The Library
Journey towards tiny perceptual super-resolution
Tools
Lee, Royson, Dudziak, Łukasz, Abdelfattah, Mohamed , Venieris, Stylianos I. , Kim, Hyeji , Wen, Hongkai and Lane, Nicholas D. (2020) Journey towards tiny perceptual super-resolution. In: 16th European Conference on Computer Vision, Virtual conference, 23-28 Aug 2020. Published in: Computer Vision – ECCV 2020 : 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXVI, 12371 pp. 85-102. ISBN 9783030585730. doi:10.1007/978-3-030-58574-7_6
|
PDF
WRAP-Journey-towards-tiny-perceptual-super-resolution-Wen-2020.pdf - Accepted Version - Requires a PDF viewer. Download (2909Kb) | Preview |
Official URL: https://doi.org/10.1007/978-3-030-58574-7_6
Abstract
Recent works in single-image perceptual super-resolution (SR) have demonstrated unprecedented performance in generating realistic textures by means of deep convolutional networks. However, these convolutional models are excessively large and expensive, hindering their effective deployment to end devices. In this work, we propose a neural architecture search (NAS) approach that integrates NAS and generative adversarial networks (GANs) with recent advances in perceptual SR and pushes the efficiency of small perceptual SR models to facilitate on-device execution. Specifically, we search over the architectures of both the generator and the discriminator sequentially, highlighting the unique challenges and key observations of searching for an SR-optimized discriminator and comparing them with existing discriminator architectures in the literature. Our tiny perceptual SR (TPSR) models outperform SRGAN and EnhanceNet on both full-reference perceptual metric (LPIPS) and distortion metric (PSNR) while being up to 26.4 × more memory efficient and 33.6 × more compute efficient respectively.
Item Type: | Conference Item (Paper) | ||||||
---|---|---|---|---|---|---|---|
Alternative Title: | |||||||
Subjects: | Q Science > Q Science (General) Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software T Technology > T Technology (General) T Technology > TK Electrical engineering. Electronics Nuclear engineering |
||||||
Divisions: | Faculty of Science, Engineering and Medicine > Science > Computer Science | ||||||
Library of Congress Subject Headings (LCSH): | High resolution imaging, Neural networks (Computer science), Computer network architectures, Machine learning | ||||||
Series Name: | Lecture Notes in Computer Science | ||||||
Journal or Publication Title: | Computer Vision – ECCV 2020 : 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXVI | ||||||
Publisher: | Springer | ||||||
ISBN: | 9783030585730 | ||||||
Official Date: | 13 November 2020 | ||||||
Dates: |
|
||||||
Volume: | 12371 | ||||||
Page Range: | pp. 85-102 | ||||||
DOI: | 10.1007/978-3-030-58574-7_6 | ||||||
Status: | Peer Reviewed | ||||||
Publication Status: | Published | ||||||
Access rights to Published version: | Restricted or Subscription Access | ||||||
Date of first compliant deposit: | 3 August 2020 | ||||||
Date of first compliant Open Access: | 4 August 2020 | ||||||
Conference Paper Type: | Paper | ||||||
Title of Event: | 16th European Conference on Computer Vision | ||||||
Type of Event: | Conference | ||||||
Location of Event: | Virtual conference | ||||||
Date(s) of Event: | 23-28 Aug 2020 | ||||||
Related URLs: | |||||||
Open Access Version: |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |
Downloads
Downloads per month over past year