Self-supervised zero-shot dehazing network based on dark channel prior
Open Access
- 14 April 2023
- journal article
- research article
- Published by Higher Education Press in Frontiers of Optoelectronics
- Vol. 16 (1) , 1-14
Abstract
Most learning-based methods previously used in image dehazing employ a supervised learning strategy, which is time-consuming and requires a large-scale dataset. However, large-scale datasets are difficult to obtain. Here, we propose a self-supervised zero-shot dehazing network (SZDNet) based on dark channel prior, which uses a hazy image generated from the output dehazed image as a pseudo-label to supervise the optimization process of the network. Additionally, we use a novel multichannel quad-tree algorithm to estimate atmospheric light values, which is more accurate than previous methods. Furthermore, the sum of the cosine distance and the mean squared error between the pseudo-label and the input image is applied as a loss function to enhance the quality of the dehazed image. The most significant advantage of the SZDNet is that it does not require a large dataset for training before performing the dehazing task. Extensive testing shows promising performances of the proposed method in both qualitative and quantitative evaluations when compared with state-of-the-art methods. Graphical AbstractKeywords
This publication has 37 references indexed in Scilit:
- AOD-Net: All-in-One Dehazing Network2017
- Fast Image Dehazing Method Based on Linear TransformationIEEE Transactions on Multimedia, 2017
- DehazeNet: An End-to-End System for Single Image Haze RemovalIEEE Transactions on Image Processing, 2016
- Non-local Image Dehazing2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Edge-Preserving Decomposition-Based Single Image Haze RemovalIEEE Transactions on Image Processing, 2015
- Making a “Completely Blind” Image Quality AnalyzerIEEE Signal Processing Letters, 2012
- Guided Image FilteringIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Single Image Haze Removal Using Dark Channel PriorIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Contrast restoration of weather degraded imagesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003