DisCo-Layout: Disentangling and Coordinating Semantic and Physical Refinement in a Multi-Agent Framework for 3D Indoor Layout Synthesis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gao, Jialin, Zhou, Donghao, Liang, Mingjian, Liu, Lihao, Fu, Chi-Wing, Hu, Xiaowei, Heng, Pheng-Ann
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909821521887232
author Gao, Jialin
Zhou, Donghao
Liang, Mingjian
Liu, Lihao
Fu, Chi-Wing
Hu, Xiaowei
Heng, Pheng-Ann
author_facet Gao, Jialin
Zhou, Donghao
Liang, Mingjian
Liu, Lihao
Fu, Chi-Wing
Hu, Xiaowei
Heng, Pheng-Ann
contents 3D indoor layout synthesis is crucial for creating virtual environments. Traditional methods struggle with generalization due to fixed datasets. While recent LLM and VLM-based approaches offer improved semantic richness, they often lack robust and flexible refinement, resulting in suboptimal layouts. We develop DisCo-Layout, a novel framework that disentangles and coordinates physical and semantic refinement. For independent refinement, our Semantic Refinement Tool (SRT) corrects abstract object relationships, while the Physical Refinement Tool (PRT) resolves concrete spatial issues via a grid-matching algorithm. For collaborative refinement, a multi-agent framework intelligently orchestrates these tools, featuring a planner for placement rules, a designer for initial layouts, and an evaluator for assessment. Experiments demonstrate DisCo-Layout's state-of-the-art performance, generating realistic, coherent, and generalizable 3D indoor layouts. Our code will be publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2510_02178
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DisCo-Layout: Disentangling and Coordinating Semantic and Physical Refinement in a Multi-Agent Framework for 3D Indoor Layout Synthesis
Gao, Jialin
Zhou, Donghao
Liang, Mingjian
Liu, Lihao
Fu, Chi-Wing
Hu, Xiaowei
Heng, Pheng-Ann
Robotics
Computer Vision and Pattern Recognition
3D indoor layout synthesis is crucial for creating virtual environments. Traditional methods struggle with generalization due to fixed datasets. While recent LLM and VLM-based approaches offer improved semantic richness, they often lack robust and flexible refinement, resulting in suboptimal layouts. We develop DisCo-Layout, a novel framework that disentangles and coordinates physical and semantic refinement. For independent refinement, our Semantic Refinement Tool (SRT) corrects abstract object relationships, while the Physical Refinement Tool (PRT) resolves concrete spatial issues via a grid-matching algorithm. For collaborative refinement, a multi-agent framework intelligently orchestrates these tools, featuring a planner for placement rules, a designer for initial layouts, and an evaluator for assessment. Experiments demonstrate DisCo-Layout's state-of-the-art performance, generating realistic, coherent, and generalizable 3D indoor layouts. Our code will be publicly available.
title DisCo-Layout: Disentangling and Coordinating Semantic and Physical Refinement in a Multi-Agent Framework for 3D Indoor Layout Synthesis
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.02178