AnchoredDream: Zero-Shot 360° Indoor Scene Generation from a Single View via Geometric Grounding
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917223159824384 |
|---|---|
| author | Yao, Runmao Zhou, Junsheng Dong, Zhen Liu, Yu-Shen |
| author_facet | Yao, Runmao Zhou, Junsheng Dong, Zhen Liu, Yu-Shen |
| contents | Single-view indoor scene generation plays a crucial role in a range of real-world applications. However, generating a complete 360° 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° 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: warp-and-inpaint, warp-and-refine, post-optimization, and a novel Grouting Block, which ensures seamless transitions between the input view and generated regions. Extensive experiments demonstrate that AnchoredDream outperforms existing methods by a large margin in both appearance consistency and geometric plausibility--all in a zero-shot manner. Our results highlight the potential of geometric grounding for high-quality, zero-shot single-view scene generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_16532 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AnchoredDream: Zero-Shot 360° Indoor Scene Generation from a Single View via Geometric Grounding Yao, Runmao Zhou, Junsheng Dong, Zhen Liu, Yu-Shen Computer Vision and Pattern Recognition Single-view indoor scene generation plays a crucial role in a range of real-world applications. However, generating a complete 360° 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° 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: warp-and-inpaint, warp-and-refine, post-optimization, and a novel Grouting Block, which ensures seamless transitions between the input view and generated regions. Extensive experiments demonstrate that AnchoredDream outperforms existing methods by a large margin in both appearance consistency and geometric plausibility--all in a zero-shot manner. Our results highlight the potential of geometric grounding for high-quality, zero-shot single-view scene generation. |
| title | AnchoredDream: Zero-Shot 360° Indoor Scene Generation from a Single View via Geometric Grounding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.16532 |