PolGS: Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction
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_ | 1866915510970482688 |
|---|---|
| author | Han, Yufei Tie, Bowen Guo, Heng Lyu, Youwei Li, Si Shi, Boxin Jia, Yunpeng Ma, Zhanyu |
| author_facet | Han, Yufei Tie, Bowen Guo, Heng Lyu, Youwei Li, Si Shi, Boxin Jia, Yunpeng Ma, Zhanyu |
| contents | Efficient shape reconstruction for surfaces with complex reflectance properties is crucial for real-time virtual reality. While 3D Gaussian Splatting (3DGS)-based methods offer fast novel view rendering by leveraging their explicit surface representation, their reconstruction quality lags behind that of implicit neural representations, particularly in the case of recovering surfaces with complex reflective reflectance. To address these problems, we propose PolGS, a Polarimetric Gaussian Splatting model allowing fast reflective surface reconstruction in 10 minutes. By integrating polarimetric constraints into the 3DGS framework, PolGS effectively separates specular and diffuse components, enhancing reconstruction quality for challenging reflective materials. Experimental results on the synthetic and real-world dataset validate the effectiveness of our method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_19726 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PolGS: Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction Han, Yufei Tie, Bowen Guo, Heng Lyu, Youwei Li, Si Shi, Boxin Jia, Yunpeng Ma, Zhanyu Computer Vision and Pattern Recognition Efficient shape reconstruction for surfaces with complex reflectance properties is crucial for real-time virtual reality. While 3D Gaussian Splatting (3DGS)-based methods offer fast novel view rendering by leveraging their explicit surface representation, their reconstruction quality lags behind that of implicit neural representations, particularly in the case of recovering surfaces with complex reflective reflectance. To address these problems, we propose PolGS, a Polarimetric Gaussian Splatting model allowing fast reflective surface reconstruction in 10 minutes. By integrating polarimetric constraints into the 3DGS framework, PolGS effectively separates specular and diffuse components, enhancing reconstruction quality for challenging reflective materials. Experimental results on the synthetic and real-world dataset validate the effectiveness of our method. |
| title | PolGS: Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.19726 |