An Efficient Dehazing Algorithm Based on the Fusion of Transformer and Convolutional Neural Network
The purpose of image dehazing is to remove the interference from weather factors in degraded images and enhance the clarity and color saturation of images to maximize the restoration of useful features. Single image dehazing is one of the most important tasks in the field of image restoration. In re...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/1/43 |
| _version_ | 1797431205497405440 |
|---|---|
| author | Jun Xu Zi-Xuan Chen Hao Luo Zhe-Ming Lu |
| author_facet | Jun Xu Zi-Xuan Chen Hao Luo Zhe-Ming Lu |
| author_sort | Jun Xu |
| collection | DOAJ |
| description | The purpose of image dehazing is to remove the interference from weather factors in degraded images and enhance the clarity and color saturation of images to maximize the restoration of useful features. Single image dehazing is one of the most important tasks in the field of image restoration. In recent years, due to the progress of deep learning, single image dehazing has made great progress. With the success of Transformer in advanced computer vision tasks, some research studies also began to apply Transformer to image dehazing tasks and obtained surprising results. However, both the deconvolution-neural-network-based dehazing algorithm and Transformer based dehazing algorithm magnify their advantages and disadvantages separately. Therefore, this paper proposes a novel Transformer–Convolution fusion dehazing network (TCFDN), which uses Transformer’s global modeling ability and convolutional neural network’s local modeling ability to improve the dehazing ability. In the Transformer–Convolution fusion dehazing network, the classic self-encoder structure is used. This paper proposes a Transformer–Convolution hybrid layer, which uses an adaptive fusion strategy to make full use of the Swin-Transformer and convolutional neural network to extract and reconstruct image features. On the basis of previous research, this layer further improves the ability of the network to remove haze. A series of contrast experiments and ablation experiments not only proved that the Transformer–Convolution fusion dehazing network proposed in this paper exceeded the more advanced dehazing algorithm, but also provided solid and powerful evidence for the basic theory on which it depends. |
| first_indexed | 2024-03-09T09:41:32Z |
| format | Article |
| id | doaj.art-3e722f89027d45909ac73cb1c128e363 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T09:41:32Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-3e722f89027d45909ac73cb1c128e3632023-12-02T00:52:50ZengMDPI AGSensors1424-82202022-12-012314310.3390/s23010043An Efficient Dehazing Algorithm Based on the Fusion of Transformer and Convolutional Neural NetworkJun Xu0Zi-Xuan Chen1Hao Luo2Zhe-Ming Lu3Wenzhou Mass Transit Railway Investment Group Co., Ltd., Wenzhou 325000, ChinaSchool of Aeronautics and Astronautics, Zhejiang University, Hangzhou 310027, ChinaSchool of Aeronautics and Astronautics, Zhejiang University, Hangzhou 310027, ChinaSchool of Aeronautics and Astronautics, Zhejiang University, Hangzhou 310027, ChinaThe purpose of image dehazing is to remove the interference from weather factors in degraded images and enhance the clarity and color saturation of images to maximize the restoration of useful features. Single image dehazing is one of the most important tasks in the field of image restoration. In recent years, due to the progress of deep learning, single image dehazing has made great progress. With the success of Transformer in advanced computer vision tasks, some research studies also began to apply Transformer to image dehazing tasks and obtained surprising results. However, both the deconvolution-neural-network-based dehazing algorithm and Transformer based dehazing algorithm magnify their advantages and disadvantages separately. Therefore, this paper proposes a novel Transformer–Convolution fusion dehazing network (TCFDN), which uses Transformer’s global modeling ability and convolutional neural network’s local modeling ability to improve the dehazing ability. In the Transformer–Convolution fusion dehazing network, the classic self-encoder structure is used. This paper proposes a Transformer–Convolution hybrid layer, which uses an adaptive fusion strategy to make full use of the Swin-Transformer and convolutional neural network to extract and reconstruct image features. On the basis of previous research, this layer further improves the ability of the network to remove haze. A series of contrast experiments and ablation experiments not only proved that the Transformer–Convolution fusion dehazing network proposed in this paper exceeded the more advanced dehazing algorithm, but also provided solid and powerful evidence for the basic theory on which it depends.https://www.mdpi.com/1424-8220/23/1/43image dehazingdeep learningconvolutional neural networkTransformerTransformer–Convolution fusion dehazing network (TCFDN) |
| spellingShingle | Jun Xu Zi-Xuan Chen Hao Luo Zhe-Ming Lu An Efficient Dehazing Algorithm Based on the Fusion of Transformer and Convolutional Neural Network Sensors image dehazing deep learning convolutional neural network Transformer Transformer–Convolution fusion dehazing network (TCFDN) |
| title | An Efficient Dehazing Algorithm Based on the Fusion of Transformer and Convolutional Neural Network |
| title_full | An Efficient Dehazing Algorithm Based on the Fusion of Transformer and Convolutional Neural Network |
| title_fullStr | An Efficient Dehazing Algorithm Based on the Fusion of Transformer and Convolutional Neural Network |
| title_full_unstemmed | An Efficient Dehazing Algorithm Based on the Fusion of Transformer and Convolutional Neural Network |
| title_short | An Efficient Dehazing Algorithm Based on the Fusion of Transformer and Convolutional Neural Network |
| title_sort | efficient dehazing algorithm based on the fusion of transformer and convolutional neural network |
| topic | image dehazing deep learning convolutional neural network Transformer Transformer–Convolution fusion dehazing network (TCFDN) |
| url | https://www.mdpi.com/1424-8220/23/1/43 |
| work_keys_str_mv | AT junxu anefficientdehazingalgorithmbasedonthefusionoftransformerandconvolutionalneuralnetwork AT zixuanchen anefficientdehazingalgorithmbasedonthefusionoftransformerandconvolutionalneuralnetwork AT haoluo anefficientdehazingalgorithmbasedonthefusionoftransformerandconvolutionalneuralnetwork AT zheminglu anefficientdehazingalgorithmbasedonthefusionoftransformerandconvolutionalneuralnetwork AT junxu efficientdehazingalgorithmbasedonthefusionoftransformerandconvolutionalneuralnetwork AT zixuanchen efficientdehazingalgorithmbasedonthefusionoftransformerandconvolutionalneuralnetwork AT haoluo efficientdehazingalgorithmbasedonthefusionoftransformerandconvolutionalneuralnetwork AT zheminglu efficientdehazingalgorithmbasedonthefusionoftransformerandconvolutionalneuralnetwork |