Towards Deep Learning Methods for Quality Assessment of Computer-Generated Imagery

Abstract

Video gaming streaming services are growing rapidly due to new services such as passive video streaming, e.g. Twitch.tv, and cloud gaming, e.g. Nvidia Geforce Now. In contrast to traditional video content, gaming content has special characteristics such as extremely high motion for some games, special motion patterns, synthetic content and repetitive content, which makes the state-of-the-art video and image quality metrics perform weaker for this special computer generated content. In this paper, we outline our plan to build a deep learningbased quality metric for video gaming quality assessment. In addition, we present initial results by training the network based on VMAF values as a ground truth to give some insights on how to build a metric in future. The paper describes the method that is used to choose an appropriate Convolutional Neural Network architecture. Furthermore, we estimate the size of the required subjective quality dataset which achieves a sufficiently high performance. The results show that by taking around 5k images for training of the last six modules of Xception, we can obtain a relatively high performance metric to assess the quality of distorted video games.

Utilizing Active Machine Learning for Quality Assurance: A Case Study of Virtual Car Renderings in the Automotive Industry

“…The closest work relevant in this regard is the area of video game streaming [15]. As cloud gaming solutions like Google Stadia, Playstation Now or Nvidia Geforce Now [36] allow the streaming of video games via the internet, a niche group of researchers aims to detect quality issues in the generated video streams [37,38,39]. However, to the best of our knowledge, no work previously explored QA for CGI within an industrial context.…”