Constrained Graphic Layout Generation via Latent Optimization

Kikuchi, Kotaro; Simo-Serra, Edgar; Otani, Mayu; Yamaguchi, Kota

doi:10.1145/3474085.3475497

Cited by 59 publications

(18 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kikuchi et al proposed LayoutGAN++ [9] demonstrating an improvement in handling user-specific constraints by optimizing layout in latent space. It got rid of using wireframe images with respect to the findings that the rendering layer is unstable with a dataset of a limited size.…”

Section: Related Workmentioning

confidence: 99%

PosterLayout: A New Benchmark and Approach for Content-aware Visual-Textual Presentation Layout

Hsu¹,

He²,

Peng³

et al. 2023

Preprint

View full text Add to dashboard Cite

Content-aware visual-textual presentation layout aims at arranging spatial space on the given canvas for pre-defined elements, including text, logo, and underlay, which is a key to automatic template-free creative graphic design. In practical applications, e.g., poster designs, the canvas is originally non-empty, and both inter-element relationships as well as inter-layer relationships should be concerned when generating a proper layout. A few recent works deal with them simultaneously, but they still suffer from poor graphic performance, such as a lack of layout variety or spatial non-alignment. Since content-aware visual-textual presentation layout is a novel task, we first construct a new dataset named PKU PosterLayout, which consists of 9,974 posterlayout pairs and 905 images, i.e., non-empty canvases. It is more challenging and useful for greater layout variety, domain diversity, and content diversity. Then, we propose design sequence formation (DSF) that reorganizes elements in layouts to imitate the design processes of human designers, and a novel CNN-LSTM-based conditional generative adversarial network (GAN) is presented to generate proper layouts. Specifically, the discriminator is design-sequenceaware and will supervise the "design" process of the generator. Experimental results verify the usefulness of the new benchmark and the effectiveness of the proposed approach, which achieves the best performance by generating suitable layouts for diverse canvases. The dataset and the source code are available at https://github.com/PKU-ICST-MIPL/PosterLayout-CVPR2023.

show abstract

Section: Related Workmentioning

confidence: 99%

PosterLayout: A New Benchmark and Approach for Content-aware Visual-Textual Presentation Layout

Hsu¹,

He²,

Peng³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Model In addition, we do not choose a wire-frame discriminator like [Li et al, 2019] because we empirically found that this relation discriminator with transformers performs better, the same as [Kikuchi et al, 2021].…”

Section: Composition-aware Layout Discriminatormentioning

confidence: 99%

Composition-aware Graphic Layout GAN for Visual-Textual Presentation Designs

Zuo

Liu

Lian

et al. 2022

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

Artistic style transfer is the task of synthesizing content images with learned artistic styles. Recent studies have shown the potential of Generative Adversarial Networks (GANs) for producing artistically rich stylizations. Despite the promising results, they usually fail to control the generated images' style degree, which is inflexible and limits their applicability for practical use. To address the issue, in this paper, we propose a novel method that for the first time allows adjusting the style degree for existing GAN-based artistic style transfer frameworks in real time after training. Our method introduces two novel modules into existing GAN-based artistic style transfer frameworks: a Style Scaling Injection (SSI) module and a Style Degree Interpretation (SDI) module. The SSI module accepts the value of Style Degree Factor (SDF) as the input and outputs parameters that scale the feature activations in existing models, offering control signals to alter the style degrees of the stylizations. And the SDI module interprets the output probabilities of a multi-scale content-style binary classifier as the style degrees, providing a mechanism to parameterize the style degree of the stylizations. Moreover, we show that after training our method can enable existing GAN-based frameworks to produce over-stylizations. The proposed method can facilitate many existing GAN-based artistic style transfer frameworks with marginal extra training overheads and modifications. Extensive qualitative evaluations on two typical GAN-based style transfer models demonstrate the effectiveness of the proposed method for gaining style degree control for them.

show abstract

“…As deep learning develops, LayoutGAN [Li et al, 2019], LayoutVAE [Jyothi et al, 2019] and VTN [Arroyo et al, 2021] appear to produce layouts from noise. Meanwhile, some conditional layout generation methods have been proposed [Li et al, 2021;Lee et al, 2020;Kikuchi et al, 2021]. But all these methods concentrate on…”

Section: Related Workmentioning

confidence: 99%

“…And the overall loss is the weighted sum of L adv and L rec . In addition, we do not choose a wire-frame discriminator like [Li et al, 2019] because we empirically found this relation discriminator with transformers performs better, the same as [Kikuchi et al, 2021].…”

Section: Composition-aware Layout Discriminatormentioning

confidence: 99%

Composition-aware Graphic Layout GAN for Visual-textual Presentation Designs

Zhou¹,

Xu²,

Ma³

et al. 2022

Preprint

View full text Add to dashboard Cite

In this paper, we study the graphic layout generation problem of producing high-quality visualtextual presentation designs for given images. We note that image compositions, which contain not only global semantics but also spatial information, would largely affect layout results. Hence, we propose a deep generative model, dubbed as composition-aware graphic layout GAN (CGL-GAN), to synthesize layouts based on the global and spatial visual contents of input images. To obtain training images from images that already contain manually designed graphic layout data, previous work suggests masking design elements (e.g., texts and embellishments) as model inputs, which inevitably leaves hint of the ground truth. We study the misalignment between the training inputs (with hint masks) and test inputs (without masks), and design a novel domain alignment module (DAM) to narrow this gap. For training, we built a large-scale layout dataset which consists of 60,548 advertising posters with annotated layout information. To evaluate the generated layouts, we propose three novel metrics according to aesthetic intuitions. Through both quantitative and qualitative evaluations, we demonstrate that the proposed model can synthesize high-quality graphic layouts according to image compositions 1 .

show abstract

Constrained Graphic Layout Generation via Latent Optimization

Cited by 59 publications

References 38 publications

PosterLayout: A New Benchmark and Approach for Content-aware Visual-Textual Presentation Layout

PosterLayout: A New Benchmark and Approach for Content-aware Visual-Textual Presentation Layout

Composition-aware Graphic Layout GAN for Visual-Textual Presentation Designs

Composition-aware Graphic Layout GAN for Visual-textual Presentation Designs

Contact Info

Product

Resources

About