Orientation-aware deep neural network for real image super-resolution

Chen Du, He Zewei, Sun Anshun, Yang Jiangxin, Cao Yanlong, Cao Yanpeng*, Tang Siliang, Michael Ying Yang

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

2 Citations (Scopus)

Abstract

Recently, Convolutional Neural Network (CNN) based approaches have achieved impressive single image super-resolution (SISR) performance in terms of accuracy and visual effects. It is noted that most SISR methods assume that the low-resolution (LR) images are obtained through bicubic interpolation down-sampling, thus their performance on real-world LR images is limited. In this paper, we proposed a novel orientation-aware deep neural network (OA-DNN) model, which incorporate a number of orientation feature extraction and channel attention modules (OAMs), to achieve good SR performance on real-world LR images captured by a single-lens reflex (DSLR) camera. Orientation-aware features extracted in different directions are adaptively combined through a channel-wise attention mechanism to generate more distinctive features for high-fidelity recovery of image details. Moreover, we reshape the input image into smaller spatial size but deeper depth via an inverse pixel-shuffle operation to accelerate the training/testing speed without sacrificing restoration accuracy. Extensive experimental results indicate that our OA-DNN model achieves a good balance between accuracy and speed. The extended OA-DNN∗+ model further increases PSNR index by 0.18 dB compared with our previously submitted version. Codes will be made public after publication.

Original languageEnglish
Title of host publicationProceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019
PublisherIEEE Computer Society Press
Pages1944-1953
Number of pages10
ISBN (Electronic)9781728125060
DOIs
Publication statusPublished - Jun 2019
Event32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019 - Long Beach, United States
Duration: 16 Jun 201920 Jun 2019
Conference number: 32

Publication series

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume2019-June
ISSN (Print)2160-7508
ISSN (Electronic)2160-7516

Conference

Conference32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019
Abbreviated titleCVPRW 2019
CountryUnited States
CityLong Beach
Period16/06/1920/06/19

Fingerprint Dive into the research topics of 'Orientation-aware deep neural network for real image super-resolution'. Together they form a unique fingerprint.

  • Cite this

    Du, C., Zewei, H., Anshun, S., Jiangxin, Y., Yanlong, C., Yanpeng, C., ... Yang, M. Y. (2019). Orientation-aware deep neural network for real image super-resolution. In Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019 (pp. 1944-1953). [9025541] (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2019-June). IEEE Computer Society Press. https://doi.org/10.1109/CVPRW.2019.00246