Paper page - Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis

Source: https://huggingface.co/papers/2605.18451

Abstract

A novel MLLM-based agentic framework called Code-as-Room generates 3D indoor rooms by converting top-down images into executable Blender code through a structured execution harness with cross-stage memory to maintain context.

Designing realistic and functional 3D indoor rooms is essential for a wide range of applications, including interior design, virtual reality, gaming, and embodied AI. While recent MLLM-based approaches have shown great potential for3D room synthesisfrom textual descriptions or reference images, text-based methods struggle to capture precise spatial information, and existing image-conditioned agents suffer from instability and infinite looping when tasked with holistic room generation fromtop-down views. To address these limitations, we propose Code-as-Room, anMLLM-based agentic frameworkequipped with astructured execution harness, which represents 3D rooms withBlender codes. Given a top-down room image, the framework parses the reference image to extractscene elementsand theirspatial relationships, and synthesizes executable Blender code for geometry, materials, and lighting in a principled,multi-stage pipeline. Across-stage memorymodule is maintained throughout to mitigate context forgetting inherent to existing agent-based frameworks. We further introduce a dedicated benchmark for code-based3D room synthesis, encompassing various evaluation protocols. Based on our benchmark, comprehensive comparisons against existing agent-based methods are conducted to validate the effectiveness of our proposed execution harness.

View arXiv pageView PDFProject pageGitHub3Add to collection

Get this paper in your agent:

hf papers read 2605\.18451

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.18451 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.18451 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.18451 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.