IllumFlow: Illumination-Adaptive Low-Light Enhancement via Conditional Rectified Flow and Retinex Decomposition
This addresses low-light enhancement for image processing applications, representing an incremental improvement through a novel hybrid method.
The authors tackled low-light image enhancement by combining conditional Rectified Flow with Retinex decomposition to handle illumination variations and noise, achieving superior quantitative and qualitative performance over existing methods in experiments.
We present IllumFlow, a novel framework that synergizes conditional Rectified Flow (CRF) with Retinex theory for low-light image enhancement (LLIE). Our model addresses low-light enhancement through separate optimization of illumination and reflectance components, effectively handling both lighting variations and noise. Specifically, we first decompose an input image into reflectance and illumination components following Retinex theory. To model the wide dynamic range of illumination variations in low-light images, we propose a conditional rectified flow framework that represents illumination changes as a continuous flow field. While complex noise primarily resides in the reflectance component, we introduce a denoising network, enhanced by flow-derived data augmentation, to remove reflectance noise and chromatic aberration while preserving color fidelity. IllumFlow enables precise illumination adaptation across lighting conditions while naturally supporting customizable brightness enhancement. Extensive experiments on low-light enhancement and exposure correction demonstrate superior quantitative and qualitative performance over existing methods.