%0 Conference Proceedings
%T Efficient Super-Resolution for Compression Of Gaming Videos
%A Yifan Wang
%A Luka Murn
%A Luis Herranz
%A Fei Yang
%A Marta Mrak
%A Wei Zhang
%A Shuai Wan
%A Marc Gorriz Blanch
%B IEEE International Conference on Acoustics, Speech and Signal Processing
%D 2023
%F Yifan Wang2023
%O LAMP; MACO
%O exported from refbase (http://158.109.8.37/show.php?record=3911), last updated on Fri, 19 Jan 2024 13:01:15 +0100
%X Due to the increasing demand for game-streaming services, efficient compression of computer-generated video is more critical than ever, especially when the available bandwidth is low. This paper proposes a super-resolution framework that improves the coding efficiency of computer-generated gaming videos at low bitrates. Most state-of-the-art super-resolution networks generalize over a variety of RGB inputs and use a unified network architecture for frames of different levels of degradation, leading to high complexity and redundancy. Since games usually consist of a limited number of fixed scenarios, we specialize one model for each scenario and assign appropriate network capacities for different QPs to perform super-resolution under the guidance of reconstructed high-quality luma components. Experimental results show that our framework achieves a superior quality-complexity trade-off compared to the ESRnet baseline, saving at most 93.59% parameters while maintaining comparable performance. The compression efficiency compared to HEVC is also improved by more than 17% BD-rate gain.
%U https://ieeexplore.ieee.org/document/10096031
%U http://dx.doi.org/10.1109/ICASSP49357.2023.10096031