Customizable Restoration in Multi-Degradation Scenarios: Joint Deraining and Low-Light Image Enhancement via Perceptual Decoupling
In real-world nighttime photography, images often suffer from both low-light conditions and rain-induced degradations simultaneously. Traditional methods typically address these issues separately, which limits their effectiveness when both types of degradation are present. To address this challenge,...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10816618/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841557015513530368 |
|---|---|
| author | Zhiyong He |
| author_facet | Zhiyong He |
| author_sort | Zhiyong He |
| collection | DOAJ |
| description | In real-world nighttime photography, images often suffer from both low-light conditions and rain-induced degradations simultaneously. Traditional methods typically address these issues separately, which limits their effectiveness when both types of degradation are present. To address this challenge, we propose the Perceptual Decoupling-based Learning Network (PDLN), designed to separate these degradations by leveraging their distinct physical properties. PDLN models rain and low-light priors and integrates them through the Decoupled Perception Transformer (DPformer), enabling a robust representation of these degradations. This approach harnesses interactions in both the spatial and frequency domains, resulting in state-of-the-art performance and allowing for personalized enhancement styles. The code and dataset will be available after receipt in <uri>https://github.com/lajiaolajiaolajiao/PDLN</uri>. |
| format | Article |
| id | doaj-art-5bb91c60d9f749058051295f9d2cd870 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-5bb91c60d9f749058051295f9d2cd8702025-01-07T00:01:40ZengIEEEIEEE Access2169-35362025-01-01131688169610.1109/ACCESS.2024.352341910816618Customizable Restoration in Multi-Degradation Scenarios: Joint Deraining and Low-Light Image Enhancement via Perceptual DecouplingZhiyong He0https://orcid.org/0000-0003-2379-9807College of Electronic Information Engineering, Nanjing Vocational University of Industry Technology, Nanjing, Jiangsu, ChinaIn real-world nighttime photography, images often suffer from both low-light conditions and rain-induced degradations simultaneously. Traditional methods typically address these issues separately, which limits their effectiveness when both types of degradation are present. To address this challenge, we propose the Perceptual Decoupling-based Learning Network (PDLN), designed to separate these degradations by leveraging their distinct physical properties. PDLN models rain and low-light priors and integrates them through the Decoupled Perception Transformer (DPformer), enabling a robust representation of these degradations. This approach harnesses interactions in both the spatial and frequency domains, resulting in state-of-the-art performance and allowing for personalized enhancement styles. The code and dataset will be available after receipt in <uri>https://github.com/lajiaolajiaolajiao/PDLN</uri>.https://ieeexplore.ieee.org/document/10816618/Image restorationtransformermulti-degradationcomputer vision |
| spellingShingle | Zhiyong He Customizable Restoration in Multi-Degradation Scenarios: Joint Deraining and Low-Light Image Enhancement via Perceptual Decoupling IEEE Access Image restoration transformer multi-degradation computer vision |
| title | Customizable Restoration in Multi-Degradation Scenarios: Joint Deraining and Low-Light Image Enhancement via Perceptual Decoupling |
| title_full | Customizable Restoration in Multi-Degradation Scenarios: Joint Deraining and Low-Light Image Enhancement via Perceptual Decoupling |
| title_fullStr | Customizable Restoration in Multi-Degradation Scenarios: Joint Deraining and Low-Light Image Enhancement via Perceptual Decoupling |
| title_full_unstemmed | Customizable Restoration in Multi-Degradation Scenarios: Joint Deraining and Low-Light Image Enhancement via Perceptual Decoupling |
| title_short | Customizable Restoration in Multi-Degradation Scenarios: Joint Deraining and Low-Light Image Enhancement via Perceptual Decoupling |
| title_sort | customizable restoration in multi degradation scenarios joint deraining and low light image enhancement via perceptual decoupling |
| topic | Image restoration transformer multi-degradation computer vision |
| url | https://ieeexplore.ieee.org/document/10816618/ |
| work_keys_str_mv | AT zhiyonghe customizablerestorationinmultidegradationscenariosjointderainingandlowlightimageenhancementviaperceptualdecoupling |