DogLayout: Denoising Diffusion GAN for Discrete and Continuous Layout Generation

TL;DR

DogLayout combines diffusion and GAN techniques to efficiently generate plausible layout arrangements with discrete labels, significantly reducing sampling time and improving layout quality over existing methods.

Contribution

It introduces a novel diffusion-GAN hybrid model that enables discrete label generation and drastically reduces sampling costs in layout synthesis.

Findings

Sampling time reduced by up to 175 times

Overlap decreased from 16.43 to 9.59

Outperforms existing GAN and diffusion-based layout methods

Abstract

Layout Generation aims to synthesize plausible arrangements from given elements. Currently, the predominant methods in layout generation are Generative Adversarial Networks (GANs) and diffusion models, each presenting its own set of challenges. GANs typically struggle with handling discrete data due to their requirement for differentiable generated samples and have historically circumvented the direct generation of discrete labels by treating them as fixed conditions. Conversely, diffusion-based models, despite achieving state-of-the-art performance across several metrics, require extensive sampling steps which lead to significant time costs. To address these limitations, we propose \textbf{DogLayout} (\textbf{D}en\textbf{o}ising Diffusion \textbf{G}AN \textbf{Layout} model), which integrates a diffusion process into GANs to enable the generation of discrete label data and significantly reduce diffusion's sampling time. Experiments demonstrate that DogLayout considerably reduces sampling costs by up to 175 times and cuts overlap from 16.43 to 9.59 compared to existing diffusion models, while also surpassing GAN based and other layout methods. Code is available at https://github.com/deadsmither5/DogLayout.