MVGSR: Multi-View Consistency Gaussian Splatting for Robust 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_ | 1866912273457479680 |
|---|---|
| author | Hou, Chenfeng Yeo, Qi Xun Guo, Mengqi Su, Yongxin Li, Yanyan Lee, Gim Hee |
| author_facet | Hou, Chenfeng Yeo, Qi Xun Guo, Mengqi Su, Yongxin Li, Yanyan Lee, Gim Hee |
| contents | 3D Gaussian Splatting (3DGS) has gained significant attention for its high-quality rendering capabilities, ultra-fast training, and inference speeds. However, when we apply 3DGS to surface reconstruction tasks, especially in environments with dynamic objects and distractors, the method suffers from floating artifacts and color errors due to inconsistency from different viewpoints. To address this challenge, we propose Multi-View Consistency Gaussian Splatting for the domain of Robust Surface Reconstruction (\textbf{MVGSR}), which takes advantage of lightweight Gaussian models and a {heuristics-guided distractor masking} strategy for robust surface reconstruction in non-static environments. Compared to existing methods that rely on MLPs for distractor segmentation strategies, our approach separates distractors from static scene elements by comparing multi-view feature consistency, allowing us to obtain precise distractor masks early in training. Furthermore, we introduce a pruning measure based on multi-view contributions to reset transmittance, effectively reducing floating artifacts. Finally, a multi-view consistency loss is applied to achieve high-quality performance in surface reconstruction tasks. Experimental results demonstrate that MVGSR achieves competitive geometric accuracy and rendering fidelity compared to the state-of-the-art surface reconstruction algorithms. More information is available on our project page (https://mvgsr.github.io). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_08093 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MVGSR: Multi-View Consistency Gaussian Splatting for Robust Surface Reconstruction Hou, Chenfeng Yeo, Qi Xun Guo, Mengqi Su, Yongxin Li, Yanyan Lee, Gim Hee Computer Vision and Pattern Recognition 3D Gaussian Splatting (3DGS) has gained significant attention for its high-quality rendering capabilities, ultra-fast training, and inference speeds. However, when we apply 3DGS to surface reconstruction tasks, especially in environments with dynamic objects and distractors, the method suffers from floating artifacts and color errors due to inconsistency from different viewpoints. To address this challenge, we propose Multi-View Consistency Gaussian Splatting for the domain of Robust Surface Reconstruction (\textbf{MVGSR}), which takes advantage of lightweight Gaussian models and a {heuristics-guided distractor masking} strategy for robust surface reconstruction in non-static environments. Compared to existing methods that rely on MLPs for distractor segmentation strategies, our approach separates distractors from static scene elements by comparing multi-view feature consistency, allowing us to obtain precise distractor masks early in training. Furthermore, we introduce a pruning measure based on multi-view contributions to reset transmittance, effectively reducing floating artifacts. Finally, a multi-view consistency loss is applied to achieve high-quality performance in surface reconstruction tasks. Experimental results demonstrate that MVGSR achieves competitive geometric accuracy and rendering fidelity compared to the state-of-the-art surface reconstruction algorithms. More information is available on our project page (https://mvgsr.github.io). |
| title | MVGSR: Multi-View Consistency Gaussian Splatting for Robust Surface Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.08093 |