Abstract
Low-light image enhancement (LLE) aims to improve the visual quality of images captured in poorly lit conditions, which often suffer from low brightness, low contrast, noise, and color distortions. These issues hinder the performance of computer vision tasks such as object detection, facial recognition, and autonomous this http URL enhancement techniques, such as multi-scale fusion and histogram equalization, fail to preserve fine details and often struggle with maintaining the natural appearance of enhanced images under complex lighting conditions. Although the Retinex theory provides a foundation for image decomposition, it often amplifies noise, leading to suboptimal image quality. In this paper, we propose the Dual Light Enhance Network (DLEN), a novel architecture that incorporates two distinct attention mechanisms, considering both spatial and frequency domains. Our model introduces a learnable wavelet transform module in the illumination estimation phase, preserving high- and low-frequency components to enhance edge and texture details. Additionally, we design a dual-branch structure that leverages the power of the Transformer architecture to enhance both the illumination and structural components of the this http URL extensive experiments, our model outperforms state-of-the-art methods on standard this http URL is available here: this https URL
Abstract (translated)
低光图像增强（LLE）旨在改善在光线不足条件下拍摄的图像的视觉质量，这些条件下的图片通常会遇到亮度低、对比度差、噪声和颜色失真等问题。这些问题会对计算机视觉任务（如物体检测、面部识别和自动驾驶等）的表现产生不利影响。现有的多尺度融合和直方图均衡化等增强技术往往难以保留细节，并且在复杂的照明条件下很难保持图像自然的外观。虽然Retinex理论为图像分解提供了基础，但它常常会放大噪声，导致图像质量不理想。 在本文中，我们提出了一种新颖的架构——双光增强网络（DLEN），该架构结合了两种不同的注意力机制，在空间和频率领域考虑问题。我们的模型引入了一个可学习的小波变换模块，在光照估计阶段保留高、低频成分以强化边缘和纹理细节。此外，我们设计了一个双分支结构，利用Transformer架构来增强图像的光照和结构组成部分。 通过广泛的实验测试，我们的模型在标准数据集上的表现优于当前最先进的方法。论文全文可在以下链接获取：[此处应为链接，请访问原文获取具体链接]
URL
https://arxiv.org/abs/2501.12235
