Perspective-aware 3D Gaussian Inpainting with Multi-view Consistency

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cheng, Yuxin, Huang, Binxiao, Wu, Taiqiang, Zhou, Wenyong, Ding, Chenchen, Liu, Zhengwu, Chesi, Graziano, Wong, Ngai
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911206782009344
author Cheng, Yuxin
Huang, Binxiao
Wu, Taiqiang
Zhou, Wenyong
Ding, Chenchen
Liu, Zhengwu
Chesi, Graziano
Wong, Ngai
author_facet Cheng, Yuxin
Huang, Binxiao
Wu, Taiqiang
Zhou, Wenyong
Ding, Chenchen
Liu, Zhengwu
Chesi, Graziano
Wong, Ngai
contents 3D Gaussian inpainting, a critical technique for numerous applications in virtual reality and multimedia, has made significant progress with pretrained diffusion models. However, ensuring multi-view consistency, an essential requirement for high-quality inpainting, remains a key challenge. In this work, we present PAInpainter, a novel approach designed to advance 3D Gaussian inpainting by leveraging perspective-aware content propagation and consistency verification across multi-view inpainted images. Our method iteratively refines inpainting and optimizes the 3D Gaussian representation with multiple views adaptively sampled from a perspective graph. By propagating inpainted images as prior information and verifying consistency across neighboring views, PAInpainter substantially enhances global consistency and texture fidelity in restored 3D scenes. Extensive experiments demonstrate the superiority of PAInpainter over existing methods. Our approach achieves superior 3D inpainting quality, with PSNR scores of 26.03 dB and 29.51 dB on the SPIn-NeRF and NeRFiller datasets, respectively, highlighting its effectiveness and generalization capability.
format Preprint
id arxiv_https___arxiv_org_abs_2510_10993
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Perspective-aware 3D Gaussian Inpainting with Multi-view Consistency
Cheng, Yuxin
Huang, Binxiao
Wu, Taiqiang
Zhou, Wenyong
Ding, Chenchen
Liu, Zhengwu
Chesi, Graziano
Wong, Ngai
Computer Vision and Pattern Recognition
3D Gaussian inpainting, a critical technique for numerous applications in virtual reality and multimedia, has made significant progress with pretrained diffusion models. However, ensuring multi-view consistency, an essential requirement for high-quality inpainting, remains a key challenge. In this work, we present PAInpainter, a novel approach designed to advance 3D Gaussian inpainting by leveraging perspective-aware content propagation and consistency verification across multi-view inpainted images. Our method iteratively refines inpainting and optimizes the 3D Gaussian representation with multiple views adaptively sampled from a perspective graph. By propagating inpainted images as prior information and verifying consistency across neighboring views, PAInpainter substantially enhances global consistency and texture fidelity in restored 3D scenes. Extensive experiments demonstrate the superiority of PAInpainter over existing methods. Our approach achieves superior 3D inpainting quality, with PSNR scores of 26.03 dB and 29.51 dB on the SPIn-NeRF and NeRFiller datasets, respectively, highlighting its effectiveness and generalization capability.
title Perspective-aware 3D Gaussian Inpainting with Multi-view Consistency
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.10993