Wenzhou Mass Transit Railway Investment Group Co., Ltd., Wenzhou 325000, China.
School of Aeronautics and Astronautics, Zhejiang University, Hangzhou 310027, China.
Sensors (Basel). 2022 Dec 21;23(1):43. doi: 10.3390/s23010043.
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.
图像去雾的目的是去除退化图像中天气因素的干扰，提高图像的清晰度和色彩饱和度，最大限度地恢复有用特征。单幅图像去雾是图像恢复领域中最重要的任务之一。近年来，由于深度学习的进步，单幅图像去雾取得了很大的进展。随着 Transformer 在高级计算机视觉任务中的成功，一些研究也开始将 Transformer 应用于图像去雾任务，并取得了令人惊讶的结果。然而，基于去卷积神经网络的去雾算法和基于 Transformer 的去雾算法都分别放大了它们的优缺点。因此，本文提出了一种新颖的 Transformer-Convolution 融合去雾网络（TCFDN），它利用 Transformer 的全局建模能力和卷积神经网络的局部建模能力来提高去雾能力。在 Transformer-Convolution 融合去雾网络中，使用了经典的自编码器结构。本文提出了一种 Transformer-Convolution 混合层，它使用自适应融合策略，充分利用 Swin-Transformer 和卷积神经网络来提取和重建图像特征。在之前研究的基础上，该层进一步提高了网络去除雾的能力。一系列对比实验和消融实验不仅证明了本文提出的 Transformer-Convolution 融合去雾网络优于更先进的去雾算法，而且为其依赖的基础理论提供了坚实而有力的证据。
