Department of Basic Sciences, Shanxi Agricultural University, Taigu 030801, China.
School of Mathematics and Statistics, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, China.
Sensors (Basel). 2022 Jul 26;22(15):5593. doi: 10.3390/s22155593.
Low-light images are a common phenomenon when taking photos in low-light environments with inappropriate camera equipment, leading to shortcomings such as low contrast, color distortion, uneven brightness, and high loss of detail. These shortcomings are not only subjectively annoying but also affect the performance of many computer vision systems. Enhanced low-light images can be better applied to image recognition, object detection and image segmentation. This paper proposes a novel RetinexDIP method to enhance images. Noise is considered as a factor in image decomposition using deep learning generative strategies. The involvement of noise makes the image more real, weakens the coupling relationship between the three components, avoids overfitting, and improves generalization. Extensive experiments demonstrate that our method outperforms existing methods qualitatively and quantitatively.
低光照图像是在使用不合适的相机设备拍摄低光照环境下的照片时常见的现象，导致对比度低、颜色失真、亮度不均匀和细节丢失等缺点。这些缺点不仅主观上令人讨厌，还会影响许多计算机视觉系统的性能。增强低光照图像可以更好地应用于图像识别、目标检测和图像分割。本文提出了一种新的 RetinexDIP 方法来增强图像。噪声被认为是使用深度学习生成策略进行图像分解的一个因素。噪声的参与使图像更真实，削弱了三个分量之间的耦合关系，避免了过拟合，提高了泛化能力。大量实验表明，我们的方法在质量和数量上都优于现有方法。
