Super-resolution Based Bitrate Adaptation for HTTP Adaptive Streaming for Mobile Devices

Published:

Published In: ACM Mile-High Video Conference, March 01-03, 2022, Denver, CO, USA
Conference Website: https://mile-high.video/
Paper Link: https://dl.acm.org/doi/10.1145/3510450.3517322

Authors: Minh Nguyen, Ekrem Çetinkaya, Hermann Hellwagner, and Christian Timmerer (Christian Doppler Laboratory ATHENA, Alpen-Adria-Universität Klagenfurt)

Abstract: This paper introduces a lightweight super-resolution (SR) network to upgrade low-resolution/-quality videos and SR-WISH, a novel adaptive bitrate (ABR) algorithm, that leverages SR networks at the client to improve the video quality depending on the client’s context. Existing results indicate that the proposed SR network can significantly improve video quality compared to traditional approaches. SR-WISH takes into account mobile device properties, video characteristics, and user preferences.

Keywords: Super resolution, Deep Neural Networks, Mobile Devices

Citation:

@inproceedings{srabr,
    author = {Nguyen, Minh and \c{C}etinkaya, Ekrem and Hellwagner, Hermann and Timmerer, Christian},
    title = {Super-Resolution Based Bitrate Adaptation for HTTP Adaptive Streaming for Mobile Devices},
    year = {2022},
    isbn = {9781450392228},
    publisher = {Association for Computing Machinery},
    address = {New York, NY, USA},
    url = {https://doi.org/10.1145/3510450.3517322},
    doi = {10.1145/3510450.3517322},
    pages = {70–76},
    numpages = {7},
    location = {Denver, Colorado},
    series = {MHV '22}
}