Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraints

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Jian, Zhang, Ruiyi, Zhou, Yufan, Jain, Rajiv, Xu, Zhiqiang, Rossi, Ryan, Chen, Changyou
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917667547381760
author Chen, Jian
Zhang, Ruiyi
Zhou, Yufan
Jain, Rajiv
Xu, Zhiqiang
Rossi, Ryan
Chen, Changyou
author_facet Chen, Jian
Zhang, Ruiyi
Zhou, Yufan
Jain, Rajiv
Xu, Zhiqiang
Rossi, Ryan
Chen, Changyou
contents Controllable layout generation refers to the process of creating a plausible visual arrangement of elements within a graphic design (e.g., document and web designs) with constraints representing design intentions. Although recent diffusion-based models have achieved state-of-the-art FID scores, they tend to exhibit more pronounced misalignment compared to earlier transformer-based models. In this work, we propose the $\textbf{LA}$yout $\textbf{C}$onstraint diffusion mod$\textbf{E}$l (LACE), a unified model to handle a broad range of layout generation tasks, such as arranging elements with specified attributes and refining or completing a coarse layout design. The model is based on continuous diffusion models. Compared with existing methods that use discrete diffusion models, continuous state-space design can enable the incorporation of differentiable aesthetic constraint functions in training. For conditional generation, we introduce conditions via masked input. Extensive experiment results show that LACE produces high-quality layouts and outperforms existing state-of-the-art baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2402_04754
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraints
Chen, Jian
Zhang, Ruiyi
Zhou, Yufan
Jain, Rajiv
Xu, Zhiqiang
Rossi, Ryan
Chen, Changyou
Computer Vision and Pattern Recognition
Machine Learning
Controllable layout generation refers to the process of creating a plausible visual arrangement of elements within a graphic design (e.g., document and web designs) with constraints representing design intentions. Although recent diffusion-based models have achieved state-of-the-art FID scores, they tend to exhibit more pronounced misalignment compared to earlier transformer-based models. In this work, we propose the $\textbf{LA}$yout $\textbf{C}$onstraint diffusion mod$\textbf{E}$l (LACE), a unified model to handle a broad range of layout generation tasks, such as arranging elements with specified attributes and refining or completing a coarse layout design. The model is based on continuous diffusion models. Compared with existing methods that use discrete diffusion models, continuous state-space design can enable the incorporation of differentiable aesthetic constraint functions in training. For conditional generation, we introduce conditions via masked input. Extensive experiment results show that LACE produces high-quality layouts and outperforms existing state-of-the-art baselines.
title Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraints
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2402.04754