Multi-Object Advertisement Creative Generation
Jialu Gao, Mithun Das Gupta, Qun Li, Raveena Kshatriya, Andrew D. Wilson, Keng-hao Chang, Balasaravanan Thoravi Kumaravel

TL;DR
This paper introduces CreativeAds, a scalable AI system for generating multi-object lifestyle advertisement images, addressing challenges in product pairing, layout, and background to help advertisers create high-quality images efficiently.
Contribution
CreativeAds is a novel multi-product ad creation system that automates image generation with customizable controls, improving scalability and quality for e-commerce advertising.
Findings
CreativeAds can generate large volumes of high-quality ad images.
The system supports user customization and oversight.
User study shows effectiveness in real-world advertising scenarios.
Abstract
Lifestyle images are photographs that capture environments and objects in everyday settings. In furniture product marketing, advertisers often create lifestyle images containing products to resonate with potential buyers, allowing buyers to visualize how the products fit into their daily lives. While recent advances in Generative Artificial Intelligence (GenAI) have given rise to realistic image content creation, their application in e-commerce advertising is challenging because high-quality ads must authentically representing the products in realistic scearios. Therefore, manual intervention is usually required for individual generations, making it difficult to scale to larger product catalogs. To understand the challenges faced by advertisers using GenAI to create lifestyle images at scale, we conducted evaluations on ad images generated using state-of-the-art image generation models…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGenerative Adversarial Networks and Image Synthesis · Innovative Human-Technology Interaction · Multimodal Machine Learning Applications
