TY - GEN
T1 - CSANet
T2 - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021
AU - Hsyu, Ming Chun
AU - Liu, Chih-Wei
AU - Chen, Chao Hung
AU - Chen, Chao Wei
AU - Tsai, Wen Chia
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/6
Y1 - 2021/6
N2 - The Image Signal Processor (ISP) is a customized device to restore RGB images from the pixel signals of CMOS image sensor. In order to realize this function, a series of processing units are leveraged to tackle different artifacts, such as color shifts, signal noise, moire effects, and so on, that are introduced from the photo-capturing devices. However, tuning each processing unit is highly complicated and requires a lot of experience and effort from image experts. In this paper, a novel network architecture, CSANet, with emphases on inference speed and high PSNR is proposed for end-to-end learned ISP task. The proposed CSANet applies a double attention module employing both channel and spatial attentions. Particularly, its spatial attention is simplified to a light-weighted dilated depth-wise convolution and still performs as well as others. As proof of performance, CSANet won 2nd place in the Mobile AI 2021 Learned Smartphone ISP Challenge with 1st place PSNR score.
AB - The Image Signal Processor (ISP) is a customized device to restore RGB images from the pixel signals of CMOS image sensor. In order to realize this function, a series of processing units are leveraged to tackle different artifacts, such as color shifts, signal noise, moire effects, and so on, that are introduced from the photo-capturing devices. However, tuning each processing unit is highly complicated and requires a lot of experience and effort from image experts. In this paper, a novel network architecture, CSANet, with emphases on inference speed and high PSNR is proposed for end-to-end learned ISP task. The proposed CSANet applies a double attention module employing both channel and spatial attentions. Particularly, its spatial attention is simplified to a light-weighted dilated depth-wise convolution and still performs as well as others. As proof of performance, CSANet won 2nd place in the Mobile AI 2021 Learned Smartphone ISP Challenge with 1st place PSNR score.
UR - http://www.scopus.com/inward/record.url?scp=85108807683&partnerID=8YFLogxK
U2 - 10.1109/CVPRW53098.2021.00282
DO - 10.1109/CVPRW53098.2021.00282
M3 - Conference contribution
AN - SCOPUS:85108807683
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 2486
EP - 2493
BT - Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021
PB - IEEE Computer Society
Y2 - 19 June 2021 through 25 June 2021
ER -