PanoGS: Gaussian-based Panoptic Segmentation for 3D Open Vocabulary Scene Understanding
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917966594965504 |
|---|---|
| author | Zhai, Hongjia Li, Hai Li, Zhenzhe Pan, Xiaokun He, Yijia Zhang, Guofeng |
| author_facet | Zhai, Hongjia Li, Hai Li, Zhenzhe Pan, Xiaokun He, Yijia Zhang, Guofeng |
| contents | Recently, 3D Gaussian Splatting (3DGS) has shown encouraging performance for open vocabulary scene understanding tasks. However, previous methods cannot distinguish 3D instance-level information, which usually predicts a heatmap between the scene feature and text query. In this paper, we propose PanoGS, a novel and effective 3D panoptic open vocabulary scene understanding approach. Technically, to learn accurate 3D language features that can scale to large indoor scenarios, we adopt the pyramid tri-plane to model the latent continuous parametric feature space and use a 3D feature decoder to regress the multi-view fused 2D feature cloud. Besides, we propose language-guided graph cuts that synergistically leverage reconstructed geometry and learned language cues to group 3D Gaussian primitives into a set of super-primitives. To obtain 3D consistent instance, we perform graph clustering based segmentation with SAM-guided edge affinity computation between different super-primitives. Extensive experiments on widely used datasets show better or more competitive performance on 3D panoptic open vocabulary scene understanding. Project page: \href{https://zju3dv.github.io/panogs}{https://zju3dv.github.io/panogs}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_18107 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PanoGS: Gaussian-based Panoptic Segmentation for 3D Open Vocabulary Scene Understanding Zhai, Hongjia Li, Hai Li, Zhenzhe Pan, Xiaokun He, Yijia Zhang, Guofeng Computer Vision and Pattern Recognition Recently, 3D Gaussian Splatting (3DGS) has shown encouraging performance for open vocabulary scene understanding tasks. However, previous methods cannot distinguish 3D instance-level information, which usually predicts a heatmap between the scene feature and text query. In this paper, we propose PanoGS, a novel and effective 3D panoptic open vocabulary scene understanding approach. Technically, to learn accurate 3D language features that can scale to large indoor scenarios, we adopt the pyramid tri-plane to model the latent continuous parametric feature space and use a 3D feature decoder to regress the multi-view fused 2D feature cloud. Besides, we propose language-guided graph cuts that synergistically leverage reconstructed geometry and learned language cues to group 3D Gaussian primitives into a set of super-primitives. To obtain 3D consistent instance, we perform graph clustering based segmentation with SAM-guided edge affinity computation between different super-primitives. Extensive experiments on widely used datasets show better or more competitive performance on 3D panoptic open vocabulary scene understanding. Project page: \href{https://zju3dv.github.io/panogs}{https://zju3dv.github.io/panogs}. |
| title | PanoGS: Gaussian-based Panoptic Segmentation for 3D Open Vocabulary Scene Understanding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.18107 |