GTFMN: Guided Texture and Feature Modulation Network for Low-Light Image Enhancement and Super-Resolution

TL;DR

GTFMN is a novel network that improves low-light image super-resolution by decoupling illumination estimation from texture restoration, using a guided modulation mechanism for adaptive enhancement.

Contribution

The paper introduces a new framework with a dedicated illumination stream and a guided modulation block for spatially adaptive low-light image enhancement and super-resolution.

Findings

Achieves state-of-the-art performance on OmniNormal datasets.

Outperforms competing methods in quantitative metrics.

Enhances visual quality in poorly lit regions.

Abstract

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.