DeepFusionNet: Autoencoder-Based Low-Light Image Enhancement and Super-Resolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Çalışkan, Halil Hüseyin, Koruk, Talha
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912642620194816
author Çalışkan, Halil Hüseyin
Koruk, Talha
author_facet Çalışkan, Halil Hüseyin
Koruk, Talha
contents Computer vision and image processing applications suffer from dark and low-light images, particularly during real-time image transmission. Currently, low light and dark images are converted to bright and colored forms using autoencoders; however, these methods often achieve low SSIM and PSNR scores and require high computational power due to their large number of parameters. To address these challenges, the DeepFusionNet architecture has been developed. According to the results obtained with the LOL-v1 dataset, DeepFusionNet achieved an SSIM of 92.8% and a PSNR score of 26.30, while containing only approximately 2.5 million parameters. On the other hand, conversion of blurry and low-resolution images into high-resolution and blur-free images has gained importance in image processing applications. Unlike GAN-based super-resolution methods, an autoencoder-based super resolution model has been developed that contains approximately 100 thousand parameters and uses the DeepFusionNet architecture. According to the results of the tests, the DeepFusionNet based super-resolution method achieved a PSNR of 25.30 and a SSIM score of 80.7 percent according to the validation set.
format Preprint
id arxiv_https___arxiv_org_abs_2510_10122
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DeepFusionNet: Autoencoder-Based Low-Light Image Enhancement and Super-Resolution
Çalışkan, Halil Hüseyin
Koruk, Talha
Computer Vision and Pattern Recognition
Artificial Intelligence
68T45, 68T10
I.2.10; I.4.9
Computer vision and image processing applications suffer from dark and low-light images, particularly during real-time image transmission. Currently, low light and dark images are converted to bright and colored forms using autoencoders; however, these methods often achieve low SSIM and PSNR scores and require high computational power due to their large number of parameters. To address these challenges, the DeepFusionNet architecture has been developed. According to the results obtained with the LOL-v1 dataset, DeepFusionNet achieved an SSIM of 92.8% and a PSNR score of 26.30, while containing only approximately 2.5 million parameters. On the other hand, conversion of blurry and low-resolution images into high-resolution and blur-free images has gained importance in image processing applications. Unlike GAN-based super-resolution methods, an autoencoder-based super resolution model has been developed that contains approximately 100 thousand parameters and uses the DeepFusionNet architecture. According to the results of the tests, the DeepFusionNet based super-resolution method achieved a PSNR of 25.30 and a SSIM score of 80.7 percent according to the validation set.
title DeepFusionNet: Autoencoder-Based Low-Light Image Enhancement and Super-Resolution
topic Computer Vision and Pattern Recognition
Artificial Intelligence
68T45, 68T10
I.2.10; I.4.9
url https://arxiv.org/abs/2510.10122