Enhancement and Noise Suppression of Single Low-Light Grayscale Images

Article Engineering, Electrical & Electronic

RetinexDIP: A Unified Deep Framework for Low-Light Image Enhancement

Zunjin Zhao et al.

Summary: This paper proposes a novel generative strategy and a unified deep framework for enhancing low-light images. Experimental results demonstrate the superiority of the proposed method.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2022)

Add to Collection

Article Computer Science, Information Systems

Image Enhancement Algorithm Based on GAN Neural Network

Bo Xu et al.

Summary: This paper proposes an enhancement method based on GAN for effectively enhancing low-quality underwater images. The method improves the quality of low-light images and restores the original scene information to obtain natural and clear images with complete details and structural information.

IEEE ACCESS (2022)

Add to Collection

Article Computer Science, Information Systems

LiCENt: Low-Light Image Enhancement Using the Light Channel of HSL

Atik Garg et al.

Summary: Images captured in low-brightness environments often suffer from poor visibility and artifacts. We proposed a fast and lightweight deep learning-based algorithm, LiCENt, which utilizes the light channel of HSL color space for low-light image enhancement. Experimental results show that our approach outperforms other methods in terms of qualitative and quantitative metrics.

IEEE ACCESS (2022)

Add to Collection

Article Environmental Sciences

Multi-Exposure Fusion of Gray Images Under Low Illumination Based on Low-Rank Decomposition

Ting Nie et al.

Summary: The proposed MEF method utilizes LatLRR technique to process low-illumination gray images by separating them into low-rank parts and saliency parts to effectively reduce noise after fusion; the fusion process is optimized through constructing different weight maps and designing an energy equation; an improved guided filtering technique is introduced to maintain spatial consistency and avoid artifacts, resulting in a high dynamic range image.

REMOTE SENSING (2021)

Add to Collection

Article Environmental Sciences

RSCNN: A CNN-Based Method to Enhance Low-Light Remote-Sensing Images

Linshu Hu et al.

Summary: Image enhancement technology using Convolutional Neural Networks, such as the RSCNN, has shown significant success in improving the brightness and quality of remote-sensing images. By utilizing multi-scaled features and training with both natural and simulated image data, RSCNN outperforms conventional techniques in terms of SSIM and PSNR for low-light remote-sensing image enhancement. Additionally, RSCNN demonstrates qualitative advantages in denoising and preserving colors and textures.

REMOTE SENSING (2021)

Add to Collection

Article Computer Science, Information Systems

LLISP: Low-Light Image Signal Processing Net via Two-Stage Network

Hongjin Zhu et al.

Summary: A two-stage Low Light Image Signal Processing Network named LLISP is proposed to effectively remove heavy noise, correct color bias, and enhance details, replacing the traditional ISP.

IEEE ACCESS (2021)

Add to Collection

Article Computer Science, Information Systems