RetinexMCNet: A Memory Controller Dominated Network for Low-Light Video Enhancement Based on Retinex

Low-light video enhancement (LLVE) aims to restore videos degraded by insufficient illumination. While existing methods have demonstrated their effectiveness, they often face challenges with intra-frame noise, overexposure, and interframe inconsistency since they fail to exploit the temporal continuity across frames. Inspired by the progressive video understanding mechanism of human, we propose a novel end-to-end two-stage memory controller (MC) dominated network (RetinexMCNet). Specifically, we first define the overall optimization objective for Retinex-based LLVE, and accordingly design our framework. In stage one, aided by a dual-perspective Lightness-Texture Stability (LTS) loss, we perform per-frame enhancement without the MC, which uses channel-aware Illumination Adjustment Module (IAM) and illumination-guided Reflectance Denoising Module (RDM) based on Retinex theory to mitigate intra-frame noise and overexposure. In stage two, we activate the MC to simulate human temporal memory and integrate it with high-quality single frames for global consistency. Extensive qualitative and quantitative experiments on common low-light datasets demonstrate our method significantly outperforms state-of-the-art approaches. Code.