论文标题
增强水下图像增强的SWIN-CONVS变压器
Reinforced Swin-Convs Transformer for Underwater Image Enhancement
论文作者
论文摘要
水下图像增强（UIE）技术旨在应对由于吸收光和散射而导致的降解水下图像的挑战。为了解决问题，提出了一种新型的基于U-NET的增强SWIN-CONVS变压器，用于水下图像增强方法（URSCT-UIE）。具体而言，由于基于纯卷积的U-NET的不足，我们将Swin Transformer嵌入了U-NET中，以提高捕获全局依赖性的能力。然后，鉴于Swin Transformer吸引了当地注意力的不足，重新引入卷积可能会引起更多的当地关注。因此，我们为融合融合和核心注意机制提供了一种巧妙的方式，以建立增强的SWIN-CONVS变压器块（RSCTB），以吸引更多的局部注意力，这在通道中得到了加强和Swin Transformer的空间注意力。最后，可用数据集的实验结果表明，与主观和客观评估相比，所提出的URSCT-UIE与其他方法相比，实现了最先进的性能。该代码接受后将在GitHub上发布。
Underwater Image Enhancement (UIE) technology aims to tackle the challenge of restoring the degraded underwater images due to light absorption and scattering. To address problems, a novel U-Net based Reinforced Swin-Convs Transformer for the Underwater Image Enhancement method (URSCT-UIE) is proposed. Specifically, with the deficiency of U-Net based on pure convolutions, we embedded the Swin Transformer into U-Net for improving the ability to capture the global dependency. Then, given the inadequacy of the Swin Transformer capturing the local attention, the reintroduction of convolutions may capture more local attention. Thus, we provide an ingenious manner for the fusion of convolutions and the core attention mechanism to build a Reinforced Swin-Convs Transformer Block (RSCTB) for capturing more local attention, which is reinforced in the channel and the spatial attention of the Swin Transformer. Finally, the experimental results on available datasets demonstrate that the proposed URSCT-UIE achieves state-of-the-art performance compared with other methods in terms of both subjective and objective evaluations. The code will be released on GitHub after acceptance.
