Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.00259 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916874991697920 |
|---|---|
| author | Sun, Wentao Xu, Hanqing Wu, Quanyun Zhang, Dedong Chen, Yiping Ma, Lingfei Zelek, John S. Li, Jonathan |
| author_facet | Sun, Wentao Xu, Hanqing Wu, Quanyun Zhang, Dedong Chen, Yiping Ma, Lingfei Zelek, John S. Li, Jonathan |
| contents | We introduce PointGauss, a novel point cloud-guided framework for real-time multi-object segmentation in Gaussian Splatting representations. Unlike existing methods that suffer from prolonged initialization and limited multi-view consistency, our approach achieves efficient 3D segmentation by directly parsing Gaussian primitives through a point cloud segmentation-driven pipeline. The key innovation lies in two aspects: (1) a point cloud-based Gaussian primitive decoder that generates 3D instance masks within 1 minute, and (2) a GPU-accelerated 2D mask rendering system that ensures multi-view consistency. Extensive experiments demonstrate significant improvements over previous state-of-the-art methods, achieving performance gains of 1.89 to 31.78% in multi-view mIoU, while maintaining superior computational efficiency. To address the limitations of current benchmarks (single-object focus, inconsistent 3D evaluation, small scale, and partial coverage), we present DesktopObjects-360, a novel comprehensive dataset for 3D segmentation in radiance fields, featuring: (1) complex multi-object scenes, (2) globally consistent 2D annotations, (3) large-scale training data (over 27 thousand 2D masks), (4) full 360° coverage, and (5) 3D evaluation masks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_00259 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PointGauss: Point Cloud-Guided Multi-Object Segmentation for Gaussian Splatting Sun, Wentao Xu, Hanqing Wu, Quanyun Zhang, Dedong Chen, Yiping Ma, Lingfei Zelek, John S. Li, Jonathan Computer Vision and Pattern Recognition We introduce PointGauss, a novel point cloud-guided framework for real-time multi-object segmentation in Gaussian Splatting representations. Unlike existing methods that suffer from prolonged initialization and limited multi-view consistency, our approach achieves efficient 3D segmentation by directly parsing Gaussian primitives through a point cloud segmentation-driven pipeline. The key innovation lies in two aspects: (1) a point cloud-based Gaussian primitive decoder that generates 3D instance masks within 1 minute, and (2) a GPU-accelerated 2D mask rendering system that ensures multi-view consistency. Extensive experiments demonstrate significant improvements over previous state-of-the-art methods, achieving performance gains of 1.89 to 31.78% in multi-view mIoU, while maintaining superior computational efficiency. To address the limitations of current benchmarks (single-object focus, inconsistent 3D evaluation, small scale, and partial coverage), we present DesktopObjects-360, a novel comprehensive dataset for 3D segmentation in radiance fields, featuring: (1) complex multi-object scenes, (2) globally consistent 2D annotations, (3) large-scale training data (over 27 thousand 2D masks), (4) full 360° coverage, and (5) 3D evaluation masks. |
| title | PointGauss: Point Cloud-Guided Multi-Object Segmentation for Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.00259 |