DepthLux: Employing Depthwise Separable Convolutions for Low-Light Image Enhancement

Low-light image enhancement is an important task in computer vision, often made challenging by the limitations of image sensors, such as noise, low contrast, and color distortion. These challenges are further exacerbated by the computational demands of processing spatial dependencies under such cond...

Full description

Saved in:
Bibliographic Details
Main Authors: Raul Balmez, Alexandru Brateanu, Ciprian Orhei, Codruta O. Ancuti, Cosmin Ancuti
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/5/1530
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850053040702226432
author Raul Balmez
Alexandru Brateanu
Ciprian Orhei
Codruta O. Ancuti
Cosmin Ancuti
author_facet Raul Balmez
Alexandru Brateanu
Ciprian Orhei
Codruta O. Ancuti
Cosmin Ancuti
author_sort Raul Balmez
collection DOAJ
description Low-light image enhancement is an important task in computer vision, often made challenging by the limitations of image sensors, such as noise, low contrast, and color distortion. These challenges are further exacerbated by the computational demands of processing spatial dependencies under such conditions. We present a novel transformer-based framework that enhances efficiency by utilizing depthwise separable convolutions instead of conventional approaches. Additionally, an original feed-forward network design reduces the computational overhead while maintaining high performance. Experimental results demonstrate that this method achieves competitive results, providing a practical and effective solution for enhancing images captured in low-light environments.
format Article
id doaj-art-bce5c69721fc4aeca4e7a1093bb1cbf7
institution DOAJ
issn 1424-8220
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-bce5c69721fc4aeca4e7a1093bb1cbf72025-08-20T02:52:38ZengMDPI AGSensors1424-82202025-03-01255153010.3390/s25051530DepthLux: Employing Depthwise Separable Convolutions for Low-Light Image EnhancementRaul Balmez0Alexandru Brateanu1Ciprian Orhei2Codruta O. Ancuti3Cosmin Ancuti4Department of Computer Science, University of Manchester, Manchester M13 9PL, UKDepartment of Computer Science, University of Manchester, Manchester M13 9PL, UKFaculty of Electronics, Telecommunications and Information Technologies, Polytechnic University Timisoara, 300223 Timisoara, RomaniaFaculty of Electronics, Telecommunications and Information Technologies, Polytechnic University Timisoara, 300223 Timisoara, RomaniaFaculty of Electronics, Telecommunications and Information Technologies, Polytechnic University Timisoara, 300223 Timisoara, RomaniaLow-light image enhancement is an important task in computer vision, often made challenging by the limitations of image sensors, such as noise, low contrast, and color distortion. These challenges are further exacerbated by the computational demands of processing spatial dependencies under such conditions. We present a novel transformer-based framework that enhances efficiency by utilizing depthwise separable convolutions instead of conventional approaches. Additionally, an original feed-forward network design reduces the computational overhead while maintaining high performance. Experimental results demonstrate that this method achieves competitive results, providing a practical and effective solution for enhancing images captured in low-light environments.https://www.mdpi.com/1424-8220/25/5/1530image sensor restorationlow-light enhancementvision transformer
spellingShingle Raul Balmez
Alexandru Brateanu
Ciprian Orhei
Codruta O. Ancuti
Cosmin Ancuti
DepthLux: Employing Depthwise Separable Convolutions for Low-Light Image Enhancement
Sensors
image sensor restoration
low-light enhancement
vision transformer
title DepthLux: Employing Depthwise Separable Convolutions for Low-Light Image Enhancement
title_full DepthLux: Employing Depthwise Separable Convolutions for Low-Light Image Enhancement
title_fullStr DepthLux: Employing Depthwise Separable Convolutions for Low-Light Image Enhancement
title_full_unstemmed DepthLux: Employing Depthwise Separable Convolutions for Low-Light Image Enhancement
title_short DepthLux: Employing Depthwise Separable Convolutions for Low-Light Image Enhancement
title_sort depthlux employing depthwise separable convolutions for low light image enhancement
topic image sensor restoration
low-light enhancement
vision transformer
url https://www.mdpi.com/1424-8220/25/5/1530
work_keys_str_mv AT raulbalmez depthluxemployingdepthwiseseparableconvolutionsforlowlightimageenhancement
AT alexandrubrateanu depthluxemployingdepthwiseseparableconvolutionsforlowlightimageenhancement
AT ciprianorhei depthluxemployingdepthwiseseparableconvolutionsforlowlightimageenhancement
AT codrutaoancuti depthluxemployingdepthwiseseparableconvolutionsforlowlightimageenhancement
AT cosminancuti depthluxemployingdepthwiseseparableconvolutionsforlowlightimageenhancement