DEFormer: DCT-driven Enhancement Transformer for Low-light Image and Dark Vision
Low-light image enhancement restores colors and details of single image and improves high-level visual tasks. However, restoring the lost details in the dark area is a challenge by only relying on the RGB domain. In this paper, we introduce frequency as a new clue into the network and propose a DCT-...
Saved in:
| Main Authors | , , , |
|---|---|
| Format | Journal Article |
| Language | English |
| Published |
13.09.2023
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Low-light image enhancement restores colors and details of single image and
improves high-level visual tasks. However, restoring the lost details in the
dark area is a challenge by only relying on the RGB domain. In this paper, we
introduce frequency as a new clue into the network and propose a DCT-driven
enhancement transformer (DEFormer) framework. First, we propose a learnable
frequency branch (LFB) for frequency enhancement contains DCT processing and
curvature-based frequency enhancement (CFE) to represent frequency features. In
addition, we propose a cross domain fusion (CDF) for reducing the differences
between the RGB domain and the frequency domain. Our DEFormer has achieved
advanced results in both the LOL and MIT-Adobe FiveK datasets and improved the
performance of dark detection. |
|---|---|
| AbstractList | Low-light image enhancement restores colors and details of single image and
improves high-level visual tasks. However, restoring the lost details in the
dark area is a challenge by only relying on the RGB domain. In this paper, we
introduce frequency as a new clue into the network and propose a DCT-driven
enhancement transformer (DEFormer) framework. First, we propose a learnable
frequency branch (LFB) for frequency enhancement contains DCT processing and
curvature-based frequency enhancement (CFE) to represent frequency features. In
addition, we propose a cross domain fusion (CDF) for reducing the differences
between the RGB domain and the frequency domain. Our DEFormer has achieved
advanced results in both the LOL and MIT-Adobe FiveK datasets and improved the
performance of dark detection. |
| Author | Gao, Xin Yin, Xiangchen Yu, Zhenda Sun, Xiao |
| Author_xml | – sequence: 1 givenname: Xiangchen surname: Yin fullname: Yin, Xiangchen – sequence: 2 givenname: Zhenda surname: Yu fullname: Yu, Zhenda – sequence: 3 givenname: Xin surname: Gao fullname: Gao, Xin – sequence: 4 givenname: Xiao surname: Sun fullname: Sun, Xiao |
| BackLink | https://doi.org/10.48550/arXiv.2309.06941$$DView paper in arXiv |
| BookMark | eNotz71OwzAYhWEPMEDhApjwDTjYseMfNpSktFIkOkRdo4_6S2vROMipCtw9EJje5ehIzzW5iGNEQu4Ez5QtCv4A6TOcs1xyl3HtlLgim6pejmnA9EirsmU-hTNGWscDxB0OGE-0TRCnft7Qn9Bm_GDHsD-c6HqAPVKInlaQ3ug2TGGMN-Syh-OEt_9dkHZZt-WKNS_P6_KpYaCNYAi9ks6i0DY3Ho2CnSty0SsBhTROYA7eaouGa22U8dL02lvJCyUEvGouF-T-73Ymde8pDJC-ul9aN9PkNwo9SWE |
| ContentType | Journal Article |
| Copyright | http://arxiv.org/licenses/nonexclusive-distrib/1.0 |
| Copyright_xml | – notice: http://arxiv.org/licenses/nonexclusive-distrib/1.0 |
| DBID | AKY GOX |
| DOI | 10.48550/arxiv.2309.06941 |
| DatabaseName | arXiv Computer Science arXiv.org |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: GOX name: arXiv.org url: http://arxiv.org/find sourceTypes: Open Access Repository |
| DeliveryMethod | fulltext_linktorsrc |
| ExternalDocumentID | 2309_06941 |
| GroupedDBID | AKY GOX |
| ID | FETCH-LOGICAL-a671-eaf4398e16827de74ac9521f41a53791e2ad868e7066747d37f6d8305411ab603 |
| IEDL.DBID | GOX |
| IngestDate | Wed Sep 11 12:28:31 EDT 2024 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | false |
| IsScholarly | false |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-a671-eaf4398e16827de74ac9521f41a53791e2ad868e7066747d37f6d8305411ab603 |
| OpenAccessLink | https://arxiv.org/abs/2309.06941 |
| ParticipantIDs | arxiv_primary_2309_06941 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-09-13 |
| PublicationDateYYYYMMDD | 2023-09-13 |
| PublicationDate_xml | – month: 09 year: 2023 text: 2023-09-13 day: 13 |
| PublicationDecade | 2020 |
| PublicationYear | 2023 |
| Score | 1.8940834 |
| SecondaryResourceType | preprint |
| Snippet | Low-light image enhancement restores colors and details of single image and
improves high-level visual tasks. However, restoring the lost details in the
dark... |
| SourceID | arxiv |
| SourceType | Open Access Repository |
| SubjectTerms | Computer Science - Artificial Intelligence Computer Science - Computer Vision and Pattern Recognition |
| Title | DEFormer: DCT-driven Enhancement Transformer for Low-light Image and Dark Vision |
| URI | https://arxiv.org/abs/2309.06941 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwdV1LT8QgECbrnrwYjZr1GQ5e0YXSQr2ZbetqfB2q6a2BAtGoXYPr4-c7tLvRiyeSYULCkGG-gXkgdGQkN6BImjBpHeE84kRq3hBArrEQYyCqkCh8fZNM7_llFVcDhJe5MMp_P3329YH1-wng4_Q4pGaCf7PCWAjZOr-t-s_JrhTXgv-XDzBmR_pjJIp1tLZAd_isP44NNLDtJrrL8gKQofWnOJuUxPhwweC8fQwCD49zuFyiR-sxDPhq9kVegteML15B3zF4-zhT_hk_dJngW6gs8nIyJYtGBkQlghKrHJh9aWkimTBWcNWkYDUdpyqOREotU0Ym0ooQcMqFiYRLjARF5JQqnYyjbTRsZ60dISxhFeUa3ugYtM3JlBpAXDZtmBGOSbqDRt3267e-VkUdJFN3ktn9f2oPrYYu6iEMgkb7aDj3H_YAbO1cH3YC_wHqsH0r |
| link.rule.ids | 228,230,783,888 |
| linkProvider | Cornell University |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=DEFormer%3A+DCT-driven+Enhancement+Transformer+for+Low-light+Image+and+Dark+Vision&rft.au=Yin%2C+Xiangchen&rft.au=Yu%2C+Zhenda&rft.au=Gao%2C+Xin&rft.au=Sun%2C+Xiao&rft.date=2023-09-13&rft_id=info:doi/10.48550%2Farxiv.2309.06941&rft.externalDocID=2309_06941 |