PhySGA: A Physics-Space Grounded Agentic Framework for Generalizable and Interactive 3D Composition· PhySGA：物理空间中的代理框架
3D object composition is pivotal to digital content creation and robot simulation, while also serving as a critical testbed for physical intelligence in foundation models. Previous methods either leverage large language models to directly predict object coordinates, or utilize generative diffusion priors to synthesize composite images for visual alignment, both of which rely on static priors in digital spaces. However, these methods consistently struggle with complex compositions such as precise hanging, gravity-driven settling and hidden containment, as these tasks require interactive construction processes involving global planning, fine-grained alignment, and physical simulation. To address these challenges, we propose PhySGA, a Physics-Space Grounded Agentic Framework for 3D compositio
提出 PhySGA 框架，实现复杂 3D 物体组合的物理交互与全局规划。
- 核心方法
- 结合物理空间的代理框架，通过全局规划和物理仿真实现3D物体的精确交互组合。
- 适合谁读
- 研究者 / 工程师
- 要解决的问题
- 现有方法在复杂3D物体组合任务中表现不佳，如精确悬挂、重力驱动放置和隐藏容纳。
- 关键实验
- 未提供
- 主要贡献
- PhySGA 框架提升了3D物体组合的精确性和交互性，特别是在复杂任务上。
- 意义与局限
- PhySGA 为数字内容创作和机器人模拟提供了更强大的3D物体组合工具，但可能需要较高的计算资源。