Saved in:
Bibliographic Details
Main Authors: Shi, Zhihao, Huo, Dong, Zhou, Yuhongze, Yin, Kejia, Min, Yan, Lu, Juwei, Zuo, Xinxin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.04501
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915184352690176
author Shi, Zhihao
Huo, Dong
Zhou, Yuhongze
Yin, Kejia
Min, Yan
Lu, Juwei
Zuo, Xinxin
author_facet Shi, Zhihao
Huo, Dong
Zhou, Yuhongze
Yin, Kejia
Min, Yan
Lu, Juwei
Zuo, Xinxin
contents Current 3D inpainting and object removal methods are largely limited to front-facing scenes, facing substantial challenges when applied to diverse, "unconstrained" scenes where the camera orientation and trajectory are unrestricted. To bridge this gap, we introduce a novel approach that produces inpainted 3D scenes with consistent visual quality and coherent underlying geometry across both front-facing and unconstrained scenes. Specifically, we propose a robust 3D inpainting pipeline that incorporates geometric priors and a multi-view refinement network trained via test-time adaptation, building on a pre-trained image inpainting model. Additionally, we develop a novel inpainting mask detection technique to derive targeted inpainting masks from object masks, boosting the performance in handling unconstrained scenes. To validate the efficacy of our approach, we create a challenging and diverse benchmark that spans a wide range of scenes. Comprehensive experiments demonstrate that our proposed method substantially outperforms existing state-of-the-art approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2503_04501
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle IMFine: 3D Inpainting via Geometry-guided Multi-view Refinement
Shi, Zhihao
Huo, Dong
Zhou, Yuhongze
Yin, Kejia
Min, Yan
Lu, Juwei
Zuo, Xinxin
Computer Vision and Pattern Recognition
Current 3D inpainting and object removal methods are largely limited to front-facing scenes, facing substantial challenges when applied to diverse, "unconstrained" scenes where the camera orientation and trajectory are unrestricted. To bridge this gap, we introduce a novel approach that produces inpainted 3D scenes with consistent visual quality and coherent underlying geometry across both front-facing and unconstrained scenes. Specifically, we propose a robust 3D inpainting pipeline that incorporates geometric priors and a multi-view refinement network trained via test-time adaptation, building on a pre-trained image inpainting model. Additionally, we develop a novel inpainting mask detection technique to derive targeted inpainting masks from object masks, boosting the performance in handling unconstrained scenes. To validate the efficacy of our approach, we create a challenging and diverse benchmark that spans a wide range of scenes. Comprehensive experiments demonstrate that our proposed method substantially outperforms existing state-of-the-art approaches.
title IMFine: 3D Inpainting via Geometry-guided Multi-view Refinement
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.04501