Photo-realistic image dehazing and verifying networks via complementary adversarial learningopen access
- Authors
- Shin, J.; Paik, Joonki
- Issue Date
- Sep-2021
- Publisher
- MDPI
- Keywords
- CNN; Dehazing; GAN
- Citation
- Sensors, v.21, no.18
- Journal Title
- Sensors
- Volume
- 21
- Number
- 18
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/49912
- DOI
- 10.3390/s21186182
- ISSN
- 1424-8220
1424-3210
- Abstract
- Physical model-based dehazing methods cannot, in general, avoid environmental variables and undesired artifacts such as non-collected illuminance, halo and saturation since it is difficult to accurately estimate the amount of the illuminance, light transmission and airlight. Furthermore, the haze model estimation process requires very high computational complexity. To solve this problem by directly estimating the radiance of the haze images, we present a novel dehazing and verifying network (DVNet). In the dehazing procedure, we enhanced the clean images by using a correction network (CNet), which uses the ground truth to learn the haze network. Haze images are then restored through a haze network (HNet). Furthermore, a verifying method verifies the error of both CNet and HNet using a self-supervised learning method. Finally, the proposed complementary adversarial learning method can produce results more naturally. Note that the proposed discriminator and generators (HNet & CNet) can be learned via an unpaired dataset. Overall, the proposed DVNet can generate a better dehazed result than state-of-the-art approaches under various hazy conditions. Experimental results show that the DVNet outperforms state-of-the-art dehazing methods in most cases. © 2021 by the authors. Licensee MDPI, Basel, Switzerland.
- Files in This Item
-
- Appears in
Collections - Graduate School of Advanced Imaging Sciences, Multimedia and Film > Department of Imaging Science and Arts > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/49912)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.