Always Clear Days: Degradation Type and Severity Aware All-in-One Adverse Weather Removal
All-in-one adverse weather removal is an emerging topic on image restoration, which aims to restore multiple weather degradations in a unified model, and the challenges are twofold. First, discover and handle the properties of the multi-domain in the target distribution formed by multiple weather co...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10829609/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536201278881792 |
|---|---|
| author | Yu-Wei Chen Soo-Chang Pei |
| author_facet | Yu-Wei Chen Soo-Chang Pei |
| author_sort | Yu-Wei Chen |
| collection | DOAJ |
| description | All-in-one adverse weather removal is an emerging topic on image restoration, which aims to restore multiple weather degradations in a unified model, and the challenges are twofold. First, discover and handle the properties of the multi-domain in the target distribution formed by multiple weather conditions. Second, design efficient and effective operations for different degradations. To resolve this problem, most prior works focus on the multi-domain caused by different weather types. Inspired by inter&intra-domain adaptation literature, we observe that not only weather type but also weather severity introduce multi-domain within each weather type domain, which is ignored by previous methods and further limits their performance. To this end, we propose a degradation type and severity aware model, called UtilityIR, for blind all-in-one bad weather image restoration. To extract weather information from a single image, we propose a novel Marginal Quality Ranking Loss (MQRL) and utilize Contrastive Loss (CL) to guide weather severity and type extraction, and leverage a bag of novel techniques such as Multi-Head Cross Attention (MHCA) and Local-Global Adaptive Instance Normalization (LG-AdaIN) to efficiently restore spatial varying weather degradation. The proposed method can outperform the state-of-the-art methods subjectively and objectively on different weather removal tasks with a large margin, and enjoy fewer model parameters. The proposed method can even restore previously unseen combined multiple degradation images, and modulate restoration level. Implementation code and pre-trained weights will be available at <uri>https://github.com/fordevoted/UtilityIR</uri>. |
| format | Article |
| id | doaj-art-b205c151cbc14dd4b9d4a670ca5c20cb |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-b205c151cbc14dd4b9d4a670ca5c20cb2025-01-15T00:02:56ZengIEEEIEEE Access2169-35362025-01-01137650766210.1109/ACCESS.2025.352616810829609Always Clear Days: Degradation Type and Severity Aware All-in-One Adverse Weather RemovalYu-Wei Chen0https://orcid.org/0000-0001-9127-6536Soo-Chang Pei1https://orcid.org/0000-0003-2448-4196Graduate Institute of Communication Engineering, National Taiwan University, Taipei, TaiwanGraduate Institute of Communication Engineering and Department of Electrical Engineering, National Taiwan University, Taipei, TaiwanAll-in-one adverse weather removal is an emerging topic on image restoration, which aims to restore multiple weather degradations in a unified model, and the challenges are twofold. First, discover and handle the properties of the multi-domain in the target distribution formed by multiple weather conditions. Second, design efficient and effective operations for different degradations. To resolve this problem, most prior works focus on the multi-domain caused by different weather types. Inspired by inter&intra-domain adaptation literature, we observe that not only weather type but also weather severity introduce multi-domain within each weather type domain, which is ignored by previous methods and further limits their performance. To this end, we propose a degradation type and severity aware model, called UtilityIR, for blind all-in-one bad weather image restoration. To extract weather information from a single image, we propose a novel Marginal Quality Ranking Loss (MQRL) and utilize Contrastive Loss (CL) to guide weather severity and type extraction, and leverage a bag of novel techniques such as Multi-Head Cross Attention (MHCA) and Local-Global Adaptive Instance Normalization (LG-AdaIN) to efficiently restore spatial varying weather degradation. The proposed method can outperform the state-of-the-art methods subjectively and objectively on different weather removal tasks with a large margin, and enjoy fewer model parameters. The proposed method can even restore previously unseen combined multiple degradation images, and modulate restoration level. Implementation code and pre-trained weights will be available at <uri>https://github.com/fordevoted/UtilityIR</uri>.https://ieeexplore.ieee.org/document/10829609/Adverse weather removalall-in-one image restorationdegradation estimationderainingdehazingdesnowing |
| spellingShingle | Yu-Wei Chen Soo-Chang Pei Always Clear Days: Degradation Type and Severity Aware All-in-One Adverse Weather Removal IEEE Access Adverse weather removal all-in-one image restoration degradation estimation deraining dehazing desnowing |
| title | Always Clear Days: Degradation Type and Severity Aware All-in-One Adverse Weather Removal |
| title_full | Always Clear Days: Degradation Type and Severity Aware All-in-One Adverse Weather Removal |
| title_fullStr | Always Clear Days: Degradation Type and Severity Aware All-in-One Adverse Weather Removal |
| title_full_unstemmed | Always Clear Days: Degradation Type and Severity Aware All-in-One Adverse Weather Removal |
| title_short | Always Clear Days: Degradation Type and Severity Aware All-in-One Adverse Weather Removal |
| title_sort | always clear days degradation type and severity aware all in one adverse weather removal |
| topic | Adverse weather removal all-in-one image restoration degradation estimation deraining dehazing desnowing |
| url | https://ieeexplore.ieee.org/document/10829609/ |
| work_keys_str_mv | AT yuweichen alwayscleardaysdegradationtypeandseverityawareallinoneadverseweatherremoval AT soochangpei alwayscleardaysdegradationtypeandseverityawareallinoneadverseweatherremoval |