DRLIE: Flexible Low-Light Image Enhancement via Disentangled Representations

SwinLightGAN a study of low-light image enhancement algorithms using depth residuals and transformer techniques

Contemporary algorithms for enhancing images in low-light conditions prioritize improving brightness and contrast but often neglect improving image details. This study introduces the Swin Transformer-based Light-enhancing Generative Adversarial Network (SwinLightGAN), a novel generative adversarial network (GAN) that effectively enhances image details under low-light conditions. The network integrates a generator model based on a Residual Jumping U-shaped Network (U-Net) architecture for precise local detail extraction with an illumination network enhanced by Shifted Window Transformer (Swin Transformer) technology that captures multi-scale spatial features and global contexts. This combination produces high-quality images that resemble those taken in normal lighting conditions, retaining intricate details. Through adversarial training that employs discriminators operating at multiple scales and a blend of loss functions, SwinLightGAN ensures a seamless distinction between generated and authentic images, ensuring superior enhancement quality. Extensive experimental analysis on multiple unpaired datasets demonstrates SwinLightGAN's outstanding performance. The system achieves Naturalness Image Quality Evaluator (NIQE) scores ranging from 5.193 to 5.397, Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) scores from 28.879 to 32.040, and Patch-based Image Quality Evaluator (PIQE) scores from 38.280 to 44.479, highlighting its efficacy in delivering high-quality enhancements across diverse metrics.

Mutually Reinforcing Learning of Decoupled Degradation and Diffusion Enhancement for Unpaired Low-Light Image Lightening

Denoising Diffusion Probabilistic Model (DDPM) has demonstrated exceptional performance in low-light enhancement task. However, the dependency on paired training datas has left the generality of DDPM in low-light enhancement largely untapped. Therefore, this paper proposes a mutually reinforcing learning framework of decoupled degradation and diffusion enhancement, named MRLIE, which leverages style guidance from unpaired low-light images to generate pseudo-image pairs that are consistent with the target domain, thereby optimizing the latter diffusion enhancement network in a supervised manner. During the degradation process, the diffusion loss of fixed enhancement network serves as a evaluation metric for structure consistency and is combined with adversarial style loss to form the optimization objective for degradation network. Such loss design ensures that scene structure information is retained during the degradation process. During the enhancement process, the degradation network with frozen parameters continuously generates pseudo-paired low-/normal-light image pairs as training datas, thus the diffusion enhancement network could be progressively optimized. On the whole, the two processes are interdependent and could achieve cooperative improvement in terms of degradation realism and enhancement quality through iterative optimization. Additionally, we propose the Retinex-based decoupled degradation strategy for simulating the complex degradation in real low-light imaging, which ensures the color correction and noise suppression capabilities of latter diffusion enhancement network. Extensive experiments show that MRLIE can achieve promising results and better generality across various datasets.

DCENet-based low-light image enhancement improved by spiking encoding and convLSTM

The direct utilization of low-light images hinders downstream visual tasks. Traditional low-light image enhancement (LLIE) methods, such as Retinex-based networks, require image pairs. A spiking-coding methodology called intensity-to-latency has been used to gradually acquire the structural characteristics of an image. convLSTM has been used to connect the features. This study introduces a simplified DCENet to achieve unsupervised LLIE as well as the spiking coding mode of a spiking neural network. It also applies the comprehensive coding features of convLSTM to improve the subjective and objective effects of LLIE. In the ablation experiment for the proposed structure, the convLSTM structure was replaced by a convolutional neural network, and the classical CBAM attention was introduced for comparison. Five objective evaluation metrics were compared with nine LLIE methods that currently exhibit strong comprehensive performance, with PSNR, SSIM, MSE, UQI, and VIFP exceeding the second place at 4.4% (0.8%), 3.9% (17.2%), 0% (15%), 0.1% (0.2%), and 4.3% (0.9%) on the LOL and SCIE datasets. Further experiments of the user study in five non-reference datasets were conducted to subjectively evaluate the effects depicted in the images. These experiments verified the remarkable performance of the proposed method.

An Automatic Method for Sublingual Image Segmentation and Color Analysis

Automatic segmentation of sublingual images and color quantification of sublingual vein are of great significance to disease diagnosis in traditional Chinese medicine. With the development of computer vision, automatic sublingual image processing provides a noninvasive way to observe patients' tongue and is convenient for both doctors and patients. However, current sublingual image segmentation methods are not accurate enough. Besides, the differences in subjective judgments by different doctors bring more difficulties in color analysis of sublingual veins. In this paper, we propose a method of sublingual image segmentation based on a modified UNet++ network to improve the segmentation accuracy, a color classification approach based on triplet network, and a color quantization method of sublingual vein based on linear discriminant analysis to provide intuitive one-dimensional results. Our methods achieve 88.2% mean intersection over union (mIoU) and 94.1% pixel accuracy on tongue dorsum segmentation, and achieves 69.8% mIoU and 82.7% pixel accuracy on sublingual vein segmentation. Compared with the state-of-art methods, the segmentation mIoUs are improved by 5.8% and 5.3% respectively. Our sublingual vein color classification method has the highest overall accuracy of 81.2% and the highest recall for the minority class of 77.5%, and the accuracy of color quantization is 90.5%.Clinical Relevance- The methods provide accurate and quantified information of the sublingual image, which can assist doctors in diagnosis.