🛰️ Daily AI Frontier
‹ back to 2026-09-11

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

arXiv cs.CV Multimodal & Generative Zhiqi Li, Yuxuan Liao, Bo Zhu 2026-09-10
Representative image for Recursive Code World Models: Building Complex Worlds through Recursive Scene Programs

TL;DR - Recursive Code World Models reconstruct complex, executable 3D scenes from a single image using compositional scene programs and a recursively invoked vision-language coding agent. The approach improves fine-detail reconstruction while preserving scene-wide geometry and spatial relationships.

  • Uses a global-local-global process: establish the full scene, recursively refine unresolved parts, then revisit overall composition.
  • Shares a reference-aligned camera projection across recursion levels for consistent geometry.
  • Parent-level revisitation corrects boundaries, spatial relationships, and shared errors introduced during local refinement.
  • Outperforms prior code-based image-to-scene reconstruction methods; ablations indicate deeper recursion can improve fine-scale reconstruction.

view merged work →