摘要
We present a Gaussian Splatting method for surface reconstruction using sparse input views. Previous methods relying on dense views struggle with extremely sparse Structure-from-Motion points for initialization. While learning-based Multi-view Stereo (MVS) provides dense 3D points, directly combining it with Gaussian Splatting leads to suboptimal results due to the ill-posed nature of sparse-view geometric optimization. We propose Sparse2DGS, an MVS-initialized Gaussian Splatting pipeline for complete and accurate reconstruction. Our key insight is to incorporate the geometric-prioritized enhancement schemes, allowing for direct and robust geometric learning under illposed conditions. Sparse2DGS outperforms existing methods by notable margins while being 2× faster than the NeRF-based fine-tuning approach. Code is available at https://github.com/Wuuu3511/Sparse2DGS.
| 源语言 | 英语 |
|---|---|
| 页(从-至) | 11307-11316 |
| 页数 | 10 |
| 期刊 | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
| DOI | |
| 出版状态 | 已出版 - 2025 |
| 活动 | 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2025 - Nashville, 美国 期限: 11 6月 2025 → 15 6月 2025 |
学术指纹
探究 'Sparse2DGS: Geometry-Prioritized Gaussian Splatting for Surface Reconstruction from Sparse Views' 的科研主题。它们共同构成独一无二的学术指纹。引用此
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver