Saved in:
Bibliographic Details
Main Authors: Zhang, Xuanqi, Lee, Jieun, Joslin, Chris, Lee, Wonsook
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.11601
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917957281513472
author Zhang, Xuanqi
Lee, Jieun
Joslin, Chris
Lee, Wonsook
author_facet Zhang, Xuanqi
Lee, Jieun
Joslin, Chris
Lee, Wonsook
contents We present a novel framework for enhancing the visual fidelity and consistency of text-guided 3D Gaussian Splatting (3DGS) editing. Existing editing approaches face two critical challenges: inconsistent geometric reconstructions across multiple viewpoints, particularly in challenging camera positions, and ineffective utilization of depth information during image manipulation, resulting in over-texture artifacts and degraded object boundaries. To address these limitations, we introduce: 1) A complementary information mutual learning network that enhances depth map estimation from 3DGS, enabling precise depth-conditioned 3D editing while preserving geometric structures. 2) A wavelet consensus attention mechanism that effectively aligns latent codes during the diffusion denoising process, ensuring multi-view consistency in the edited results. Through extensive experimentation, our method demonstrates superior performance in rendering quality and view consistency compared to state-of-the-art approaches. The results validate our framework as an effective solution for text-guided editing of 3D scenes.
format Preprint
id arxiv_https___arxiv_org_abs_2503_11601
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Advancing 3D Gaussian Splatting Editing with Complementary and Consensus Information
Zhang, Xuanqi
Lee, Jieun
Joslin, Chris
Lee, Wonsook
Computer Vision and Pattern Recognition
We present a novel framework for enhancing the visual fidelity and consistency of text-guided 3D Gaussian Splatting (3DGS) editing. Existing editing approaches face two critical challenges: inconsistent geometric reconstructions across multiple viewpoints, particularly in challenging camera positions, and ineffective utilization of depth information during image manipulation, resulting in over-texture artifacts and degraded object boundaries. To address these limitations, we introduce: 1) A complementary information mutual learning network that enhances depth map estimation from 3DGS, enabling precise depth-conditioned 3D editing while preserving geometric structures. 2) A wavelet consensus attention mechanism that effectively aligns latent codes during the diffusion denoising process, ensuring multi-view consistency in the edited results. Through extensive experimentation, our method demonstrates superior performance in rendering quality and view consistency compared to state-of-the-art approaches. The results validate our framework as an effective solution for text-guided editing of 3D scenes.
title Advancing 3D Gaussian Splatting Editing with Complementary and Consensus Information
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.11601