SPATIALGEN: 布局引导的3D室内场景生成
SPATIALGEN: Layout-guided 3D Indoor Scene Generation
AI总结：
SPATIALGEN通过布局引导的多视角多模态扩散模型生成高质量3D室内场景，解决现有方法在视觉质量、多样性及语义一致性方面的不足。
摘要：
创建高保真的3D室内环境模型对于设计、虚拟现实和机器人应用至关重要。然而，手动3D建模仍然耗时且劳动强度大。尽管最近生成式AI的进步使自动场景合成成为可能，但现有方法在平衡视觉质量、多样性、语义一致性及用户控制之间面临挑战。主要瓶颈是缺乏专门为此任务设计的大型高质量数据集。为解决这一差距，我们引入了一个全面的合成数据集，包含12,328个结构标注的场景，57,431个房间，以及4.7M张逼真2D渲染图像。利用此数据集，我们提出了SpatialGen，一种新的多视角多模态扩散模型，能够生成逼真且语义一致的3D室内场景。给定一个3D布局和一个参考图像（源自文本提示），我们的模型能够从任意视角合成外观（颜色图像）、几何（场景坐标图）和语义（语义分割图），同时保持各模态间的空间一致性。SpatialGen在我们的实验中始终生成优于先前方法的结果。我们开源我们的数据和模型，以赋能社区并推进室内场景理解和生成领域。
英文摘要：
Creating high-fidelity 3D models of indoor environments is essential for applications in design, virtual reality, and robotics. However, manual 3D modeling remains time-consuming and labor-intensive. While recent advances in generative AI have enabled automated scene synthesis, existing methods often face challenges in balancing visual quality, diversity, semantic consistency, and user control. A major bottleneck is the lack of a large-scale, high-quality dataset tailored to this task. To address this gap, we introduce a comprehensive synthetic dataset, featuring 12,328 structured annotated scenes with 57,431 rooms, and 4.7M photorealistic 2D renderings. Leveraging this dataset, we present SpatialGen, a novel multi-view multi-modal diffusion model that generates realistic and semantically consistent 3D indoor scenes. Given a 3D layout and a reference image (derived from a text prompt), our model synthesizes appearance (color image), geometry (scene coordinate map), and semantic (semantic segmentation map) from arbitrary viewpoints, while preserving spatial consistency across modalities. SpatialGen consistently generates superior results to previous methods in our experiments. We are open-sourcing our data and models to empower the community and advance the field of indoor scene understanding and generation.
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。
