
| author | Zhang, Yujia Wu, Xiaoyang Yang, Yunhan Fan, Xianzhe Li, Han Zhang, Yuechen Huang, Zehao Wang, Naiyan Zhao, Hengshuang |
| author_facet | Zhang, Yujia Wu, Xiaoyang Yang, Yunhan Fan, Xianzhe Li, Han Zhang, Yuechen Huang, Zehao Wang, Naiyan Zhao, Hengshuang |
| contents | We dream of a future where point clouds from all domains can come together to shape a single model that benefits them all. Toward this goal, we present Utonia, a first step toward training a single self-supervised point transformer encoder across diverse domains, spanning remote sensing, outdoor LiDAR, indoor RGB-D sequences, object-centric CAD models, and point clouds lifted from RGB-only videos. Despite their distinct sensing geometries, densities, and priors, Utonia learns a consistent representation space that transfers across domains. This unification improves perception capability while revealing intriguing emergent behaviors that arise only when domains are trained jointly. Beyond perception, we observe that Utonia representations can also benefit embodied and multimodal reasoning: conditioning vision-language-action policies on Utonia features improves robotic manipulation, and integrating them into vision-language models yields gains on spatial reasoning. We hope Utonia can serve as a step toward foundation models for sparse 3D data, and support downstream applications in AR/VR, robotics, and autonomous driving. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_03283 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Utonia: Toward One Encoder for All Point Clouds Zhang, Yujia Wu, Xiaoyang Yang, Yunhan Fan, Xianzhe Li, Han Zhang, Yuechen Huang, Zehao Wang, Naiyan Zhao, Hengshuang Computer Vision and Pattern Recognition We dream of a future where point clouds from all domains can come together to shape a single model that benefits them all. Toward this goal, we present Utonia, a first step toward training a single self-supervised point transformer encoder across diverse domains, spanning remote sensing, outdoor LiDAR, indoor RGB-D sequences, object-centric CAD models, and point clouds lifted from RGB-only videos. Despite their distinct sensing geometries, densities, and priors, Utonia learns a consistent representation space that transfers across domains. This unification improves perception capability while revealing intriguing emergent behaviors that arise only when domains are trained jointly. Beyond perception, we observe that Utonia representations can also benefit embodied and multimodal reasoning: conditioning vision-language-action policies on Utonia features improves robotic manipulation, and integrating them into vision-language models yields gains on spatial reasoning. We hope Utonia can serve as a step toward foundation models for sparse 3D data, and support downstream applications in AR/VR, robotics, and autonomous driving. |
| title | Utonia: Toward One Encoder for All Point Clouds |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.03283 |