TY - GEN
T1 - Lightweight Deep Extraction Networks for Single Image De-raining
AU - Jang, Yunseon
AU - Son, Chang Hwan
AU - Choo, Hyunseung
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/1/4
Y1 - 2021/1/4
N2 - In bad weather, artifacts such as rain streaks degrade the image quality. In addition, artifacts in the damaged image obstruct human vision and adversely affect the accuracy of object detection. Hence, single image rain removal is an important issue to improve image quality. However, state-of-the-art methods have limitation that require a lot of training data. This paper proposes a lightweight Deep Extraction Network (DEN), which performs well on image de-raining even with a small training dataset. Particularly, we design a novel Light Residual Block (LRB), which is connected in five cascading layers for extracting a deep local feature. Furthermore, DEN deploys a residual learning for training only artifacts. The experimental results on synthetic and real-world rainy image demonstrate the effectiveness in terms of visual and quantitative performance.
AB - In bad weather, artifacts such as rain streaks degrade the image quality. In addition, artifacts in the damaged image obstruct human vision and adversely affect the accuracy of object detection. Hence, single image rain removal is an important issue to improve image quality. However, state-of-the-art methods have limitation that require a lot of training data. This paper proposes a lightweight Deep Extraction Network (DEN), which performs well on image de-raining even with a small training dataset. Particularly, we design a novel Light Residual Block (LRB), which is connected in five cascading layers for extracting a deep local feature. Furthermore, DEN deploys a residual learning for training only artifacts. The experimental results on synthetic and real-world rainy image demonstrate the effectiveness in terms of visual and quantitative performance.
KW - Computer Vision
KW - Deep learning
KW - Single image rain removal
UR - https://www.scopus.com/pages/publications/85103739078
U2 - 10.1109/IMCOM51814.2021.9377428
DO - 10.1109/IMCOM51814.2021.9377428
M3 - Conference contribution
AN - SCOPUS:85103739078
T3 - Proceedings of the 2021 15th International Conference on Ubiquitous Information Management and Communication, IMCOM 2021
BT - Proceedings of the 2021 15th International Conference on Ubiquitous Information Management and Communication, IMCOM 2021
A2 - Lee, Sukhan
A2 - Choo, Hyunseung
A2 - Ismail, Roslan
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 15th International Conference on Ubiquitous Information Management and Communication, IMCOM 2021
Y2 - 4 January 2021 through 6 January 2021
ER -