CSANet: High Speed Channel Spatial Attention Network for Mobile ISP

被引：17

作者：

Hsyu, Ming-Chun ^{[1
]}

Liu, Chih-Wei ^{[1
,2
]}

Chen, Chao-Hung ^{[1
]}

Chen, Chao-Wei ^{[1
]}

Tsai, Wen-Chia ^{[1
]}

机构：

[1] Ind Technol Res Inst, Hsinchu, Taiwan

[2] Natl Yang Ming Chiao Tung Univ, Hsinchu, Taiwan

来源：

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021 | 2021年

关键词：

D O I：

10.1109/CVPRW53098.2021.00282

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：2486 / 2493

页数：8

共 30 条

[1]

[Anonymous], 2018, PROC CVPR IEEE, DOI DOI 10.1109/CVPR.2018.00262

[2] Lucas/Kanade meets Horn/Schunck: Combining local and global optic flow methods [J].

Bruhn A. ;

Weickert J. ;

Schnörr C. .

International Journal of Computer Vision, 2005, 61 (3) :1-21

[3]

Dai Linhui, 2020, ARXIV200809228

[4]

Fisher Y, 2015, ARXIV151107122

[5] Dual Attention Network for Scene Segmentation [J].

Fu, Jun ;

Liu, Jing ;

Tian, Haijie ;

Li, Yong ;

Bao, Yongjun ;

Fang, Zhiwei ;

Lu, Hanqing .

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :3141-3149

[6] Deep Joint Demosaicking and Denoising [J].

Gharbi, Michael ;

Chaurasia, Gaurav ;

Paris, Sylvain ;

Durand, Fredo .

ACM TRANSACTIONS ON GRAPHICS, 2016, 35 (06)

[7] Deep Residual Learning for Image Recognition [J].

He, Kaiming ;

Zhang, Xiangyu ;

Ren, Shaoqing ;

Sun, Jian .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778

[8]

Howard A. G., MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications, DOI DOI 10.48550/ARXIV.1704.04861

[9]

Hu J, 2018, PROC CVPR IEEE, P7132, DOI [10.1109/TPAMI.2019.2913372, 10.1109/CVPR.2018.00745]

[10] AIM 2020 Challenge on Learned Image Signal Processing Pipeline [J].

Ignatov, Andrey ;

Timofte, Radu ;

Zhang, Zhilu ;

Liu, Ming ;

Wang, Haolin ;

Zuo, Wangmeng ;

Zhang, Jiawei ;

Zhang, Ruimao ;

Peng, Zhanglin ;

Ren, Sijie ;

Dai, Linhui ;

Liu, Xiaohong ;

Li, Chengqi ;

Chen, Jun ;

Ito, Yuichi ;

Vasudeva, Bhavya ;

Deora, Puneesh ;

Pal, Umapada ;

Guo, Zhenyu ;

Zhu, Yu ;

Liang, Tian ;

Li, Chenghua ;

Leng, Cong ;

Pan, Zhihong ;

Li, Baopu ;

Kim, Byung-Hoon ;

Song, Joonyoung ;

Ye, Jong Chul ;

Baek, JaeHyun ;

Zhussip, Magauiya ;

Koishekenov, Yeskendir ;

Ye, Hwechul Cho ;

Liu, Xin ;

Hu, Xueying ;

Jiang, Jun ;

Gu, Jinwei ;

Li, Kai ;

Tan, Pengliang ;

Hou, Bingxin .

COMPUTER VISION - ECCV 2020 WORKSHOPS, PT III, 2020, 12537 :152-170

← 1 2 3 →