HaloGS: Loose Coupling of Compact Geometry and Gaussian Splats for 3D Scenes
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_ | 1866918034962120704 |
|---|---|
| author | Jiang, Changjian Ren, Kerui Xu, Linning Chen, Jiong Pang, Jiangmiao Zhang, Yu Dai, Bo Yu, Mulin |
| author_facet | Jiang, Changjian Ren, Kerui Xu, Linning Chen, Jiong Pang, Jiangmiao Zhang, Yu Dai, Bo Yu, Mulin |
| contents | High fidelity 3D reconstruction and rendering hinge on capturing precise geometry while preserving photo realistic detail. Most existing methods either fuse these goals into a single cumbersome model or adopt hybrid schemes whose uniform primitives lead to a trade off between efficiency and fidelity. In this paper, we introduce HaloGS, a dual representation that loosely couples coarse triangles for geometry with Gaussian primitives for appearance, motivated by the lightweight classic geometry representations and their proven efficiency in real world applications. Our design yields a compact yet expressive model capable of photo realistic rendering across both indoor and outdoor environments, seamlessly adapting to varying levels of scene complexity. Experiments on multiple benchmark datasets demonstrate that our method yields both compact, accurate geometry and high fidelity renderings, especially in challenging scenarios where robust geometric structure make a clear difference. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_20267 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HaloGS: Loose Coupling of Compact Geometry and Gaussian Splats for 3D Scenes Jiang, Changjian Ren, Kerui Xu, Linning Chen, Jiong Pang, Jiangmiao Zhang, Yu Dai, Bo Yu, Mulin Computer Vision and Pattern Recognition High fidelity 3D reconstruction and rendering hinge on capturing precise geometry while preserving photo realistic detail. Most existing methods either fuse these goals into a single cumbersome model or adopt hybrid schemes whose uniform primitives lead to a trade off between efficiency and fidelity. In this paper, we introduce HaloGS, a dual representation that loosely couples coarse triangles for geometry with Gaussian primitives for appearance, motivated by the lightweight classic geometry representations and their proven efficiency in real world applications. Our design yields a compact yet expressive model capable of photo realistic rendering across both indoor and outdoor environments, seamlessly adapting to varying levels of scene complexity. Experiments on multiple benchmark datasets demonstrate that our method yields both compact, accurate geometry and high fidelity renderings, especially in challenging scenarios where robust geometric structure make a clear difference. |
| title | HaloGS: Loose Coupling of Compact Geometry and Gaussian Splats for 3D Scenes |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.20267 |