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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Jiang, Li, Rui, Zhu, Yu, Guo, Rong, Sun, Jinqiu, Zhang, Yanning
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908342901800960
author Wu, Jiang
Li, Rui
Zhu, Yu
Guo, Rong
Sun, Jinqiu
Zhang, Yanning
author_facet Wu, Jiang
Li, Rui
Zhu, Yu
Guo, Rong
Sun, Jinqiu
Zhang, Yanning
contents 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 ill-posed conditions. Sparse2DGS outperforms existing methods by notable margins while being ${2}\times$ faster than the NeRF-based fine-tuning approach.
format Preprint
id arxiv_https___arxiv_org_abs_2504_20378
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sparse2DGS: Geometry-Prioritized Gaussian Splatting for Surface Reconstruction from Sparse Views
Wu, Jiang
Li, Rui
Zhu, Yu
Guo, Rong
Sun, Jinqiu
Zhang, Yanning
Computer Vision and Pattern Recognition
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 ill-posed conditions. Sparse2DGS outperforms existing methods by notable margins while being ${2}\times$ faster than the NeRF-based fine-tuning approach.
title Sparse2DGS: Geometry-Prioritized Gaussian Splatting for Surface Reconstruction from Sparse Views
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.20378