Task-Oriented Network for Image Dehazing
| Autor: | Zechao Li, Min He, Runde Li, Jinhui Tang, Jinshan Pan |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Image formation
Haze Computer science business.industry Distortion (optics) ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 02 engineering and technology Radiation Computer Graphics and Computer-Aided Design Convolutional neural network Network planning and design Recurrent neural network Distortion 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Artificial intelligence business Encoder Software Image restoration |
| Zdroj: | IEEE Transactions on Image Processing. 29:6523-6534 |
| ISSN: | 1941-0042 1057-7149 |
| DOI: | 10.1109/tip.2020.2991509 |
| Popis: | Haze interferes the transmission of scene radiation and significantly degrades color and details of outdoor images. Existing deep neural networks-based image dehazing algorithms usually use some common networks. The network design does not model the image formation of haze process well, which accordingly leads to dehazed images containing artifacts and haze residuals in some special scenes. In this paper, we propose a task-oriented network for image dehazing, where the network design is motivated by the image formation of haze process. The task-oriented network involves a hybrid network containing an encoder and decoder network and a spatially variant recurrent neural network which is derived from the hazy process. In addition, we develop a multi-stage dehazing algorithm to further improve the accuracy by filtering haze residuals in a step-by-step fashion. To constrain the proposed network, we develop a dual composition loss, content-based pixel-wise loss and total variation constraint. We train the proposed network in an end-to-end manner and analyze its effect on image dehazing. Experimental results demonstrate that the proposed algorithm achieves favorable performance against state-of-the-art dehazing methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|