Low-light Enhancement Method Based on Attention Map Net

TL;DR

This paper introduces BrightenNet, an attention-based U-Net model combined with LSGAN for low-light image enhancement, improving detail preservation and robustness for downstream vision tasks.

Contribution

The paper proposes BrightenNet, an improved low-light enhancement network integrating attention mechanisms and GAN training for superior performance.

Findings

Enhanced image details and human vision conformity.

Robustness of the enhancement network.

Effective application in complex vision tasks.

Abstract

Low-light image enhancement is a crucial preprocessing task for some complex vision tasks. Target detection, image segmentation, and image recognition outcomes are all directly impacted by the impact of image enhancement. However, the majority of the currently used image enhancement techniques do not produce satisfactory outcomes, and these enhanced networks have relatively weak robustness. We suggest an improved network called BrightenNet that uses U-Net as its primary structure and incorporates a number of different attention mechanisms as a solution to this issue. In a specific application, we employ the network as the generator and LSGAN as the training framework to achieve better enhancement results. We demonstrate the validity of the proposed network BrightenNet in the experiments that follow in this paper. The results it produced can both preserve image details and conform to human vision standards.