Enregistré dans:
Détails bibliographiques
Auteurs principaux: Huang, Yi-Chuan, Chien, Hao-Jen, Lin, Chin-Yang, Chen, Ying-Huan, Liu, Yu-Lun
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2512.25073
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915914514956288
author Huang, Yi-Chuan
Chien, Hao-Jen
Lin, Chin-Yang
Chen, Ying-Huan
Liu, Yu-Lun
author_facet Huang, Yi-Chuan
Chien, Hao-Jen
Lin, Chin-Yang
Chen, Ying-Huan
Liu, Yu-Lun
contents Recent 3D reconstruction methods achieve impressive results with dense multi-view imagery but struggle when only a few views are available. Various approaches, including regularization techniques, semantic priors, and geometric constraints, have been implemented to address this challenge. Recent diffusion-based approaches further improve performance by generating novel views to augment training data. Despite this progress, we identify three critical limitations in current state-of-the-art approaches: (i) inadequate coverage beyond known view peripheries, (ii) geometric inconsistencies across generated views, and (iii) computational inefficiency due to expensive pipelines. We introduce GaMO (Geometry-aware Multi-view Outpainter), a framework that reformulates sparse-view reconstruction through multi-view outpainting. Instead of generating new viewpoints, GaMO expands the field of view from existing camera poses, which inherently preserves geometric consistency while providing broader scene coverage. Our approach employs multi-view conditioning and geometry-aware denoising strategies in a zero-shot manner without training. Extensive experiments on Replica, ScanNet++, and Mip-NeRF 360 demonstrate strong reconstruction performance across sparse-view settings (3, 6, and 9 input views). Notably, our method is significantly more efficient than existing diffusion-based approaches, reducing the overall runtime to within 10 minutes. Project page: https://yichuanh.github.io/GaMO/
format Preprint
id arxiv_https___arxiv_org_abs_2512_25073
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GaMO: Geometry-aware Multi-view Diffusion Outpainting for Sparse-View 3D Reconstruction
Huang, Yi-Chuan
Chien, Hao-Jen
Lin, Chin-Yang
Chen, Ying-Huan
Liu, Yu-Lun
Computer Vision and Pattern Recognition
Recent 3D reconstruction methods achieve impressive results with dense multi-view imagery but struggle when only a few views are available. Various approaches, including regularization techniques, semantic priors, and geometric constraints, have been implemented to address this challenge. Recent diffusion-based approaches further improve performance by generating novel views to augment training data. Despite this progress, we identify three critical limitations in current state-of-the-art approaches: (i) inadequate coverage beyond known view peripheries, (ii) geometric inconsistencies across generated views, and (iii) computational inefficiency due to expensive pipelines. We introduce GaMO (Geometry-aware Multi-view Outpainter), a framework that reformulates sparse-view reconstruction through multi-view outpainting. Instead of generating new viewpoints, GaMO expands the field of view from existing camera poses, which inherently preserves geometric consistency while providing broader scene coverage. Our approach employs multi-view conditioning and geometry-aware denoising strategies in a zero-shot manner without training. Extensive experiments on Replica, ScanNet++, and Mip-NeRF 360 demonstrate strong reconstruction performance across sparse-view settings (3, 6, and 9 input views). Notably, our method is significantly more efficient than existing diffusion-based approaches, reducing the overall runtime to within 10 minutes. Project page: https://yichuanh.github.io/GaMO/
title GaMO: Geometry-aware Multi-view Diffusion Outpainting for Sparse-View 3D Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.25073