Client Side Dynamic Aspect Ratio Based on Automated AI Analysis

Abstract

Media is to a large extent consumed on devices that have non-standard aspect ratios, both physically or while rendering content. For example, social media platforms, televisions, tablets, and android devices, most commonly utilise varying aspect ratios of 1, 16:9, 4:3/3:4, 16:9/9:16, respectively. Web pages tend to use responsive design and can therefore have almost any aspect ratio. As current solutions are static, multiple encoded versions of the content must be created to cater for different aspect ratios, increasing workload, storage space requirements and content management complexity. With this in mind, there is a case for client side dynamic aspect ratios that adapt suitably to the user's device to improve their viewing experience based on a common encoded version of the content. In this paper we make the case for a client side dynamic aspect ratio solution, present work on implementation and experimentation, and finally provide some insights into how such a system could be implemented and provided in real world systems. Our solution was tested on content provided by NRK, including both drama series and TV debates.