Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/82318
Title: Coupled rain streak and background estimation via separable element-wise attention
Authors: Tan, YJ
Wen, Q
Qin, J 
Jiao, JB
Han, GQ
He, SF
Issue Date: 2020
Source: IEEE access, 20 Jan. 2020, v. 8, p. 16627-16636
Abstract: Single image de-raining is challenging especially in the scenarios with dense rain streaks. Existing methods resolve this problem by predicting the rain streaks of the image, which constrains the network to focus on local rain streaks features. However, dense rain streaks are visually similar to mist or fog (with large intensities), in this case, the training objective should be shifted to image recovery instead of extracting rain streaks. In this paper, we propose a coupled rain streak and background estimation network that explores the intrinsic relations between two tasks. In particular, our network produces task-dependent feature maps, each part of the features correspond to the estimation of rain streak and background. Furthermore, to inject element-wise attention to all the convolutional blocks for better understanding the rain streaks distribution, we propose a Separable Element-wise Attention mechanism. In this way, dense element-wise attention can be obtained by a sequence of channel and spatial attention modules, with negligible computation. Extensive experiments demonstrate that the proposed method outperforms state-of-the-arts on 5 existing synthesized rain datasets and the real-world scenarios, without extra multi-scale or recurrent structure.
Keywords: Background estimation
De-raining
Element-wise attention
Publisher: Institute of Electrical and Electronics Engineers
Journal: IEEE access 
EISSN: 2169-3536
DOI: 10.1109/ACCESS.2020.2967891
Rights: This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see http://creativecommons.org/licenses/by/4.0/
The following publication Y. Tan, Q. Wen, J. Qin, J. Jiao, G. Han and S. He, "Coupled Rain Streak and Background Estimation via Separable Element-Wise Attention," in IEEE Access, vol. 8, pp. 16627-16636, 2020 is available at https://dx.doi.org/10.1109/ACCESS.2020.2967891
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

Page view(s)

40
Citations as of Jul 14, 2020

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.