Vinci: An Intelligent Graphic Design System for Generating Advertising Posters

Advertising posters are a commonly used form of information presentation to promote a product. Producing advertising posters often takes much time and effort of designers when confronted with abundant choices of design elements and layouts. This paper presents Vinci, an intelligent system that supports the automatic generation of advertising posters. Given the user-specified product image and taglines, Vinci uses a deep generative model to match the product image with a set of design elements and layouts for generating an aesthetic poster. The system also integrates online editing-feedback that supports users in editing the posters and updating the generated results with their design preference. Through a series of user studies and a Turing test, we found that Vinci can generate posters as good as human designers and that the online editing-feedback improves the efficiency in poster modification.

[1]  Chen Sun,et al.  Revisiting Unreasonable Effectiveness of Data in Deep Learning Era , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[2]  S. Srihari.  Mixture Density Networks , 1994 .

[3]  Jock D. Mackinlay,et al.  Applying a theory of graphical presentation to the graphic design of user interfaces , 1988, UIST '88.

[4]  Antti Oulasvirta,et al.  Sketchplore: Sketch and Explore with a Layout Optimiser , 2016, Conference on Designing Interactive Systems.

[5]  Gang Chen,et al.  Understanding Programmatic Creative: The Role of AI , 2019, Journal of Advertising.

[6]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[7]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[8]  Ali Jahanian,et al.  Automatic Design of Self-Published Media: A Case Study of Magazine Covers , 2016 .

[9]  Steven K. Feiner,et al.  A Survey of Automated Layout Techniques for Information Presentations , 2005 .

[10]  Yanghua Jin.  Create Anime Characters with A . I . ! , 2017 .

[11]  Tao Mei,et al.  Automatic Generation of Visual-Textual Presentation Layout , 2016, ACM Trans. Multim. Comput. Commun. Appl..

[12]  Ya Zhang,et al.  Chinese Typeface Transformation with Hierarchical Adversarial Network , 2017, ArXiv.

[13]  Douglas Eck,et al.  A Neural Representation of Sketch Drawings , 2017, ICLR.

[14]  Nan Cao,et al.  EmoG: Supporting the Sketching of Emotional Expressions for Storyboarding , 2020, CHI.

[15]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[16]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[17]  Irfan Essa,et al.  Automatic Video Creation From a Web Page , 2020, UIST.

[18]  Leon A. Gatys,et al.  Image Style Transfer Using Convolutional Neural Networks , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Rynson W. H. Lau,et al.  Content-aware generative modeling of graphic design layouts , 2019, ACM Trans. Graph..

[20]  Anthony Jameson,et al.  Understanding and Dealing With Usability Side Effects of Intelligent Processing , 2009, AI Mag..

[21]  Rynson W. H. Lau,et al.  What characterizes personalities of graphic designs? , 2018, ACM Trans. Graph..

[22]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[23]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[24]  Simon Haykin,et al.  GradientBased Learning Applied to Document Recognition , 2001 .

[25]  Xin Yan,et al.  AI-Sketcher : A Deep Generative Model for Producing High-Quality Sketches , 2019, AAAI.

[26]  Keigo Hirokawa,et al.  Diverse Layout Generation for Graphical Design Magazines , 2019, SIGGRAPH Asia Posters.

[27]  Melanie Hartmann,et al.  Challenges in Developing User-Adaptive Intelligent User Interfaces , 2009, LWA.

[28]  Çagatay Demiralp,et al.  Data2Vis: Automatic Generation of Data Visualizations Using Sequence-to-Sequence Recurrent Neural Networks , 2018, IEEE Computer Graphics and Applications.

[29]  Hiroki Yoshihara,et al.  Automatic layout generation for graphical design magazines , 2019, SIGGRAPH Posters.

[30]  Robin Landa,et al.  Graphic Design Solutions , 1996 .

[31]  Zhi-Hua Zhou,et al.  Learning to Generate Posters of Scientific Papers by Probabilistic Graphical Models , 2017, Journal of Computer Science and Technology.

[32]  Alexei A. Efros,et al.  Generative Visual Manipulation on the Natural Image Manifold , 2016, ECCV.

[33]  Aaron Hertzmann,et al.  DesignScape: Design with Interactive Layout Suggestions , 2015, CHI.

[34]  Rynson W. H. Lau,et al.  ICONATE: Automatic Compound Icon Generation and Ideation , 2020, CHI.

[35]  Xin Wang,et al.  Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfer , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  Samy Bengio,et al.  Generating Sentences from a Continuous Space , 2015, CoNLL.

[37]  Tingfa Xu,et al.  LayoutGAN: Generating Graphic Layouts with Wireframe Discriminators , 2019, ICLR.

[38]  Tao Mei,et al.  Automatic generation of social media snippets for mobile browsing , 2013, ACM Multimedia.

[39]  Fernando Alonso,et al.  On the testability of WCAG 2.0 for beginners , 2010, W4A.