Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2025
|
| Online Access: | https://doi.org/10.5281/zenodo.18034621 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- <p>Low-light imaging has become a popular topic in image processing, with the quality enhancement of low light images<br>being as a significant challenge, due to the difficulty in retaining colors, patterns, texture and style when generating<br>a normal light image. Our objectives are mainly to firstly better preserve texture regions in image enhancement,<br>while, secondly, preserving colors via color histogram blocks and, finally, to enhance the quality of image through<br>dense denoising blocks. Our proposed novel framework, namely HDD-Unet, is a double Unet based on photorealistic<br>style transfer for low-light image enhancement. The proposed low-light image enhancement method combines<br>color histogram-based fusion, Haar wavelet pooling, dense-denoising blocks and U-net as a backbone architecture to<br>enhance the contrast, reduce noise, and improve the visibility of low light images. Experimental results demonstrate<br>that our proposed method outperforms existing methods in terms of PSNR and SSIM quantitative evaluation metrics,<br>reaching or outperforming state-of-the-art accuracy, but with less resources. We also conduct an ablation study to<br>investigate the impact of our approach on overexposed images, and systematic analysis on the late fusion weighting<br>parameters. Multiple experiments were conducted with artificial noise inserted to accomplish more efficient comparison.<br>The results show that the proposed framework enhances accurately images with various gamma corrections. The<br>proposed method represents a significant advance in the field of low light image enhancement and has the potential to<br>address several challenges associated with low light imaging.</p>