Study of Subjective and Objective Quality Assessment of Mobile Cloud Gaming Videos
Avinab Saha, Yu-Chih Chen, Chase Davis, Bo Qiu, Xiaoming Wang, Rahul Gowda, Ioannis Katsavounidis, Alan C. Bovik
TL;DR
This work addresses the lack of large-scale, publicly available Mobile Cloud Gaming VQA data by introducing the LIVE-Meta Mobile Cloud Gaming (LIVE-Meta MCG) database, comprising 600 distorted videos derived from 30 pristine sources and 14,400 subjective ratings collected in-lab on a modern mobile device. The authors provide a detailed subjective study protocol, including source selection, distortion pipeline (resolution/bitrate variants), a controlled testing environment, and an MLE-based MOS estimation that yields reliable DMOS values and subject/content consistency metrics. To demonstrate utility, they benchmark a wide range of NR-VQA models and compare them to FR-VQA baselines, revealing that hybrid deep-learning and NSS-based models (e.g., GAMIVAL, VSFA, GAME-VQP, RAPIQUE) achieve the best correlations with MOS, while VMAF-based proxies show strong potential for pre-training and as proxy-MOS sources. The dataset covers both portrait and landscape orientations, enabling analysis of orientation effects and content-dependent rate-distortion behavior, with findings suggesting landscape video may yield tighter confidence in MOS estimates and inform perceptually optimized mobile streaming strategies. Public release of LIVE-Meta MCG will support real-time VQA research, model benchmarking, and the development of perceptually aware cloud gaming QoE optimizations on mobile networks.
Abstract
We present the outcomes of a recent large-scale subjective study of Mobile Cloud Gaming Video Quality Assessment (MCG-VQA) on a diverse set of gaming videos. Rapid advancements in cloud services, faster video encoding technologies, and increased access to high-speed, low-latency wireless internet have all contributed to the exponential growth of the Mobile Cloud Gaming industry. Consequently, the development of methods to assess the quality of real-time video feeds to end-users of cloud gaming platforms has become increasingly important. However, due to the lack of a large-scale public Mobile Cloud Gaming Video dataset containing a diverse set of distorted videos with corresponding subjective scores, there has been limited work on the development of MCG-VQA models. Towards accelerating progress towards these goals, we created a new dataset, named the LIVE-Meta Mobile Cloud Gaming (LIVE-Meta-MCG) video quality database, composed of 600 landscape and portrait gaming videos, on which we collected 14,400 subjective quality ratings from an in-lab subjective study. Additionally, to demonstrate the usefulness of the new resource, we benchmarked multiple state-of-the-art VQA algorithms on the database. The new database will be made publicly available on our website: \url{https://live.ece.utexas.edu/research/LIVE-Meta-Mobile-Cloud-Gaming/index.html}