A 7K Parameter Model for Underwater Image Enhancement based on Transmission Map Prior

TL;DR

This paper introduces LSNet, a lightweight underwater image enhancement model with only 7K parameters that outperforms similar models in efficiency and effectiveness, leveraging transmission map prior and selective attention.

Contribution

The paper proposes a novel lightweight network, LSNet, that effectively enhances underwater images using transmission map prior and top-k selective attention, reducing computational cost.

Findings

Achieves 97% PSNR with only 7K parameters.

Outperforms state-of-the-art models in efficiency and effectiveness.

Requires less computational resources for underwater image enhancement.

Abstract

Although deep learning based models for underwater image enhancement have achieved good performance, they face limitations in both lightweight and effectiveness, which prevents their deployment and application on resource-constrained platforms. Moreover, most existing deep learning based models use data compression to get high-level semantic information in latent space instead of using the original information. Therefore, they require decoder blocks to generate the details of the output. This requires additional computational cost. In this paper, a lightweight network named lightweight selective attention network (LSNet) based on the top-k selective attention and transmission maps mechanism is proposed. The proposed model achieves a PSNR of 97\% with only 7K parameters compared to a similar attention-based model. Extensive experiments show that the proposed LSNet achieves excellent performance in state-of-the-art models with significantly fewer parameters and computational resources. The code is available at https://github.com/FuhengZhou/LSNet}{https://github.com/FuhengZhou/LSNet.