SolidGS: Consolidating Gaussian Surfel Splatting for Sparse-View Surface Reconstruction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shen, Zhuowen, Liu, Yuan, Chen, Zhang, Li, Zhong, Wang, Jiepeng, Liang, Yongqing, Yu, Zhengming, Zhang, Jingdong, Xu, Yi, Schaefer, Scott, Li, Xin, Wang, Wenping
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913620562018304
author Shen, Zhuowen
Liu, Yuan
Chen, Zhang
Li, Zhong
Wang, Jiepeng
Liang, Yongqing
Yu, Zhengming
Zhang, Jingdong
Xu, Yi
Schaefer, Scott
Li, Xin
Wang, Wenping
author_facet Shen, Zhuowen
Liu, Yuan
Chen, Zhang
Li, Zhong
Wang, Jiepeng
Liang, Yongqing
Yu, Zhengming
Zhang, Jingdong
Xu, Yi
Schaefer, Scott
Li, Xin
Wang, Wenping
contents Gaussian splatting has achieved impressive improvements for both novel-view synthesis and surface reconstruction from multi-view images. However, current methods still struggle to reconstruct high-quality surfaces from only sparse view input images using Gaussian splatting. In this paper, we propose a novel method called SolidGS to address this problem. We observed that the reconstructed geometry can be severely inconsistent across multi-views, due to the property of Gaussian function in geometry rendering. This motivates us to consolidate all Gaussians by adopting a more solid kernel function, which effectively improves the surface reconstruction quality. With the additional help of geometrical regularization and monocular normal estimation, our method achieves superior performance on the sparse view surface reconstruction than all the Gaussian splatting methods and neural field methods on the widely used DTU, Tanks-and-Temples, and LLFF datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2412_15400
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SolidGS: Consolidating Gaussian Surfel Splatting for Sparse-View Surface Reconstruction
Shen, Zhuowen
Liu, Yuan
Chen, Zhang
Li, Zhong
Wang, Jiepeng
Liang, Yongqing
Yu, Zhengming
Zhang, Jingdong
Xu, Yi
Schaefer, Scott
Li, Xin
Wang, Wenping
Computer Vision and Pattern Recognition
Gaussian splatting has achieved impressive improvements for both novel-view synthesis and surface reconstruction from multi-view images. However, current methods still struggle to reconstruct high-quality surfaces from only sparse view input images using Gaussian splatting. In this paper, we propose a novel method called SolidGS to address this problem. We observed that the reconstructed geometry can be severely inconsistent across multi-views, due to the property of Gaussian function in geometry rendering. This motivates us to consolidate all Gaussians by adopting a more solid kernel function, which effectively improves the surface reconstruction quality. With the additional help of geometrical regularization and monocular normal estimation, our method achieves superior performance on the sparse view surface reconstruction than all the Gaussian splatting methods and neural field methods on the widely used DTU, Tanks-and-Temples, and LLFF datasets.
title SolidGS: Consolidating Gaussian Surfel Splatting for Sparse-View Surface Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.15400