PLay: Parametrically Conditioned Layout Generation using Latent Diffusion

Chin-Yi Cheng, Forrest Huang, Gang Li, Yang Li
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5449-5471, 2023.

Abstract

Layout design is an important task in various design fields, including user interfaces, document, and graphic design. As this task requires tedious manual effort by designers, prior works have attempted to automate this process using generative models, but commonly fell short of providing intuitive user controls and achieving design objectives. In this paper, we build a conditional latent diffusion model, PLay, that generates parametrically conditioned layouts in vector graphic space from user-specified guidelines, which are commonly used by designers for representing their design intents in current practices. Our method outperforms prior works across three datasets on metrics including FID and FD-VG, and in user test. Moreover, it brings a novel and interactive experience to professional layout design processes.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-cheng23b, title = {{PL}ay: Parametrically Conditioned Layout Generation using Latent Diffusion}, author = {Cheng, Chin-Yi and Huang, Forrest and Li, Gang and Li, Yang}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {5449--5471}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/cheng23b/cheng23b.pdf}, url = {https://proceedings.mlr.press/v202/cheng23b.html}, abstract = {Layout design is an important task in various design fields, including user interfaces, document, and graphic design. As this task requires tedious manual effort by designers, prior works have attempted to automate this process using generative models, but commonly fell short of providing intuitive user controls and achieving design objectives. In this paper, we build a conditional latent diffusion model, PLay, that generates parametrically conditioned layouts in vector graphic space from user-specified guidelines, which are commonly used by designers for representing their design intents in current practices. Our method outperforms prior works across three datasets on metrics including FID and FD-VG, and in user test. Moreover, it brings a novel and interactive experience to professional layout design processes.} }
Endnote
%0 Conference Paper %T PLay: Parametrically Conditioned Layout Generation using Latent Diffusion %A Chin-Yi Cheng %A Forrest Huang %A Gang Li %A Yang Li %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-cheng23b %I PMLR %P 5449--5471 %U https://proceedings.mlr.press/v202/cheng23b.html %V 202 %X Layout design is an important task in various design fields, including user interfaces, document, and graphic design. As this task requires tedious manual effort by designers, prior works have attempted to automate this process using generative models, but commonly fell short of providing intuitive user controls and achieving design objectives. In this paper, we build a conditional latent diffusion model, PLay, that generates parametrically conditioned layouts in vector graphic space from user-specified guidelines, which are commonly used by designers for representing their design intents in current practices. Our method outperforms prior works across three datasets on metrics including FID and FD-VG, and in user test. Moreover, it brings a novel and interactive experience to professional layout design processes.
APA
Cheng, C., Huang, F., Li, G. & Li, Y.. (2023). PLay: Parametrically Conditioned Layout Generation using Latent Diffusion. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:5449-5471 Available from https://proceedings.mlr.press/v202/cheng23b.html.

Related Material