MirrorGaussian: Reflecting 3D Gaussians for Reconstructing Mirror Reflections

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Jiayue, Tang, Xiao, Cheng, Freeman, Yang, Roy, Li, Zhihao, Liu, Jianzhuang, Huang, Yi, Lin, Jiaqi, Liu, Shiyong, Wu, Xiaofei, Xu, Songcen, Yuan, Chun
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929348832919552
author Liu, Jiayue
Tang, Xiao
Cheng, Freeman
Yang, Roy
Li, Zhihao
Liu, Jianzhuang
Huang, Yi
Lin, Jiaqi
Liu, Shiyong
Wu, Xiaofei
Xu, Songcen
Yuan, Chun
author_facet Liu, Jiayue
Tang, Xiao
Cheng, Freeman
Yang, Roy
Li, Zhihao
Liu, Jianzhuang
Huang, Yi
Lin, Jiaqi
Liu, Shiyong
Wu, Xiaofei
Xu, Songcen
Yuan, Chun
contents 3D Gaussian Splatting showcases notable advancements in photo-realistic and real-time novel view synthesis. However, it faces challenges in modeling mirror reflections, which exhibit substantial appearance variations from different viewpoints. To tackle this problem, we present MirrorGaussian, the first method for mirror scene reconstruction with real-time rendering based on 3D Gaussian Splatting. The key insight is grounded on the mirror symmetry between the real-world space and the virtual mirror space. We introduce an intuitive dual-rendering strategy that enables differentiable rasterization of both the real-world 3D Gaussians and the mirrored counterpart obtained by reflecting the former about the mirror plane. All 3D Gaussians are jointly optimized with the mirror plane in an end-to-end framework. MirrorGaussian achieves high-quality and real-time rendering in scenes with mirrors, empowering scene editing like adding new mirrors and objects. Comprehensive experiments on multiple datasets demonstrate that our approach significantly outperforms existing methods, achieving state-of-the-art results. Project page: https://mirror-gaussian.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2405_11921
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MirrorGaussian: Reflecting 3D Gaussians for Reconstructing Mirror Reflections
Liu, Jiayue
Tang, Xiao
Cheng, Freeman
Yang, Roy
Li, Zhihao
Liu, Jianzhuang
Huang, Yi
Lin, Jiaqi
Liu, Shiyong
Wu, Xiaofei
Xu, Songcen
Yuan, Chun
Computer Vision and Pattern Recognition
3D Gaussian Splatting showcases notable advancements in photo-realistic and real-time novel view synthesis. However, it faces challenges in modeling mirror reflections, which exhibit substantial appearance variations from different viewpoints. To tackle this problem, we present MirrorGaussian, the first method for mirror scene reconstruction with real-time rendering based on 3D Gaussian Splatting. The key insight is grounded on the mirror symmetry between the real-world space and the virtual mirror space. We introduce an intuitive dual-rendering strategy that enables differentiable rasterization of both the real-world 3D Gaussians and the mirrored counterpart obtained by reflecting the former about the mirror plane. All 3D Gaussians are jointly optimized with the mirror plane in an end-to-end framework. MirrorGaussian achieves high-quality and real-time rendering in scenes with mirrors, empowering scene editing like adding new mirrors and objects. Comprehensive experiments on multiple datasets demonstrate that our approach significantly outperforms existing methods, achieving state-of-the-art results. Project page: https://mirror-gaussian.github.io/.
title MirrorGaussian: Reflecting 3D Gaussians for Reconstructing Mirror Reflections
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.11921