Bright-Channel Retinex Enhancement with a Conditional Overdispered-Noise Analysis
2026-08-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors propose a method to make dark photos look clearer without needing to train a computer model. They estimate the lighting in small parts of the image and use mathematical techniques to separate the light from the surface details while reducing noise. Their approach works well on a standard dataset, achieving better quality scores than other traditional methods and runs quickly on common hardware. The noise model they use helps understand noise but is not based on exact sensor data, and some steps are approximations rather than exact solutions.
low-light enhancementRetinex theoryillumination estimationheteroscedastic noiseNegative Binomial modelmaximum-likelihood estimationedge-preserving denoisingPSNRSSIMbilateral filter
Authors
Jongpil Jeong
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.