| title | Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis |
|---|---|
| authors | Yixuan Yang, Zhen Luo, Wanshui Gan, Jinkun Hao, Junru Lu, Jinghao Yan, Zhaoyang Lyu, Xudong Xu |
| date | 2026-05-18 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.18451 |
| affiliation | shanghai ailab |
| upvotes | 40 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | 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 for 3D room synthesis from 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 from top-down views. To address these limitations, we propose Code-as-Room, an MLLM-based agentic framework equipped with a structured execution harness, which represents 3D rooms with Blender codes. Given a top-down room image, the framework parses the reference image to extract scene elements and their spatial relationships, and synthesizes executable Blender code for geometry, materials, and lighting in a principled, multi-stage pipeline. A cross-stage memory module is maintained throughout to mitigate context forgetting inherent to existing agent-based frameworks. We further introduce a dedicated benchmark for code-based 3D 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. |
cite
@misc{yang2026code,
title={Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis},
author={Yixuan Yang and Zhen Luo and Wanshui Gan and Jinkun Hao and Junru Lu and Jinghao Yan and Zhaoyang Lyu and Xudong Xu},
year={2026},
eprint={2605.18451},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.18451}
}