TL;DR
This work validates the design effectiveness of decoupling global and local representations within a frozen backbone, and establishes a new baseline for parameter-efficient enhancement.
Image enhancement is a widely researched area in the domain of computer vision, particularly image processing. Among the subdomains, low-light image enhancement (LLIE) receives considerable attention due to problems and challenges imposed by poor lighting conditions. As such, low-light images suffer from poor visibility, distorted colors, and loss of details, which limits their usability in many applications. The traditional methods have struggled to preserve such details and make the images susceptible to over-enhancement. Whereas, the learning-based techniques rely heavily on paired datasets for training. Therefore, we propose a Bidirectional Conv-GRU integrated GAN framework. Involving bidirectional Conv-GRU modules in our use-case enables the model to capture both local textures and long-range feature dependencies. Also, the use of unpaired datasets allows it to learn flexible and realistic mappings without the strict need for aligned image pairs. The results demonstrate the potency of our proposed work as compared to state-of-the-art methods.
Low-light image enhancement is crucial in situations where visible sensors might suffer from severe noise and information loss ( e.g., nighttime surveillance). Recent approaches investigate auxiliary modalities invariant to illumination to improve the performance, such as thermal infrared imaging. We propose a Multimodal Intrinsics-Guided Framework that integrates RGB and thermal data to reconstruct well-lit images. Our method utilizes a two-stage pipeline: first, we employ an intrinsic decomposition strategy to separate re-flectance and shading components through knowledge distillation, where a teacher network guides a student model in re-constructing consistent intrinsic components; then, a refine-ment stage restores fine structures and visual details. We train the proposed model on synthetic data from HDRT dataset and demonstrate strong generalization to real-world benchmarks such as LLVIP and V-TIEE, outperforming state-of-the-art methods in most evaluation metrics. Code is available at : https://github.com/simonemelc/TIRGlow
Images captured under practical low-light conditions typically suffer from insufficient brightness, color distortion, noise, and blur, and the enhancement process itself may further introduce overexposed highlights. This paper presents HLCNet, an HVI-guided Large-Small Convolutional Cross-Branch Network for low-light restoration. RGB inputs are transformed into the HVI space so that chromatic and intensity information can be enhanced in two complementary branches. Each branch applies LSConv to couple broad illumination context with local structural modeling, followed by SE channel recalibration and an LCA-based encoder–decoder, while a soft overexposure constraint suppresses excessive responses without hard clipping. To ensure a controlled comparison, CIDNet is reproduced in the same Tesla T4 environment, whereas the published CIDNet results and other previously reported values are explicitly marked as external references. On LOL-Blur, HLCNet raises the PSNR of the reproduced CIDNet baseline from 26.5438 dB to 27.6260 dB, increases the SSIM from 0.8839 to 0.8863, and reduces the LPIPS from 0.1224 to 0.1056. On LOL-v2 Real and Synthetic, it attains 23.843 dB and 25.991 dB PSNR, respectively. Ablation, sensitivity, qualitative, and perceptual color-space analyses indicate that HLCNet is particularly effective for low-light images containing blur and weak structural details.
Joint photographic experts group (JPEG) is one of the most widely used image compression standards, but its lossy nature often introduces visible artifacts such as blocking, ringing, and blurring, particularly at lower quality factors. These degradations significantly reduce perceptual quality and affect downstream computer vision tasks. To address these limitations, in this study work a CNN-based edge-aware artifact reduction framework (CNN-AR) is proposed that integrates an enhanced deep super-resolution (EDSR) backbone with a holistically nested edge detection (HED) guided loss. This design enforces both pixel fidelity and edge consistency, enabling superior artifact suppression while preserving fine structural details. Extensive experiments conducted on benchmark datasets (LIVE1, Kodak, Set14, Classic5, and CLIC) across quality factors 10–40 demonstrate the effectiveness of the proposed approach. Compared to state-ofthe-art models including ARCNN, DnCNN, and DPW-SDNet, the proposed method consistently achieves higher perceptual scores. On average, CNN-AR improves PSNR by +0.38 dB, Structural Similarity Index (SSIM) by +0.012, MS-SSIM by +0.009, and PSNR-B by +0.41 dB across datasets, shows its ability to deliver both numerically superior and visually sharper reconstructions.
Images captured in hazy environment are often degraded, thereby impacting several applications of computer vision, like image segmentation, classification, object recognition, and many others. Accordingly, various techniques and algorithms for image dehazing were developed over the years - from old days traditional to the recent deep learning methods. Although deep learning technology have been proved to be better performing than the traditional methods, they are plagued by several drawbacks like high computational demand, limiting their usage for real-time applications. In view of this, here we develop a lightweight encoder-decoder network (LED-Net) for single-image haze removal in real-time using deep learning technology. To make it lightweight, we incorporate the depth-wise convolution in each convolution block. The performance of LED-Net is assessed on the basis of quantitative performance metrics, viz., PSNR and SSIM), qualitative analysis (visual quality), and real-time performance metrics such as inference time and throughput. Results obtained in our experiments show that, in comparison to some other previous state-of-the-art methods, our model offers a good compromise between output image quality and architectural complexity.
Low-light image enhancement has made significant progress through both traditional Retinex methods and deep learning techniques. Traditional Retinex-based methods decompose images into illumination and reflectance components to mimic human perception of brightness and color. However, these methods often struggle with noise suppression and detail preservation, particularly under severe low-light conditions. Recent Transformer-based methods, such as RetinexFormer and Restormer, have improved restoration performance by modeling long-range dependencies, but they still insufficiently explore the interaction between illumination variations and spatial--semantic features. To address these limitations, we propose Illumination-Aware Attention-based Transformer (IA2former), a novel low-light image enhancement model that explicitly models illumination-aware feature interactions. By integrating an Illumination-Aware Attention mechanism and an Illumination-Aware Loss function, IA2former effectively captures long-range dependencies, improves detail restoration, and preserves spatial structures under challenging illumination conditions. Experimental evaluations on the LOL-v1 and LOL-v2 datasets demonstrate that IA2former achieves a favorable overall balance across PSNR, SSIM, and LPIPS, obtaining the best performance on multiple metrics and remaining competitive on others. These results validate the effectiveness and robustness of the proposed illumination-aware modeling strategy for low-light image enhancement.