MGSR: 2D/3D Mutual-boosted Gaussian Splatting for High-fidelity Surface Reconstruction under Various Light Conditions
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_ | 1866913951691833344 |
|---|---|
| author | Zhou, Qingyuan Gong, Yuehu Yang, Weidong Li, Jiaze Luo, Yeqi Xu, Baixin Li, Shuhao Fei, Ben He, Ying |
| author_facet | Zhou, Qingyuan Gong, Yuehu Yang, Weidong Li, Jiaze Luo, Yeqi Xu, Baixin Li, Shuhao Fei, Ben He, Ying |
| contents | Novel view synthesis (NVS) and surface reconstruction (SR) are essential tasks in 3D Gaussian Splatting (3D-GS). Despite recent progress, these tasks are often addressed independently, with GS-based rendering methods struggling under diverse light conditions and failing to produce accurate surfaces, while GS-based reconstruction methods frequently compromise rendering quality. This raises a central question: must rendering and reconstruction always involve a trade-off? To address this, we propose MGSR, a 2D/3D Mutual-boosted Gaussian splatting for Surface Reconstruction that enhances both rendering quality and 3D reconstruction accuracy. MGSR introduces two branches--one based on 2D-GS and the other on 3D-GS. The 2D-GS branch excels in surface reconstruction, providing precise geometry information to the 3D-GS branch. Leveraging this geometry, the 3D-GS branch employs a geometry-guided illumination decomposition module that captures reflected and transmitted components, enabling realistic rendering under varied light conditions. Using the transmitted component as supervision, the 2D-GS branch also achieves high-fidelity surface reconstruction. Throughout the optimization process, the 2D-GS and 3D-GS branches undergo alternating optimization, providing mutual supervision. Prior to this, each branch completes an independent warm-up phase, with an early stopping strategy implemented to reduce computational costs. We evaluate MGSR on a diverse set of synthetic and real-world datasets, at both object and scene levels, demonstrating strong performance in rendering and surface reconstruction. Code is available at https://github.com/TsingyuanChou/MGSR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_05182 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MGSR: 2D/3D Mutual-boosted Gaussian Splatting for High-fidelity Surface Reconstruction under Various Light Conditions Zhou, Qingyuan Gong, Yuehu Yang, Weidong Li, Jiaze Luo, Yeqi Xu, Baixin Li, Shuhao Fei, Ben He, Ying Computer Vision and Pattern Recognition Novel view synthesis (NVS) and surface reconstruction (SR) are essential tasks in 3D Gaussian Splatting (3D-GS). Despite recent progress, these tasks are often addressed independently, with GS-based rendering methods struggling under diverse light conditions and failing to produce accurate surfaces, while GS-based reconstruction methods frequently compromise rendering quality. This raises a central question: must rendering and reconstruction always involve a trade-off? To address this, we propose MGSR, a 2D/3D Mutual-boosted Gaussian splatting for Surface Reconstruction that enhances both rendering quality and 3D reconstruction accuracy. MGSR introduces two branches--one based on 2D-GS and the other on 3D-GS. The 2D-GS branch excels in surface reconstruction, providing precise geometry information to the 3D-GS branch. Leveraging this geometry, the 3D-GS branch employs a geometry-guided illumination decomposition module that captures reflected and transmitted components, enabling realistic rendering under varied light conditions. Using the transmitted component as supervision, the 2D-GS branch also achieves high-fidelity surface reconstruction. Throughout the optimization process, the 2D-GS and 3D-GS branches undergo alternating optimization, providing mutual supervision. Prior to this, each branch completes an independent warm-up phase, with an early stopping strategy implemented to reduce computational costs. We evaluate MGSR on a diverse set of synthetic and real-world datasets, at both object and scene levels, demonstrating strong performance in rendering and surface reconstruction. Code is available at https://github.com/TsingyuanChou/MGSR. |
| title | MGSR: 2D/3D Mutual-boosted Gaussian Splatting for High-fidelity Surface Reconstruction under Various Light Conditions |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.05182 |