A Lightweight Real-Time Low-Light Enhancement Network for Embedded Automotive Vision Systems

TL;DR

This paper introduces UltraFast-LieNET, a lightweight, real-time neural network designed for low-light image enhancement in automotive systems, achieving high performance with minimal computational resources.

Contribution

It proposes a novel Dynamic Shifted Convolution and multi-scale residual blocks for efficient low-light enhancement, enabling real-time processing on embedded systems.

Findings

Outperforms state-of-the-art methods by 4.6 dB PSNR on LOLI-Street dataset.

Uses only 180 parameters, demonstrating high efficiency.

Achieves real-time enhancement suitable for embedded automotive applications.

Abstract

In low-light environments like nighttime driving, image degradation severely challenges in-vehicle camera safety. Since existing enhancement algorithms are often too computationally intensive for vehicular applications, we propose UltraFast-LieNET, a lightweight multi-scale shifted convolutional network for real-time low-light image enhancement. We introduce a Dynamic Shifted Convolution (DSConv) kernel with only 12 learnable parameters for efficient feature extraction. By integrating DSConv with varying shift distances, a Multi-scale Shifted Residual Block (MSRB) is constructed to significantly expand the receptive field. To mitigate lightweight network instability, a residual structure and a novel multi-level gradient-aware loss function are incorporated. UltraFast-LieNET allows flexible parameter configuration, with a minimum size of only 36 parameters. Results on the LOLI-Street dataset show a PSNR of 26.51 dB, outperforming state-of-the-art methods by 4.6 dB while utilizing only 180 parameters. Experiments across four benchmark datasets validate its superior balance of real-time performance and enhancement quality under limited resources. Code is available at https://githubhttps://github.com/YuhanChen2024/UltraFast-LiNET