Low-light images often suffer from severe noise, low brightness, low contrast, and color deviation. While several low-light image enhancement methods have been proposed, there remains a lack of efficient methods that can simultaneously solve all of these problems. In this paper, we introduce FLW-Net, a Fast and LightWeight Network for low-light image enhancement that significantly improves processing speed and overall effect. To achieve efficient low-light image enhancement, we recognize the challenges of the lack of an absolute reference and the need for a large receptive field to obtain global contrast. Therefore, we propose an efficient global feature information extraction component and design loss functions based on relative information to overcome these challenges. Finally, we conduct comparative experiments to demonstrate the effectiveness of the proposed method, and the results confirm that FLW-Net can significantly reduce the complexity of supervised low-light image enhancement networks while improving processing effect. Code is available at https://github.com/hitzhangyu/FLW-Net
翻译：低光图像通常存在严重的噪声、低亮度、低对比度和色偏问题。虽然已提出多种低光图像增强方法，但仍缺乏能同时解决所有这些问题的高效方法。在本文中，我们介绍FLW-Net，它是一种快速轻量级低光图像增强网络，可显着提高处理速度和整体效果。为了实现高效的低光图像增强，我们认识到绝对参考的缺乏和需要获得全局对比度的大感受野是面临的挑战。因此，我们提出了一种高效的全局特征信息提取部分，并设计了基于相对信息的损失函数来克服这些挑战。最后，我们进行了比较实验，证实了所提出方法的有效性，结果表明FLW-Net能够显著降低有监督低光图像增强网络的复杂性，同时提高处理效果。代码可在https://github.com/hitzhangyu/FLW-Net中获得。
相关内容
微信扫码咨询专知VIP会员