InSpace：从单张360°图像生成具有结构感知的3D室内场景
InSpace: Structure-Aware 3D Indoor Scene Generation from a Single 360° Image
AI总结：
针对单图像到3D生成扩展到室内场景有挑战的问题，提出InSpace框架，利用360°图像，经估计部分场景几何、生成粗结构、产生详细布局和资产几何三阶段，还建数据集，实验表明其性能强。
摘要：
单图像到3D生成的进展使高质量资产合成成为可能，但扩展到室内场景生成仍具挑战性。现有方法忽视结构布局，单图像视野有限。为此，我们使用等距投影表示的360°图像，提出InSpace框架，含三个阶段，还提出数据集ERP-FRONT，实验表明InSpace性能良好。
英文摘要：
Recent advances in single image-to-3D generation have enabled high-quality asset synthesis, yet extending these capabilities to indoor scene generation remains challenging. Existing methods focus on asset-level generation while neglecting the structural layout, which is essential for downstream applications and serves as the spatial anchor for grounding assets. However, a single image with a limited field of view lacks the spatial coverage to recover a coherent global layout. To this end, we use a 360° image represented in equirectangular projection (ERP) and propose InSpace, a structure-aware framework for 3D indoor scene generation. InSpace comprises three stages: (1) estimating partial scene geometry as spatial priors, (2) generating coarse scene structure with view-selective cross-attention, and (3) producing detailed layout and asset geometry with textures through a global-local hybrid attention, using flow matching. We also propose ERP-FRONT, a paired ERP-Image-to-3D indoor scene dataset based on 3D-FRONT. Experiments show that InSpace generates complete 3D indoor scenes with structural layout, along with separate textured assets from a single ERP image, achieving strong performance across 3D and 2D metrics. Project Page: https://kookie12.github.io/InSpace-Project-Page/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
