House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation

2020/03/16 by Nelson Nauata, Kai-Hung Chang, Nauata, Nelson +7 · 1 voice · 8 citations
Computer Science · Engineering · #3D Shape Modeling and Analysis #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #cs.CV

paper · pdf · doi:10.48550/arxiv.2003.06988

openalex publication_date 2020/03/16 · arxiv published 2020/03/16 · arxiv updated 2020/03/16 · openalex created_date 2020/03/23 · openalex updated_date 2026/07/28

Abstract

This paper proposes a novel graph-constrained generative adversarial network, whose generator and discriminator are built upon relational architecture. The main idea is to encode the constraint into the graph structure of its relational networks. We have demonstrated the proposed architecture for a new house layout generation problem, whose task is to take an architectural constraint as a graph (i.e., the number and types of rooms with their spatial adjacency) and produce a set of axis-aligned bounding boxes of rooms. We measure the quality of generated house layouts with the three metrics: the realism, the diversity, and the compatibility with the input graph constraint. Our qualitative and quantitative evaluations over 117,000 real floorplan images demonstrate that the proposed approach outperforms existing methods and baselines. We will publicly share all our code and data.

Cited by

• GFLAN: Generative Functional Layouts
• GreenPlanner: Practical Floorplan Layout Generation via an Energy-Aware and Function-Feasible Generative Framework
• Co-Layout: LLM-driven Co-optimization for Interior Layout
• OmniDocLayout: Towards Diverse Document Layout Generation via Coarse-to-Fine LLM Learning
• Learning and Simulating Building Evacuation Patterns for Enhanced Safety Design Using Generative Models
• LayoutGKN: Graph Similarity Learning of Floor Plans
• Eliminating Rasterization: Direct Vector Floor Plan Generation with DiffPlanner
• FloorPlan-DeepSeek (FPDS): A multimodal approach to floorplan generation using vector-based next room prediction

Discussions

• HouseGAN: Generate Realistic Floor Plan Layouts from Relational Graphs [hn, 2 points, 1 comments]

Related

• House-GAN++: Generative Adversarial Layout Refinement Networks
• Graph Transformer GANs for Graph-Constrained House Generation
• Graph Transformer GANs with Graph Masked Modeling for Architectural Layout Generation
• ActFloor-GAN: Activity-Guided Adversarial Networks for Human-Centric Floorplan Design
• GFLAN: Generative Functional Layouts