跳到主要导航 跳到搜索 跳到主要内容

Sparse2DGS: Geometry-Prioritized Gaussian Splatting for Surface Reconstruction from Sparse Views

  • Northwestern Polytechnical University Xian

科研成果: 期刊稿件 › 会议文章 › 同行评审

15 引用 (Scopus)

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