Paper Info
Title
Layout Style Modeling for Automating Banner Design.
Abstract
Banner design for is challenging to clearly convey information while also satisfying aesthetic goals and complying with the banner owner or advertiser's visual identity system. In online advertising, banners are often born with tens of different display sizes and rapidly changing design styles to chase fashion in many distinct market areas and designers have to make huge efforts to adjust their designs for each display size and target style. Therefore, automating multi-size and multi-style banner design can greatly release designers' creativity. Different from previous work relying on a single unified omnipotent optimization to accomplish such a complex problem, we tackle it with a combination of layout style learning, interpolation and transfer. We optimize banner layout given the style parameter learned from a set of training banners for a particular display size and layout style. Such kind of optimization is faster and much more controllable than optimizing for all sizes and diverse styles. To achieve multi-size banner design, we collect style parameters for a small collection of various sizes and interpolate them to support arbitrary target size. To reduce the difficulty of style parameter training, we invent a novel style transfer technique so that creating a multi-size style becomes as easy as designing a single banner. With all of the three techniques described above, a robust and easy-to-use layout style model is built, upon which we automate the banner design. We test our method on a data set containing thousands of real banners for online advertising and evaluate our generated banners in various sizes and styles by comparing them with professional designs.
Year
DOI
Venue
2017
10.1145/3126686.3126718
MM '17: ACM Multimedia Conference Mountain View California USA October, 2017
Keywords
Field
DocType
Banner Layout, Multi-size Style, Layout Optimization, Style Interpolation, Style Transfer
Display size,Computer science,Design styles,Online advertising,Banner,Creativity,Multimedia
Conference
ISBN
Citations 
PageRank 
978-1-4503-5416-5
2
0.36
References 
Authors
26
6
Name
Order
Citations
PageRank
Yunke Zhang131.38
Kangkang Hu242.42
Peiran Ren316211.58
Changyuan Yang443.10
Weiwei Xu587550.19
Xian-Sheng Hua66566328.17