TY - GEN
T1 - DcSR
T2 - 17th ACM International Conference on emerging Networking EXperiments and Technologies, CoNEXT 2021
AU - Baek, Duin
AU - Dasari, Mallesham
AU - Das, Samir R.
AU - Ryoo, Jihoon
N1 - Publisher Copyright: © 2021 ACM.
PY - 2021/12/2
Y1 - 2021/12/2
N2 - With the next generation immersive video applications, network capacity is becoming a growing bottleneck to deliver a high quality video to end-users. Recent advances to tackle this challenge introduced super-resolution (SR) for video quality enhancement through neural computations by leveraging client-side compute capacity. However, the existing SR models are bulky, compute-, and memory-expensive, which makes it difficult to deploy them in practice. In this work, we present dcSR, a lightweight data-centric SR approach that enables a practical neural quality enhancement for videos. On the server-side, dcSR constructs micro SR models trained on a few selected frames from each video through a data-centric paradigm by employing a long term video scene understanding mechanism. On the client-side, dcSR integrates the micro SR models into the regular video decoder and enhances the video quality in real-time without compromising on quality enhancement. We evaluate dcSR and show its benefits by comparing it with previous methods.
AB - With the next generation immersive video applications, network capacity is becoming a growing bottleneck to deliver a high quality video to end-users. Recent advances to tackle this challenge introduced super-resolution (SR) for video quality enhancement through neural computations by leveraging client-side compute capacity. However, the existing SR models are bulky, compute-, and memory-expensive, which makes it difficult to deploy them in practice. In this work, we present dcSR, a lightweight data-centric SR approach that enables a practical neural quality enhancement for videos. On the server-side, dcSR constructs micro SR models trained on a few selected frames from each video through a data-centric paradigm by employing a long term video scene understanding mechanism. On the client-side, dcSR integrates the micro SR models into the regular video decoder and enhances the video quality in real-time without compromising on quality enhancement. We evaluate dcSR and show its benefits by comparing it with previous methods.
KW - Super resolution
KW - Video compression
KW - Video streaming
UR - https://www.scopus.com/pages/publications/85121653336
U2 - 10.1145/3485983.3494856
DO - 10.1145/3485983.3494856
M3 - Conference contribution
T3 - CoNEXT 2021 - Proceedings of the 17th International Conference on emerging Networking EXperiments and Technologies
SP - 336
EP - 343
BT - CoNEXT 2021 - Proceedings of the 17th International Conference on emerging Networking EXperiments and Technologies
PB - Association for Computing Machinery, Inc
Y2 - 7 December 2021 through 10 December 2021
ER -