Learning Gated Non-Local Residual for Single-Image Rain Streak Removal

IEEE Transactions on Circuits and Systems for Video Technology - Tập 31 Số 6 - Trang 2147-2159 - 2021
Lei Zhu1, Zijun Deng2, Xiaowei Hu1, Haoran Xie3, Xuemiao Xu4,2,5, Jing Qin6, Pheng‐Ann Heng7,8
1Department of Computer Science and Engineering, The Chinese University of Hong Kong, HONG KONG
2School of Computer Science and Engineering, South China University of Technology, Guangzhou, China
3Department of Computing and Decision Sciences, Lingnan University, Hong Kong
4Guangdong Provincial Key Laboratory of Computational Intelligence and Cyberspace Information, Guangzhou, China
5State Key Laboratory of Subtropical Building Science, Ministry of Education Key Laboratory of Big Data and Intelligent Robot, Guangzhou, China
6Centre for Smart Health, School of Nursing, The Hong Kong Polytechnic University, Hong Kong
7Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
8The Chinese University of Hong Kong, Hong Kong

Tóm tắt

Từ khóa


Tài liệu tham khảo

10.1109/CVPR.2005.38

10.1109/CVPR.2018.00813

10.1007/s11760-012-0373-6

10.1007/s11263-006-0028-6

10.1109/CVPR.2004.1315077

10.1109/CVPR.2018.00263

wang, 2017, Understanding convolution for semantic segmentation, arXiv 1702 08502

krizhevsky, 2012, ImageNet classification with deep convolutional neural networks, Proc Adv Neural Inf Process Syst (NIPS), 1097

yu, 2016, Multi-scale context aggregation by dilated convolutions, Proc ICLR, 1

10.1109/CVPRW.2017.151

10.1109/CVPR.2019.00400

10.1109/CVPR.2018.00745

10.1109/CVPR.2019.00396

10.1109/TIP.2011.2179057

10.1109/ICIP.2014.7025909

10.1109/TMM.2013.2284759

10.1109/ICCV.2013.247

10.1109/TIP.2017.2691802

10.1109/CVPR.2017.186

10.1109/CVPR.2017.183

li, 2018, Recurrent squeeze-and-excitation context aggregation net for single image deraining, Proc ECCV, 254

10.1109/ICCV.2013.84

10.1145/3240508.3240694

10.1109/IVS.2005.1505103

10.1145/3240508.3240636

10.1109/CVPR.2019.00821

10.1109/TPAMI.2015.2491937

10.1109/CVPR.2019.01255

10.1109/ICCV.2015.388

10.1109/CVPR.2019.00173

10.1109/ICCV.2017.276

10.1109/CVPR.2018.00079

10.1109/CVPR.2016.299

10.1109/TIP.2020.2994443

10.1109/CVPR.2016.90

10.1109/TPAMI.2019.2895793

redmon, 2018, YOLOv3: An incremental improvement, arXiv 1804 02767

10.1109/CVPR.2017.75

wang, 2019, A survey on rain removal from video and single image, arXiv 1909 08326

10.1109/CVPR.2019.00406

nair, 2010, Rectified linear units improve restricted Boltzmann machines, Proc ICML, 807

10.1109/JPROC.2010.2040551

10.1109/CVPR.2018.00544

10.1109/CVPR.2018.00012

10.1109/TIP.2003.819861

10.1109/TPAMI.2017.2699184

10.1109/TCSVT.2019.2920407

ren, 2015, Faster R-CNN: Towards real-time object detection with region proposal networks, Proc Adv Neural Inf Process Syst, 91

Thông tin
Thông tin xuất bản

IEEE Transactions on Circuits and Systems for Video Technology

Tập 31 Số 6

2147-2159

Thông tin tác giả