With recent developments in Embodied Artificial Intelligence (EAI) research, there has been a growing demand for high-quality, large-scale interactive scene generation. While prior methods in scene synthesis have prioritized the naturalness and realism of the generated scenes, the physical plausibility and interactivity of scenes have been largely left unexplored. To address this disparity, we introduce PhyScene, a novel method dedicated to generating interactive 3D scenes characterized by realistic layouts, articulated objects, and rich physical interactivity tailored for embodied agents. Based on a conditional diffusion model for capturing scene layouts, we devise novel physics- and interactivity-based guidance mechanisms that integrate constraints from object collision, room layout, and object reachability. Through extensive experiments, we demonstrate that PhyScene effectively leverages these guidance functions for physically interactable scene synthesis, outperforming existing state-of-the-art scene synthesis methods by a large margin. Our findings suggest that the scenes generated by PhyScene hold considerable potential for facilitating diverse skill acquisition among agents within interactive environments, thereby catalyzing further advancements in embodied AI research. Project website: http://physcene.github.io.

翻译：随着具身人工智能（Embodied AI）研究的不断发展，对于高质量、大规模交互式场景生成的需求日益增长。尽管现有场景合成方法主要关注生成场景的自然性与逼真度，但场景的物理合理性与交互性在很大程度上仍未被探索。针对这一差异，我们提出PhyScene——一种专为具身智能体生成交互式3D场景的新方法，其特点在于具有真实的布局、可动关节物体以及丰富的物理交互性。该方法基于捕捉场景布局的条件扩散模型，创新性地设计了一套基于物理与交互性的引导机制，该机制整合了物体碰撞、房间布局及物体可达性约束。通过大量实验，我们证明PhyScene能有效利用这些引导函数实现物理可交互场景合成，其性能大幅超越现有最先进的场景合成方法。研究结果表明，PhyScene生成的场景在促进智能体于交互环境中习得多样化技能方面具有显著潜力，从而进一步推动具身人工智能研究的发展。项目网站：http://physcene.github.io。