Towards Lightest Low-Light Image Enhancement Architecture for Mobile Devices

TL;DR

LiteIE is an ultra-lightweight, unsupervised low-light image enhancement framework designed for mobile devices, achieving high quality and real-time performance with minimal parameters.

Contribution

The paper introduces LiteIE, a novel unsupervised, parameter-efficient architecture with a parameter-free iterative module for real-time low-light enhancement on mobile devices.

Findings

LiteIE surpasses SOTA by 1.4 dB PSNR on LOL dataset.

LiteIE runs at 30 FPS on Snapdragon 8 Gen 3 for 4K images.

LiteIE uses only 0.07% of parameters compared to existing methods.

Abstract

Real-time low-light image enhancement on mobile and embedded devices requires models that balance visual quality and computational efficiency. Existing deep learning methods often rely on large networks and labeled datasets, limiting their deployment on resource-constrained platforms. In this paper, we propose LiteIE, an ultra-lightweight unsupervised enhancement framework that eliminates dependence on large-scale supervision and generalizes well across diverse conditions. We design a backbone-agnostic feature extractor with only two convolutional layers to produce compact image features enhancement tensors. In addition, we develop a parameter-free Iterative Restoration Module, which reuses the extracted features to progressively recover fine details lost in earlier enhancement steps, without introducing any additional learnable parameters. We further propose an unsupervised training objective that integrates exposure control, edge-aware smoothness, and multi-scale color consistency losses. Experiments on the LOL dataset, LiteIE achieves 19.04 dB PSNR, surpassing SOTA by 1.4 dB while using only 0.07\% of its parameters. On a Snapdragon 8 Gen 3 mobile processor, LiteIE runs at 30 FPS for 4K images with just 58 parameters, enabling real-time deployment on edge devices. These results establish LiteIE as an efficient and practical solution for low-light enhancement on resource-limited platforms.