Saved in:
Bibliographic Details
Main Authors: Huang, Zhisheng, Wang, Peng, Zhang, Jingdong, Liu, Yuan, Li, Xin, Wang, Wenping
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.04294
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913778525798400
author Huang, Zhisheng
Wang, Peng
Zhang, Jingdong
Liu, Yuan
Li, Xin
Wang, Wenping
author_facet Huang, Zhisheng
Wang, Peng
Zhang, Jingdong
Liu, Yuan
Li, Xin
Wang, Wenping
contents 3D Gaussian Splatting (3DGS) has revolutionized neural rendering with its efficiency and quality, but like many novel view synthesis methods, it heavily depends on accurate camera poses from Structure-from-Motion (SfM) systems. Although recent SfM pipelines have made impressive progress, questions remain about how to further improve both their robust performance in challenging conditions (e.g., textureless scenes) and the precision of camera parameter estimation simultaneously. We present 3R-GS, a 3D Gaussian Splatting framework that bridges this gap by jointly optimizing 3D Gaussians and camera parameters from large reconstruction priors MASt3R-SfM. We note that naively performing joint 3D Gaussian and camera optimization faces two challenges: the sensitivity to the quality of SfM initialization, and its limited capacity for global optimization, leading to suboptimal reconstruction results. Our 3R-GS, overcomes these issues by incorporating optimized practices, enabling robust scene reconstruction even with imperfect camera registration. Extensive experiments demonstrate that 3R-GS delivers high-quality novel view synthesis and precise camera pose estimation while remaining computationally efficient. Project page: https://zsh523.github.io/3R-GS/
format Preprint
id arxiv_https___arxiv_org_abs_2504_04294
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle 3R-GS: Best Practice in Optimizing Camera Poses Along with 3DGS
Huang, Zhisheng
Wang, Peng
Zhang, Jingdong
Liu, Yuan
Li, Xin
Wang, Wenping
Computer Vision and Pattern Recognition
3D Gaussian Splatting (3DGS) has revolutionized neural rendering with its efficiency and quality, but like many novel view synthesis methods, it heavily depends on accurate camera poses from Structure-from-Motion (SfM) systems. Although recent SfM pipelines have made impressive progress, questions remain about how to further improve both their robust performance in challenging conditions (e.g., textureless scenes) and the precision of camera parameter estimation simultaneously. We present 3R-GS, a 3D Gaussian Splatting framework that bridges this gap by jointly optimizing 3D Gaussians and camera parameters from large reconstruction priors MASt3R-SfM. We note that naively performing joint 3D Gaussian and camera optimization faces two challenges: the sensitivity to the quality of SfM initialization, and its limited capacity for global optimization, leading to suboptimal reconstruction results. Our 3R-GS, overcomes these issues by incorporating optimized practices, enabling robust scene reconstruction even with imperfect camera registration. Extensive experiments demonstrate that 3R-GS delivers high-quality novel view synthesis and precise camera pose estimation while remaining computationally efficient. Project page: https://zsh523.github.io/3R-GS/
title 3R-GS: Best Practice in Optimizing Camera Poses Along with 3DGS
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.04294