A neural network approach to remove rain using reconstruction and feature losses
- Authors
- Javed, Kamran; Hussain, Ghulam; Shaukat, Furqan; Hwang, Seong Oun
- Issue Date
- Sep-2020
- Publisher
- SPRINGER LONDON LTD
- Keywords
- Rain removal; Generative adversarial network; Structural similarity loss; UNET; Pix2Pix
- Citation
- NEURAL COMPUTING & APPLICATIONS, v.32, no.17, pp.13129 - 13138
- Journal Title
- NEURAL COMPUTING & APPLICATIONS
- Volume
- 32
- Number
- 17
- Start Page
- 13129
- End Page
- 13138
- URI
- https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/78459
- DOI
- 10.1007/s00521-019-04558-2
- ISSN
- 0941-0643
- Abstract
- Rain streaks can eclipse some information of an image taken during rainfall which can degrade the performance of a vision system. While existing rain removing methods can recover the semantic structure, they lack natural texture recovery. The aim of this work is to recover the hidden structure and texture under the rain streaks with fine details. We propose a novel generative adversarial network with two discriminators to remove rain called rain removal generative adversarial network, where a combination of reconstruction, feature and adversarial losses is used for low level, structural and natural recovery, respectively. We have found that exploiting low-level loss with high-level structural similarity loss as a reconstruction loss is quite effective in attaining visually plausible and consistent texture. Qualitative and quantitative evaluations on our synthetically created dataset and a benchmark dataset show substantial performance gain than state-of-the-art rain removing methods.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - IT융합대학 > 컴퓨터공학과 > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.