用几何约束实现单图生成360°室内场景，零样本下保持视觉与结构一致
AnchoredDream: Zero-Shot 360° Indoor Scene Generation from a Single View via Geometric Grounding
- 以外观引导几何生成，构建可靠3D布局
- 多阶段模块融合，实现视角间无缝衔接
- 无需训练数据，直接跨视角生成高质量场景
单视图室内场景生成在诸多实际应用中至关重要，但仅凭一张图像生成完整的360°场景仍属高度病态且极具挑战。现有方法虽借助扩散模型与深度估计网络取得进展，但在大幅视角变化下仍难以维持外观一致性与几何合理性，限制了全场景生成效果。为此，我们提出AnchoredDream，一种新颖的零样本流程，通过外观-几何互增强机制，将360°场景生成锚定于高保真几何结构。给定单张图像，该方法首先进行外观引导的几何生成，构建可靠3D场景布局；随后通过一系列模块——扭曲-修复、扭曲-精修、后优化及新型灌浆模块（Grouting Block）——逐步完成完整场景生成，确保输入视图与生成区域间的无缝过渡。大量实验表明，AnchoredDream在外观一致性和几何合理性方面均显著优于现有方法，且全程零样本。结果凸显几何锚定在高质量、零样本单视图场景生成中的潜力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。