Filters








3 Hits in 3.8 sec

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

Nelson Nauata, Kai-Hung Chang, Chin-Yi Cheng, Greg Mori, Yasutaka Furukawa
2020 arXiv   pre-print
This paper proposes a novel graph-constrained generative adversarial network, whose generator and discriminator are built upon relational architecture.  ...  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  ...  We would like to thank architects and students for participating in our user study.  ... 
arXiv:2003.06988v1 fatcat:l3awmdlkxrau3flx5l64oigbea

House-GAN++: Generative Adversarial Layout Refinement Networks [article]

Nelson Nauata, Sepidehsadat Hosseini, Kai-Hung Chang, Hang Chu, Chin-Yi Cheng, Yasutaka Furukawa
2021 arXiv   pre-print
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 previously generated layout becomes the next input constraint, enabling iterative refinement.  ...  We would like to thank architects and students for participating in our user study.  ... 
arXiv:2103.02574v1 fatcat:kqeskhqec5dulesb23mkl6gkme

Generative Design Software Development Process for Architecture

Siyu Guo
2021
To demonstrate the feasibility of the process, I developed a GD software for a basement parking layout design task.  ...  Based on the generative method of variational modeling with optimization, this tool can generate a variety of valuablebasement parking layouts in a very limited amount of time.  ...  For example the House-GAN project, which is a novel graph-constrained house layout generator based on a relational generative adversarial network (Nauata et al. 2020) , and the GAN based room layout  ... 
doi:10.1184/r1/14136008.v1 fatcat:tvijsckei5beneqywuunneq7na