Hybrid bundle-adjusting 3D Gaussians for view consistent rendering with pose optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guo, Yanan, Xie, Ying, Chang, Ying, Zhang, Benkui, Jia, Bo, Cao, Lin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909353162833920
author Guo, Yanan
Xie, Ying
Chang, Ying
Zhang, Benkui
Jia, Bo
Cao, Lin
author_facet Guo, Yanan
Xie, Ying
Chang, Ying
Zhang, Benkui
Jia, Bo
Cao, Lin
contents Novel view synthesis has made significant progress in the field of 3D computer vision. However, the rendering of view-consistent novel views from imperfect camera poses remains challenging. In this paper, we introduce a hybrid bundle-adjusting 3D Gaussians model that enables view-consistent rendering with pose optimization. This model jointly extract image-based and neural 3D representations to simultaneously generate view-consistent images and camera poses within forward-facing scenes. The effective of our model is demonstrated through extensive experiments conducted on both real and synthetic datasets. These experiments clearly illustrate that our model can effectively optimize neural scene representations while simultaneously resolving significant camera pose misalignments. The source code is available at https://github.com/Bistu3DV/hybridBA.
format Preprint
id arxiv_https___arxiv_org_abs_2410_13280
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Hybrid bundle-adjusting 3D Gaussians for view consistent rendering with pose optimization
Guo, Yanan
Xie, Ying
Chang, Ying
Zhang, Benkui
Jia, Bo
Cao, Lin
Computer Vision and Pattern Recognition
Novel view synthesis has made significant progress in the field of 3D computer vision. However, the rendering of view-consistent novel views from imperfect camera poses remains challenging. In this paper, we introduce a hybrid bundle-adjusting 3D Gaussians model that enables view-consistent rendering with pose optimization. This model jointly extract image-based and neural 3D representations to simultaneously generate view-consistent images and camera poses within forward-facing scenes. The effective of our model is demonstrated through extensive experiments conducted on both real and synthetic datasets. These experiments clearly illustrate that our model can effectively optimize neural scene representations while simultaneously resolving significant camera pose misalignments. The source code is available at https://github.com/Bistu3DV/hybridBA.
title Hybrid bundle-adjusting 3D Gaussians for view consistent rendering with pose optimization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.13280