ZeroHour
Hugging Face daily paperspublished ()ingested Zhiqi Li, Yuxuan Liao, Bo Zhu1

Recursive Code World Models: Building Complex Worlds through Recursive Scene Programs

infoAI researchimportance 33
AI summary · glm-5.3-flash

RCWM reconstructs complex 3D worlds as executable code from a single image using recursive scene programs with global-local-global solver recursion.

The paper introduces Recursive Code World Models, coupling a Recursive Scene Program representation with a recursive construction solver for image-to-3D-world reconstruction. Each solver call establishes the whole scene, recursively reconstructs unresolved parts, and revisits the whole to refine composition, while a vision-language coding agent compares reference images with scene renders to guide refinement. RCWM outperforms prior code-based image-to-scene reconstruction methods, and ablations show deeper recursive calls improve fine-scale reconstruction.

  • Recursive Scene Programs represent executable worlds as compositional scene code
  • Global-local-global recursion preserves scene-wide geometry while refining local detail
  • VLM coding agent compares reference images with renders to guide refinement
  • Outperforms prior code-based image-to-scene reconstruction methods
AI modelsRCWM
Full article192 words · extracted from huggingface.co · click to collapse

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.

Text extracted automatically; images, tables and formatting may be missing. Original: https://huggingface.co/papers/2609.11499