Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Supremo: Cloud-Assisted Low-Latency Super-Resolution in Mobile Devices

Authors
Yi, JuheonKim, SeongwonKim, JoongheonChoi, Sunghyun
Issue Date
1-5월-2022
Publisher
IEEE COMPUTER SOC
Keywords
Mobile deep learning; cloud offloading; image super-resolution
Citation
IEEE TRANSACTIONS ON MOBILE COMPUTING, v.21, no.5, pp.1847 - 1860
Indexed
SCIE
SCOPUS
Journal Title
IEEE TRANSACTIONS ON MOBILE COMPUTING
Volume
21
Number
5
Start Page
1847
End Page
1860
URI
https://scholar.korea.ac.kr/handle/2021.sw.korea/140398
DOI
10.1109/TMC.2020.3025300
ISSN
1536-1233
Abstract
We present Supremo, a cloud-assisted system for low-latency image super-resolution (SR) in mobile devices. As SR is extremely compute-intensive, we first further optimize state-of-the-art DNN to reduce the inference latency. Furthermore, we design a mobile-cloud cooperative execution pipeline composed of specialized data compression algorithms to minimize end-to-end latency with minimal image quality degradation. Finally, we extend Supremo to video applications by formulating a dynamic optimal control algorithm to design Supremo-Opt, which aims to maximize the impact of SR while satisfying latency and resource constraints under practical network conditions. Supremo upscales 360p image to 1080p in 122 ms, which is 43.68x faster than on-device GPU execution. Compared to cloud offloading-based solutions, Supremo reduces wireless network bandwidth consumption and end-to-end latency by 15.23 x and 4.85x compared to baseline approach of sending and receiving whole images, and achieves 2.39 dB higher PSNR compared to using conventional JPEG to achieve similar data size compression. Furthermore, Supremo-Opt guarantees robust performance in practical scenarios.
Files in This Item
There are no files associated with this item.
Appears in
Collections
College of Engineering > School of Electrical Engineering > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Kim, Joong heon photo

Kim, Joong heon
공과대학 (전기전자공학부)
Read more

Altmetrics

Total Views & Downloads

BROWSE