LayoutDiffusion: Improving Graphic Layout Generation by Discrete Diffusion Probabilistic Models
This work addresses the challenge of generating graphic layouts, which is fundamental in design, by introducing a novel diffusion-based approach that improves performance and flexibility.
The paper tackles the problem of automatic graphic layout generation by proposing LayoutDiffusion, a discrete diffusion probabilistic model that improves layout generation by modeling it as a discrete denoising process with a mild forward process. It significantly outperforms state-of-the-art methods on RICO and PubLayNet datasets and enables plug-and-play conditional generation tasks without re-training.
Creating graphic layouts is a fundamental step in graphic designs. In this work, we present a novel generative model named LayoutDiffusion for automatic layout generation. As layout is typically represented as a sequence of discrete tokens, LayoutDiffusion models layout generation as a discrete denoising diffusion process. It learns to reverse a mild forward process, in which layouts become increasingly chaotic with the growth of forward steps and layouts in the neighboring steps do not differ too much. Designing such a mild forward process is however very challenging as layout has both categorical attributes and ordinal attributes. To tackle the challenge, we summarize three critical factors for achieving a mild forward process for the layout, i.e., legality, coordinate proximity and type disruption. Based on the factors, we propose a block-wise transition matrix coupled with a piece-wise linear noise schedule. Experiments on RICO and PubLayNet datasets show that LayoutDiffusion outperforms state-of-the-art approaches significantly. Moreover, it enables two conditional layout generation tasks in a plug-and-play manner without re-training and achieves better performance than existing methods.