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

• URL: http://arxiv.org/abs/2605.18451v1
• Date: Mon, 18 May 2026 14:18:36 GMT
• Title: Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis
• Abstract summary: We propose Code-as-Room, an MLLM-based agentic framework equipped with a structured execution harness.<n>Given a top-down room image, the framework parses the reference image to extract scene elements and their spatial relationships.<n>A cross-stage memory module is maintained throughout to mitigate context inherent to existing agent-based frameworks.
• Score: 12.68633443613779
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• 3DHarnessBench: Probing Agentic 3D-to-Code Capabilities of Frontier Vision-Language Models [35.365323691170616]
  3DHarnessBench is a benchmark that evaluates the agentic ability of vision-correction models to recover 3D geometry as Blender Python code.<n>We observe that the ability of all frontier models to recover 3D geometry improves significantly with richer function call access.<n>We will release the benchmark, code, outputs, and agent trajectories for reproducible 3D evaluation.
  arXiv  Detail & Related papers  (2026-09-06T10:59:15Z)
• 3D-CoS: A New 3D Reconstruction Paradigm Based on VLM Code Synthesis [69.23609431485401]
  We propose and systematically evaluate a new 3D reconstruction paradigm, where 3D assets are constructed as executable code.<n>Our study shows that code as a 3D representation offers strong controllability and locality, yielding stronger edit fidelity and better preservation of unedited regions.
  arXiv  Detail & Related papers  (2026-06-09T06:46:29Z)
• Think, Act, Build: An Agentic Framework with Vision Language Models for Zero-Shot 3D Visual Grounding [34.1504914582344]
  3D Visual Grounding aims to localize objects in 3D scenes via natural language descriptions.<n>We propose "Think, Act, Build (TAB)", a generative 2D-to-3D reconstruction paradigm operating directly on raw RGB-D streams.<n>To overcome the multi-view coverage deficit caused by strict VLM semantic tracking, we introduce the Semantic-Anchored Geometric Expansion.
  arXiv  Detail & Related papers  (2026-04-01T06:12:16Z)
• RoomEditor++: A Parameter-Sharing Diffusion Architecture for High-Fidelity Furniture Synthesis [89.26382925677301]
  Virtual furniture synthesis holds substantial promise for home design and e-commerce applications.<n>RoomEditor++ is a versatile diffusion-based architecture featuring a parameter-sharing dual diffusion backbone.<n>RoomEditor++ is superior over state-of-the-art approaches in terms of quantitative metrics, qualitative assessments, and human preference studies.
  arXiv  Detail & Related papers  (2025-12-19T13:39:43Z)
• SeqAffordSplat: Scene-level Sequential Affordance Reasoning on 3D Gaussian Splatting [85.87902260102652]
  We introduce the novel task of Sequential 3D Gaussian Affordance Reasoning.<n>We then propose SeqSplatNet, an end-to-end framework that directly maps an instruction to a sequence of 3D affordance masks.<n>Our method sets a new state-of-the-art on our challenging benchmark, effectively advancing affordance reasoning from single-step interactions to complex, sequential tasks at the scene level.
  arXiv  Detail & Related papers  (2025-07-31T17:56:55Z)
• Agentic 3D Scene Generation with Spatially Contextualized VLMs [67.31920821192323]
  We introduce a new paradigm that enables vision-language models to generate, understand, and edit complex 3D environments.<n>We develop an agentic 3D scene generation pipeline in which the VLM iteratively reads from and updates the spatial context.<n>Results show that our framework can handle diverse and challenging inputs, achieving a level of generalization not observed in prior work.
  arXiv  Detail & Related papers  (2025-05-26T15:28:17Z)
• HiScene: Creating Hierarchical 3D Scenes with Isometric View Generation [50.206100327643284]
  HiScene is a novel hierarchical framework that bridges the gap between 2D image generation and 3D object generation.<n>We generate 3D content that aligns with 2D representations while maintaining compositional structure.
  arXiv  Detail & Related papers  (2025-04-17T16:33:39Z)
• DeBaRA: Denoising-Based 3D Room Arrangement Generation [22.96293773013579]
  We introduce DeBaRA, a score-based model specifically tailored for precise, controllable and flexible arrangement generation in a bounded environment. We demonstrate that by focusing on spatial attributes of objects, a single trained DeBaRA model can be leveraged at test time to perform several downstream applications such as scene synthesis, completion and re-arrangement.
  arXiv  Detail & Related papers  (2024-09-26T23:18:25Z)
• Anything-3D: Towards Single-view Anything Reconstruction in the Wild [61.090129285205805]
  We introduce Anything-3D, a methodical framework that ingeniously combines a series of visual-language models and the Segment-Anything object segmentation model. Our approach employs a BLIP model to generate textural descriptions, utilize the Segment-Anything model for the effective extraction of objects of interest, and leverages a text-to-image diffusion model to lift object into a neural radiance field.
  arXiv  Detail & Related papers  (2023-04-19T16:39:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.