GTFMN: Guided Texture and Feature Modulation Network for Low-Light Image Enhancement and Super-Resolution
This work addresses the coupled degradation in low-light image super-resolution, which is an incremental improvement for image processing applications.
The paper tackled the problem of low-light image super-resolution by proposing a network that decouples illumination estimation and texture restoration, achieving state-of-the-art performance on OmniNormal5 and OmniNormal15 datasets.
Low-light image super-resolution (LLSR) is a challenging task due to the coupled degradation of low resolution and poor illumination. To address this, we propose the Guided Texture and Feature Modulation Network (GTFMN), a novel framework that decouples the LLSR task into two sub-problems: illumination estimation and texture restoration. First, our network employs a dedicated Illumination Stream whose purpose is to predict a spatially varying illumination map that accurately captures lighting distribution. Further, this map is utilized as an explicit guide within our novel Illumination Guided Modulation Block (IGM Block) to dynamically modulate features in the Texture Stream. This mechanism achieves spatially adaptive restoration, enabling the network to intensify enhancement in poorly lit regions while preserving details in well-exposed areas. Extensive experiments demonstrate that GTFMN achieves the best performance among competing methods on the OmniNormal5 and OmniNormal15 datasets, outperforming them in both quantitative metrics and visual quality.