Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhao, Qingcheng, Zhang, Xiang, Xu, Haiyang, Chen, Zeyuan, Xie, Jianwen, Gao, Yuan, Tu, Zhuowen
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2507.22825
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916871373062144
author Zhao, Qingcheng
Zhang, Xiang
Xu, Haiyang
Chen, Zeyuan
Xie, Jianwen
Gao, Yuan
Tu, Zhuowen
author_facet Zhao, Qingcheng
Zhang, Xiang
Xu, Haiyang
Chen, Zeyuan
Xie, Jianwen
Gao, Yuan
Tu, Zhuowen
contents We propose DepR, a depth-guided single-view scene reconstruction framework that integrates instance-level diffusion within a compositional paradigm. Instead of reconstructing the entire scene holistically, DepR generates individual objects and subsequently composes them into a coherent 3D layout. Unlike previous methods that use depth solely for object layout estimation during inference and therefore fail to fully exploit its rich geometric information, DepR leverages depth throughout both training and inference. Specifically, we introduce depth-guided conditioning to effectively encode shape priors into diffusion models. During inference, depth further guides DDIM sampling and layout optimization, enhancing alignment between the reconstruction and the input image. Despite being trained on limited synthetic data, DepR achieves state-of-the-art performance and demonstrates strong generalization in single-view scene reconstruction, as shown through evaluations on both synthetic and real-world datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2507_22825
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DepR: Depth Guided Single-view Scene Reconstruction with Instance-level Diffusion
Zhao, Qingcheng
Zhang, Xiang
Xu, Haiyang
Chen, Zeyuan
Xie, Jianwen
Gao, Yuan
Tu, Zhuowen
Computer Vision and Pattern Recognition
We propose DepR, a depth-guided single-view scene reconstruction framework that integrates instance-level diffusion within a compositional paradigm. Instead of reconstructing the entire scene holistically, DepR generates individual objects and subsequently composes them into a coherent 3D layout. Unlike previous methods that use depth solely for object layout estimation during inference and therefore fail to fully exploit its rich geometric information, DepR leverages depth throughout both training and inference. Specifically, we introduce depth-guided conditioning to effectively encode shape priors into diffusion models. During inference, depth further guides DDIM sampling and layout optimization, enhancing alignment between the reconstruction and the input image. Despite being trained on limited synthetic data, DepR achieves state-of-the-art performance and demonstrates strong generalization in single-view scene reconstruction, as shown through evaluations on both synthetic and real-world datasets.
title DepR: Depth Guided Single-view Scene Reconstruction with Instance-level Diffusion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.22825