Poisson Informed Retinex Network for Extreme Low-Light Image Enhancement
This addresses the problem of low-light image enhancement for applications like photography or surveillance where traditional noise assumptions fail, though it appears incremental as it builds on existing Retinex and deep learning approaches.
The paper tackles denoising and enhancing images degraded by Poisson noise in extreme low-light conditions by introducing a lightweight deep learning method that integrates Retinex decomposition with Poisson denoising into a unified encoder-decoder network, resulting in significant improvements in visibility and brightness while preserving image structure and color constancy.
Low-light image denoising and enhancement are challenging, especially when traditional noise assumptions, such as Gaussian noise, do not hold in majority. In many real-world scenarios, such as low-light imaging, noise is signal-dependent and is better represented as Poisson noise. In this work, we address the problem of denoising images degraded by Poisson noise under extreme low-light conditions. We introduce a light-weight deep learning-based method that integrates Retinex based decomposition with Poisson denoising into a unified encoder-decoder network. The model simultaneously enhances illumination and suppresses noise by incorporating a Poisson denoising loss to address signal-dependent noise. Without prior requirement for reflectance and illumination, the network learns an effective decomposition process while ensuring consistent reflectance and smooth illumination without causing any form of color distortion. The experimental results demonstrate the effectiveness and practicality of the proposed low-light illumination enhancement method. Our method significantly improves visibility and brightness in low-light conditions, while preserving image structure and color constancy under ambient illumination.