A Taxonomy for Generative Adversarial Networks in Dynamic Adaptive Streaming Over HTTP

Abstract

Generative Adversarial Networks (GANs) have emerged as a powerful tool in the field of Dynamic Adaptive Streaming over HTTP (DASH) to enhance various aspects of video streaming. This paper presents a taxonomy that categorizes the applications and techniques of GANs in the context of DASH. The taxonomy covers several key dimensions, including video generation, compression, quality enhancement, bandwidth adaptation, dynamic bitrate streaming, and cross-modal applications. Within each dimension, specific subcategories are identified to capture the diverse applications of GANs in DASH. Additionally, evaluation metrics for assessing the quality and effectiveness of GAN-based approaches are discussed. The taxonomy serves as a comprehensive framework to understand and organize the different ways in which GANs can be utilized to improve the streaming experience in DASH. By providing an organized structure, this taxonomy facilitates better understanding, comparison, and exploration of GAN-based approaches in DASH and enables researchers and practitioners to identify areas for further research and development.