Publikation: LiDeR: Lightweight Dense Residual Netwo...
Stammdaten
Titel: | LiDeR: Lightweight Dense Residual Network for Video Super-Resolution on Mobile Devices |
Untertitel: | |
Kurzfassung: | Video is now an essential part of the Internet. The increasing popularity of video streaming on mobile devices and the improvement in mobile displays brought together challenges to meet user expectations. Advancements in deep neural networks have seen successful applications on several computer vision tasks such as super-resolution (SR). Although DNN-based SR methods significantly improve over traditional methods, their computational complexity makes them challenging to apply on devices with limited power, such as smartphones. However, with the improvement in mobile hardware, especially GPUs, it is now possible to use DNN based solutions, though existing DNN based SR solutions are still too complex. This paper proposes LiDeR, a lightweight video SR network specifically tailored toward mobile devices. Experimental results show that LiDeR can achieve competitive SR performance with state-of-the-art networks while improving the execution speed significantly, i.e., 267% for X4 upscaling and 353% for X2 upscaling compared to ESPCN. |
Schlagworte: | Super-resolution, mobile devices, residual networks, deep neural networks, HAS |
Publikationstyp: | Beitrag in Proceedings (Autorenschaft) |
Erscheinungsdatum: | 26.06.2022 (Print) |
Erschienen in: |
IVMSP 2022 Proceedings of the IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop
IVMSP 2022 Proceedings of the IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop
(
IEEE;
)
zur Publikation |
Titel der Serie: | - |
Bandnummer: | - |
Erstveröffentlichung: | Ja |
Version: | - |
Seite: | S. 1 - 5 |
Versionen
Keine Version vorhanden |
Erscheinungsdatum: | 26.06.2022 |
ISBN: |
|
ISSN: | - |
Homepage: | https://ieeexplore.ieee.org/document/9816346 |
Erscheinungsdatum: | 11.07.2022 |
ISBN (e-book): | - |
eISSN: | - |
DOI: | http://dx.doi.org/10.1109/ivmsp54334.2022.9816346 |
Homepage: | https://ieeexplore.ieee.org/document/9816346 |
Open Access |
|
AutorInnen
Zuordnung
Organisation | Adresse | ||||
---|---|---|---|---|---|
Fakultät für Technische Wissenschaften
Institut für Informationstechnologie
|
AT - 9020 Klagenfurt am Wörthersee |
Kategorisierung
Sachgebiete | |
Forschungscluster | Kein Forschungscluster ausgewählt |
Peer Reviewed |
|
Publikationsfokus |
Klassifikationsraster der zugeordneten Organisationseinheiten:
|
Arbeitsgruppen |
|
Kooperationen
Forschungsaktivitäten
(Achtung: Externe Aktivitäten werden im Suchergebnis nicht mitangezeigt)
Projekte: |
|
Publikationen: | Keine verknüpften Publikationen vorhanden |
Veranstaltungen: |
|
Vorträge: |
|