View-Consistent 3D Editing with Gaussian Splatting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Yuxuan, Yi, Xuanyu, Wu, Zike, Zhao, Na, Chen, Long, Zhang, Hanwang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916615432437760
author Wang, Yuxuan
Yi, Xuanyu
Wu, Zike
Zhao, Na
Chen, Long
Zhang, Hanwang
author_facet Wang, Yuxuan
Yi, Xuanyu
Wu, Zike
Zhao, Na
Chen, Long
Zhang, Hanwang
contents The advent of 3D Gaussian Splatting (3DGS) has revolutionized 3D editing, offering efficient, high-fidelity rendering and enabling precise local manipulations. Currently, diffusion-based 2D editing models are harnessed to modify multi-view rendered images, which then guide the editing of 3DGS models. However, this approach faces a critical issue of multi-view inconsistency, where the guidance images exhibit significant discrepancies across views, leading to mode collapse and visual artifacts of 3DGS. To this end, we introduce View-consistent Editing (VcEdit), a novel framework that seamlessly incorporates 3DGS into image editing processes, ensuring multi-view consistency in edited guidance images and effectively mitigating mode collapse issues. VcEdit employs two innovative consistency modules: the Cross-attention Consistency Module and the Editing Consistency Module, both designed to reduce inconsistencies in edited images. By incorporating these consistency modules into an iterative pattern, VcEdit proficiently resolves the issue of multi-view inconsistency, facilitating high-quality 3DGS editing across a diverse range of scenes. Further video results are shown in http://vcedit.github.io.
format Preprint
id arxiv_https___arxiv_org_abs_2403_11868
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle View-Consistent 3D Editing with Gaussian Splatting
Wang, Yuxuan
Yi, Xuanyu
Wu, Zike
Zhao, Na
Chen, Long
Zhang, Hanwang
Graphics
Computer Vision and Pattern Recognition
The advent of 3D Gaussian Splatting (3DGS) has revolutionized 3D editing, offering efficient, high-fidelity rendering and enabling precise local manipulations. Currently, diffusion-based 2D editing models are harnessed to modify multi-view rendered images, which then guide the editing of 3DGS models. However, this approach faces a critical issue of multi-view inconsistency, where the guidance images exhibit significant discrepancies across views, leading to mode collapse and visual artifacts of 3DGS. To this end, we introduce View-consistent Editing (VcEdit), a novel framework that seamlessly incorporates 3DGS into image editing processes, ensuring multi-view consistency in edited guidance images and effectively mitigating mode collapse issues. VcEdit employs two innovative consistency modules: the Cross-attention Consistency Module and the Editing Consistency Module, both designed to reduce inconsistencies in edited images. By incorporating these consistency modules into an iterative pattern, VcEdit proficiently resolves the issue of multi-view inconsistency, facilitating high-quality 3DGS editing across a diverse range of scenes. Further video results are shown in http://vcedit.github.io.
title View-Consistent 3D Editing with Gaussian Splatting
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.11868