Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2412.00381 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916501091516416 |
|---|---|
| author | Gan, Zhaoxing Ye, Guangnan |
| author_facet | Gan, Zhaoxing Ye, Guangnan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_00381 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DogLayout: Denoising Diffusion GAN for Discrete and Continuous Layout Generation Gan, Zhaoxing Ye, Guangnan Computer Vision and Pattern Recognition 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. |
| title | DogLayout: Denoising Diffusion GAN for Discrete and Continuous Layout Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.00381 |