Evaluating parameterization methods for convolutional neural network (CNN)-based image operators

Seung Wook Kim, Sung Jin Cho, Kwang Hyun Uhm, Seo Won Ji, Sang Won Lee, Sung Jea Ko

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Recently, deep neural networks have been widely used to approximate or improve image operators. In general, an image operator has some hyper-parameters that change its operating configurations, e.g., the strength of smoothing, up-scale factors in super-resolution, or a type of image operator. To address varying parameter settings, an image operator taking such parameters as its input, namely a parameterized image operator, is an essential cue in image processing. Since many types of parameterization techniques exist, a comparative analysis is required in the context of image processing. In this paper, we therefore analytically explore the operation principles of these parameterization techniques and study their differences. In addition, performance comparisons between image operators parameterized by using these methods are assessed experimentally on common image processing tasks including image smoothing, denoising, deblocking, and super-resolution.

Original languageEnglish
Title of host publicationProceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019
PublisherIEEE Computer Society
Pages1862-1870
Number of pages9
ISBN (Electronic)9781728125060
DOIs
Publication statusPublished - 2019 Jun
Event32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019 - Long Beach, United States
Duration: 2019 Jun 162019 Jun 20

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
CountryUnited States
CityLong Beach
Period19/6/1619/6/20

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Evaluating parameterization methods for convolutional neural network (CNN)-based image operators'. Together they form a unique fingerprint.

  • Cite this

    Kim, S. W., Cho, S. J., Uhm, K. H., Ji, S. W., Lee, S. W., & Ko, S. J. (2019). Evaluating parameterization methods for convolutional neural network (CNN)-based image operators. In Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019 (pp. 1862-1870). [9025633] (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2019-June). IEEE Computer Society. https://doi.org/10.1109/CVPRW.2019.00237