AnchoredDream: Zero-Shot 360{\deg} Indoor Scene Generation from a Single View via Geometric Grounding
Runmao Yao, Junsheng Zhou, Zhen Dong, Yu-Shen Liu

TL;DR
AnchoredDream is a zero-shot pipeline that generates complete 360-degree indoor scenes from a single image by leveraging geometric grounding and an appearance-geometry mutual boosting mechanism, improving consistency and plausibility.
Contribution
It introduces a novel zero-shot approach that anchors scene generation on high-fidelity geometry, with modules ensuring seamless transitions and improved scene quality.
Findings
Outperforms existing methods in appearance consistency
Achieves superior geometric plausibility
Operates effectively in a zero-shot setting
Abstract
Single-view indoor scene generation plays a crucial role in a range of real-world applications. However, generating a complete 360{\deg} scene from a single image remains a highly ill-posed and challenging problem. Recent approaches have made progress by leveraging diffusion models and depth estimation networks, yet they still struggle to maintain appearance consistency and geometric plausibility under large viewpoint changes, limiting their effectiveness in full-scene generation. To address this, we propose AnchoredDream, a novel zero-shot pipeline that anchors 360{\deg} scene generation on high-fidelity geometry via an appearance-geometry mutual boosting mechanism. Given a single-view image, our method first performs appearance-guided geometry generation to construct a reliable 3D scene layout. Then, we progressively generate the complete scene through a series of modules:…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Vision and Imaging · Generative Adversarial Networks and Image Synthesis · 3D Shape Modeling and Analysis
