Conference proceeding
FBRNN: feedback recurrent neural network for extreme image super-resolution
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), v 2020-, pp 2021-2028
Jun 2020
Abstract
Single image extreme Super Resolution (SR) is a difficult task as scale factor in the order of 10X or greater is typically attempted. For instance, in the case of 16x upscale of an image, a single pixel from a low resolution image gets expanded to a 16x16 image patch. Such attempts often result fuzzy quality and loss in details in reconstructed images. To handle these difficulties, we propose a network architecture composed of a series of connected blocks in recurrent and feedback fashions for enhanced SR reconstruction. By use of recurrent network, an SR image is refined over a sequence of enhancement stages in coarse to fine manner. Additionally, each stage involves back projection of SR image to LR images for continuously being refined during the sequence. According to the preliminary results of NTIRE 2020 Perceptual Extreme SR challenge, our team (KU_ISPLB) secured 6th place by PSNR and 7th place by SSIM among all participants.
Metrics
Details
- Title
- FBRNN: feedback recurrent neural network for extreme image super-resolution
- Creators
- Junyeop Lee - Korea UniversityJaihyun Park - Korea UniversityKanghyu Lee - Korea UniversityJeongki Min - Korea UniversityGwantae Kim - Korea UniversityBokyeung Lee - Korea UniversityBonhwa Ku - Korea UniversityDavid K. Han - DEVCOM Army Research LaboratoryHanseok Ko - Korea UniversityIEEE COMP SOC
- Publication Details
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), v 2020-, pp 2021-2028
- Publisher
- IEEE
- Number of pages
- 8
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Electrical and Computer Engineering
- Web of Science ID
- WOS:000788279002012
- Scopus ID
- 2-s2.0-85090155281
- Other Identifier
- 991021931089304721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- International collaboration
- Web of Science research areas
- Computer Science, Artificial Intelligence
- Computer Science, Theory & Methods