Jiahao Fan, Yuxin Qin, Wei Feng, Yanyin Chen, Yaoyu Li, Ao Ma, Yixiu Li, Li Zhuang, Haoyi Bian, Zheng Zhang, Jingjing Lv, Junjie Shen, Ching Law
AutoPP automates the creation and optimization of product posters using a novel pipeline that integrates design and performance feedback to improve Click-Through Rates (CTR).
Creating eye-catching product posters that effectively capture customer interest can be a time-consuming task. AutoPP is a new system that automates this process by generating posters using basic product information and optimizing them based on how well they perform online. The system designs posters by combining background, text, and layout elements, and then tweaks them to improve their effectiveness in attracting clicks. AutoPP uses a large dataset of one million posters and feedback from users to refine its approach, showing significant improvements over traditional methods.
