TY - GEN
T1 - Evaluating parameterization methods for convolutional neural network (CNN)-based image operators
AU - Kim, Seung Wook
AU - Cho, Sung Jin
AU - Uhm, Kwang Hyun
AU - Ji, Seo Won
AU - Lee, Sang Won
AU - Ko, Sung Jea
N1 - Funding Information:
This work was supported by Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No.2014-3-00077, Development of global multi-target tracking and event prediction techniques based on real-time large-scale analysis)
Publisher Copyright:
© 2019 IEEE.
PY - 2019/6
Y1 - 2019/6
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85083342351&partnerID=8YFLogxK
U2 - 10.1109/CVPRW.2019.00237
DO - 10.1109/CVPRW.2019.00237
M3 - Conference contribution
AN - SCOPUS:85083342351
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 1862
EP - 1870
BT - Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019
PB - IEEE Computer Society
T2 - 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019
Y2 - 16 June 2019 through 20 June 2019
ER -