Lightweight Image Enhancement Network for Mobile Devices Using Self-Feature Extraction and Dense Modulation

TL;DR

This paper introduces a lightweight CNN for mobile image enhancement that uses self-feature extraction and dense modulation to improve detail restoration while reducing computational costs.

Contribution

It proposes a novel lightweight network with self-feature extraction and dense modulation blocks for efficient image enhancement on mobile devices.

Findings

Outperforms existing methods in quantitative metrics

Achieves better qualitative visual results

Reduces computational complexity for mobile deployment

Abstract

Convolutional neural network (CNN) based image enhancement methods such as super-resolution and detail enhancement have achieved remarkable performances. However, amounts of operations including convolution and parameters within the networks cost high computing power and need huge memory resource, which limits the applications with on-device requirements. Lightweight image enhancement network should restore details, texture, and structural information from low-resolution input images while keeping their fidelity. To address these issues, a lightweight image enhancement network is proposed. The proposed network include self-feature extraction module which produces modulation parameters from low-quality image itself, and provides them to modulate the features in the network. Also, dense modulation block is proposed for unit block of the proposed network, which uses dense connections of concatenated features applied in modulation layers. Experimental results demonstrate better performance over existing approaches in terms of both quantitative and qualitative evaluations.