递归代码世界模型：通过递归场景程序构建复杂世界
Recursive Code World Models: Building Complex Worlds through Recursive Scene Programs
- Georgia Institute of Technology（佐治亚理工学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出递归代码世界模型（RCWM），通过递归场景程序从单张参考图像重建复杂3D世界，采用全局-局部-全局递归和视觉-语言代理引导，优于现有方法。
AI中文摘要：
代码世界模型将世界表示为可执行程序，但仅凭这种表示本身并不能决定如何构建一个复杂世界。我们引入了递归代码世界模型（RCWM），这是一个从单张参考图像以代码形式重建复杂3D世界的框架。RCWM将递归场景程序（RSP）表示与一个递归调用自身的构建求解器相结合。RSP将可执行世界表示为组合式场景代码，而每次求解器调用都遵循相同的完整流程：建立整体，递归重建未解析的部分，并重新审视整体以优化其组合。这种全局-局部-全局的递归为精细结构提供了各自的感知与编辑循环，同时保持了场景级的几何形状和关系。参考对齐视图在各级之间传播共享的相机投影，而父级重新审视则处理局部细化后出现的边界、空间关系和共享错误。一个视觉-语言编码代理直接比较参考图像与场景渲染，以指导细化、递归下降和返回。在复杂场景中，RCWM优于先前的基于代码的图像到场景重建方法。消融研究进一步支持了递归构建的优势，并表明更深的调用可以改善更精细尺度的重建。RCWM提供了一种从视觉证据构建复杂可执行世界的递归构建原则。
英文摘要：
Code world models represent worlds as executable programs, but this representation alone does not determine how to construct a complex world. We introduce Recursive Code World Models (RCWM), a framework for reconstructing complex 3D worlds in code from a single reference image. RCWM couples a Recursive Scene Program (RSP) representation with a construction solver that recursively calls itself. An RSP represents the executable world as compositional scene code, while each solver call follows the same complete process: establish the whole, recursively reconstruct unresolved parts, and revisit the whole to refine their composition. This global-local-global recursion gives fine-scale structures their own perception-and-editing loops while preserving scene-wide geometry and relationships. Reference-aligned views propagate a shared camera projection across levels, while parent revisitation addresses boundaries, spatial relations, and shared errors that emerge after local refinement. A vision-language coding agent directly compares reference images with scene renders to guide refinement, recursive descent, and return. Across complex scenes, RCWM outperforms prior code-based image-to-scene reconstruction methods. Ablation studies further support the benefits of recursive construction and suggest that deeper calls can improve finer-scale reconstruction. RCWM provides a recursive construction principle for building complex executable worlds from visual evidence.
