Skip to content
NewA calmer, faster ZeroHour

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

Hugging Face daily papersby Zhiqi Li, Yuxuan Liao, Bo Zhu ()1 min read2 · 1 read
AI summary · glm-5.3-flashSummaries by Vani AI

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.

Key facts
  • 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
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

1 min read at huggingface.co

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.

Hugging Face daily papers

By Zhiqi Li, Yuxuan Liao, Bo Zhu · huggingface.co

Read the full article at Hugging Face daily papers

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.