paper-with-me

홈 › Papers

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

2020-03-16 · ECCV 2020 8 · Nelson Nauata, Kai-Hung Chang, Chin-Yi Cheng, Greg Mori, Yasutaka Furukawa

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.

📄 PDF Abstract BibTeX arXiv:2003.06988

Code (1)

ennauata/housegan pytorch

Tasks

DiversityGenerative Adversarial NetworkLayout Generation

Similar Papers 제목 키워드 기반

House-GAN++: Generative Adversarial Layout Refinement Network towards Intelligent Computational Agent for Professional Architects

2021-06-19 · CVPR 2021 1 · Nelson Nauata, Sepidehsadat Hosseini, Kai-Hung Chang, Hang Chu 외

This paper proposes a generative adversarial layout refinement network for automated floorplan generation. Our architecture is an integration of a graph-constrained relational GAN and a conditional GAN, where a previ…

House-GAN++: Generative Adversarial Layout Refinement Networks

2021-03-03 · Nelson Nauata, Sepidehsadat Hosseini, Kai-Hung Chang, Hang Chu 외

This paper proposes a novel generative adversarial layout refinement network for automated floorplan generation. Our architecture is an integration of a graph-constrained relational GAN and a conditional GAN, where a pre…

Graph Transformer GANs for Graph-Constrained House Generation

2023-03-14 · CVPR 2023 1 · Hao Tang, Zhenyu Zhang, Humphrey Shi, Bo Li 외

We present a novel graph Transformer generative adversarial network (GTGAN) to learn effective graph node relations in an end-to-end fashion for the challenging graph-constrained house generation task. The proposed graph…

Generative Adversarial NetworkHouse GenerationNode Classification

Graph Transformer GANs with Graph Masked Modeling for Architectural Layout Generation

2024-01-15 · Hao Tang, Ling Shao, Nicu Sebe, Luc van Gool

We present a novel graph Transformer generative adversarial network (GTGAN) to learn effective graph node relations in an end-to-end fashion for challenging graph-constrained architectural layout generation tasks. The pr…

Generative Adversarial NetworkGraph Representation LearningLayout GenerationNode Classification+1

GrannGAN: Graph annotation generative adversarial networks

2022-12-01 · Yoann Boget, Magda Gregorova, Alexandros Kalousis

We consider the problem of modelling high-dimensional distributions and generating new examples of data with complex relational feature structure coherent with a graph skeleton. The model we propose tackles the problem o…

Generative Adversarial NetworkGraph Matching