Abstract
This publication describes an approach for creating dynamic layouts in responsive advertising displays by utilizing artificial intelligence (AI) to extract comprehensive metadata from image assets. This methodology enhances presentation effectiveness by tailoring the arrangement and appearance of visual components based on the specific content of each image. Key information, such as saliency maps identifying visually important regions, extracted color data, and image quality signals, is leveraged during ad rendering to achieve dynamic layout adjustments, prevent component overlap, and ensure visual coherence for improved ad performance in responsive advertising.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Zhao, Yang; Li, Clyde; Jain, Parag; Terwilliger, Sam; Ruthazer, Alan; Lavelle, Rachel; Wang, Jiachen; and Gong, Haifeng, "AI-Powered Layout Generation for Dynamic Advertising Displays", Technical Disclosure Commons, (November 06, 2025)
https://www.tdcommons.org/dpubs_series/8844