A training-free low-light enhancement method that combines local bright-channel illumination estimation, Retinex division, and edge-preserving denoising and obtains mean PSNR/SSIM of 17.74dB/0.739, the highest values among the evaluated with conventional methods.
Abstract
I present a training-free low-light enhancement method that combines local bright-channel illumination estimation, Retinex division, and edge-preserving denoising. For a fixed illumination estimate, a conditional Negative -Binominal psueduo-count method characterises the heteroscedastic noise amplified by division. The unconstrained reflectance ratio is the pixelwise maximum-likelihood estimate, with a boundary solution for zero-valued observations; the implemented estimate additionally applies illumination filtering and range clipping. The NB model is a diagnostic noise analysis rather than a calibrated sensor model, and the final fixed-bandwidth bilateral filter is an empirical approximation rather than the exact Bayesian solution. On the LOL-v1 dataset, the methodobtains mean PSNR/SSIM of 17.74dB/0.739, the highest values among the evaluated with conventional methods. A 400X600 image is processed at approximately 43 FPS on an Apple M2 Pro CPU.
A blind image denoising framework based on an infinite directional lower semi-frame (DLSF) is proposed for additive white Gaussian noise. The model employs scale-dependent directional analysis with resolvent regularization of the unbounded semi-frame operator. Noise variance is estimated directly in the DLSF domain by...
SF-GAL, a prior-calibrated spatial-frequency Retinex decomposition framework for unsupervised low-light image enhancement, which calibrates a CLAHE-derived structural prior, decomposes low-light features through complementary spatial and wavelet branches, and uses structure-guided frequency modulation to regulate frequ...
Xin-Hua Dong, Yu Gao, Hongmu Han et al.· The Visual Computer· 0 citations
Retinex-based low-light image enhancement methods have drawn significant interest due to their excellent performance and extensibility. However, most of them exhibit poor robustness when images are corrupted by noise. The main reason is that traditional Retinex models cannot effectively characterize the coupling betwee...
Jing-Tian Zhao, Xue-Li Xie, Jian-Xiang Xi et al.· Image Analysis and Stereolog...· 0 citations
Low-light images suffer from coupled degradations of insufficient illumination, low contrast and amplified noise. Curve-based methods needing no paired supervision are efficient, but they correct luminance and rarely address the noise that amplification makes visible. This paper couples an iterative curve estimator wit...
Low-light image enhancement is a longstanding challenge in computer vision, aiming to restore visibility and contrast in suboptimal lighting conditions. Recently, the illumination-based self-reinforced retinex projection (SRRP) model and its enhanced version (ESRRP) have made strides in eliminating artifact-inducing po...
Kwanda Samukelo Hlatshwayo, Hong-Jun Xu, N. Pillay et al.· IEEE Access· 0 citations
Deep image denoisers achieve strong performance on synthetic additive white Gaussian noise (AWGN), but under heavy noise they often oversmooth edges and destabilize fine textures. Existing gradient-and frequency-based regularization can improve detail preservation, yet uniformly enforcing such constraints may over-regu...
Deng-Feng Qiao· 2026 7th International Confe...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
