{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T11:30:40Z","timestamp":1764588640830,"version":"3.44.0"},"reference-count":70,"publisher":"Association for Computing Machinery (ACM)","issue":"9","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62375133"],"award-info":[{"award-number":["62375133"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Key Projects of University Natural Science Fund of Jiangsu Province","award":["23KJA520009"],"award-info":[{"award-number":["23KJA520009"]}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"crossref","award":["BK20230440"],"award-info":[{"award-number":["BK20230440"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2025,9,30]]},"abstract":"<jats:p>Images captured under low-light conditions suffer from poor visibility and clarity due to insufficient light. The emergence of deep learning has greatly boosted the development of low-light enhancement techniques and achieved promising results. However, while these low-light enhancement methods have enhanced the perceptual effects of human vision, their results in high-level visual tasks (e.g., object detection and semantic segmentation) are still unstable and even sometimes bring negative effects. Therefore, in this work, we propose a new model, KANformer, which uses a semantic-gradient prior as a guide to recover pixels relevant to the image subject from both high-frequency and low-frequency perspectives. Specifically, our model consists of three key components: Low-Frequency Enhancement (LFE) module, which aims to enhance the restoration of the image subject via the semantic prior obtained from SAM; Low-Frequency-Based High-Frequency Enhancement (LFHE) module, which utilizes the KAN module to obtain information from the low-frequency features conducive to the enhancement of high-frequency features; and Gradient-Based High-Frequency Enhancement (GHE) module, which aims to utilize the original gradient as prior to further enhance the structural information of the image and reduce the effect of noise. In addition, we introduce the discrete wavelet transform as down-sampling method while transforming the spatial domain features to the frequency domain for processing. Experiments on multiple paired and unpaired datasets show that our method achieves better visualization and image fidelity compared to other state-of-the-art methods. In addition, experiments on object detection and segmentation show that our method provides better enhancement in improving low-light high-level vision tasks.<\/jats:p>","DOI":"10.1145\/3750732","type":"journal-article","created":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T15:12:49Z","timestamp":1753456369000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["KANformer: Dual-Priors-Guided Low-Light Enhancement via KAN and Transformer"],"prefix":"10.1145","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7911-6748","authenticated-orcid":false,"given":"Chenyang","family":"Lu","sequence":"first","affiliation":[{"name":"School of Computer Science, Nanjing Audit University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8481-9779","authenticated-orcid":false,"given":"Zhikai","family":"Wei","sequence":"additional","affiliation":[{"name":"Nanjing Audit University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4584-216X","authenticated-orcid":false,"given":"Huapeng","family":"Wu","sequence":"additional","affiliation":[{"name":"Nanjing Audit University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4221-0327","authenticated-orcid":false,"given":"Le","family":"Sun","sequence":"additional","affiliation":[{"name":"Nanjing University of Information Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2269-2808","authenticated-orcid":false,"given":"Tianming","family":"Zhan","sequence":"additional","affiliation":[{"name":"Nanjing Audit University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,9,11]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCS48705.2020.9074386"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.23919\/ELINFOCOM.2018.8330564"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995332"},{"key":"e_1_3_1_5_2","first-page":"12504","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Cai Yuanhao","year":"2023","unstructured":"Yuanhao Cai, Hao Bian, Jing Lin, Haoqian Wang, Radu Timofte, and Yulun Zhang. 2023. Retinexformer: One-stage retinex-based transformer for low-light image enhancement. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), 12504\u201312513."},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110626"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2797872"},{"key":"e_1_3_1_8_2","first-page":"19341","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Chen Sijia","year":"2024","unstructured":"Sijia Chen, En Yu, Jinyang Li, and Wenbing Tao. 2024. Delving into the trajectory long-tail distribution for muti-object tracking. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 19341\u201319351."},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27906"},{"key":"e_1_3_1_10_2","volume-title":"Proceedings of the 33rd British Machine Vision Conference 2022 (BMVC \u201922)","author":"Cui Ziteng","year":"2022","unstructured":"Ziteng Cui, Kunchang Li, Lin Gu, Shenghan Su, Peng Gao, ZhengKai Jiang, Yu Qiao, and Tatsuya Harada. 2022. You only need 90K parameters to adapt light: A light weight transformer for image enhancement and exposure correction. In Proceedings of the 33rd British Machine Vision Conference 2022 (BMVC \u201922). BMVA Press. Retrieved from https:\/\/bmvc2022.mpi-inf.mpg.de\/0238.pdf"},{"key":"e_1_3_1_11_2","first-page":"2553","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Cui Ziteng","year":"2021","unstructured":"Ziteng Cui, Guo-Jun Qi, Lin Gu, Shaodi You, Zenghui Zhang, and Tatsuya Harada. 2021. Multitask AET with orthogonal tangent regularity for dark object detection. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), 2553\u20132562."},{"key":"e_1_3_1_12_2","first-page":"12666","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Du Zhipeng","year":"2024","unstructured":"Zhipeng Du, Miaojing Shi, and Jiankang Deng. 2024. Boosting object detection with zero-shot day-night domain adaptation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 12666\u201312676."},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02131"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00185"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2639450"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2023.3340617"},{"key":"e_1_3_1_17_2","first-page":"6725","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Hashmi Khurram Azeem","year":"2023","unstructured":"Khurram Azeem Hashmi, Goutham Kallempudi, Didier Stricker, and Muhammad Zeshan Afzal. 2023. FeatEnHancer: Enhancing hierarchical features for object detection and beyond under low-light vision. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), 6725\u20136735."},{"key":"e_1_3_1_18_2","first-page":"17574","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Hou Xiuquan","year":"2024","unstructured":"Xiuquan Hou, Meiqin Liu, Senlin Zhang, Ping Wei, and Badong Chen. 2024. Salience DETR: Enhancing detection transformer with hierarchical salience filtering refinement. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 17574\u201317583."},{"key":"e_1_3_1_19_2","first-page":"9924","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Hoyer Lukas","year":"2022","unstructured":"Lukas Hoyer, Dengxin Dai, and Luc Van Gool. 2022. DAFormer: Improving network architectures and training strategies for domain-adaptive semantic segmentation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 9924\u20139935."},{"key":"e_1_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Md Tanvir Islam Inzamamul Alam Simon S. Woo Saeed Anwar I. K. Hyun Lee and Khan Muhammad. 2024. LoLI-Street: Benchmarking low-light image enhancement and beyond. arXiv:2410.09831. Retrieved from https:\/\/arxiv.org\/abs\/2410.09831","DOI":"10.1007\/978-981-96-0917-8_20"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/83.597272"},{"key":"e_1_3_1_22_2","unstructured":"Glenn Jocher Ayush Chaurasia and Jing Qiu. 2023. YOLO by Ultralytics. Retrieved from https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"e_1_3_1_23_2","first-page":"4015","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Kirillov Alexander","unstructured":"Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C. Berg, Wan-Yen Lo, et al. 2023. Segment anything. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), 4015\u20134026."},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2012.6467022"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2810539"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110972"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cja.2023.12.009"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3390838"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01042"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3370107"},{"key":"e_1_3_1_32_2","unstructured":"Ziming Liu Yixuan Wang Sachin Vaidya Fabian Ruehle James Halverson Marin Solja\u010di\u0107 Thomas Y. Hou and Max Tegmark. 2024. KAN: Kolmogorov-Arnold networks. arXiv:2404.19756. Retrieved from https:\/\/arxiv.org\/abs\/2404.19756"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2018.10.010"},{"key":"e_1_3_1_34_2","unstructured":"Zhenliang Ni Xinghao Chen Yingjie Zhai Yehui Tang and Yunhe Wang. 2024. Context-guided spatial feature reconstruction for efficient semantic segmentation. arXiv:2405.06228. Retrieved from https:\/\/arxiv.org\/abs\/2405.06228"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3359755"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01059"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2024.3378091"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.125423"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijleo.2010.06.041"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.infrared.2013.12.022"},{"key":"e_1_3_1_41_2","first-page":"4461","volume-title":"Advances in Neural Information Processing Systems","author":"Sun Shangquan","year":"2022","unstructured":"Shangquan Sun, Wenqi Ren, Tao Wang, and Xiaochun Cao. 2022. Rethinking image restoration for object detection. In Advances in Neural Information Processing Systems. S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35, Curran Associates, Inc., 4461\u20134474. Retrieved from https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/1cac8326ce3fbe79171db9754211530c-Paper-Conference.pdf"},{"key":"e_1_3_1_42_2","first-page":"3449","volume-title":"Proceedings of the Asian Conference on Computer Vision (ACCV)","author":"Tan Junhao","year":"2024","unstructured":"Junhao Tan, Songwen Pei, Wei Qin, Bo Fu, Ximing Li, and Libo Huang. 2024. Wavelet-based mamba with Fourier adjustment for low-light image enhancement. In Proceedings of the Asian Conference on Computer Vision (ACCV), 3449\u20133464."},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3315123"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611907"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611909"},{"key":"e_1_3_1_47_2","first-page":"2654","volume-title":"Proceedings of the 37th AAAI Conference on Artificial Intelligence","author":"Wang Tao","year":"2023","unstructured":"Tao Wang, Kaihao Zhang, Tianrun Shen, Wenhan Luo, Bjorn Stenger, and Tong Lu. 2023. Ultra-high-definition low-light image enhancement: A benchmark and transformer-based method. In Proceedings of the 37th AAAI Conference on Artificial Intelligence, 2654\u20132662."},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"e_1_3_1_49_2","volume-title":"British Machine Vision Conference","author":"Wei Chen","year":"2018","unstructured":"Chen Wei, Wenjing Wang, Wenhan Yang, and Jiaying Liu. 2018. Deep retinex decomposition for low-light enhancement. In British Machine Vision Conference. British Machine Vision Association."},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3278385"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00581"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3665498"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00166"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3434531"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01719"},{"key":"e_1_3_1_56_2","unstructured":"Qingsen Yan Yixu Feng Cheng Zhang Pei Wang Peng Wu Wei Dong Jinqiu Sun and Yanning Zhang. 2024. You only need one color space: An efficient network for low-light image enhancement. arXiv:2402.05809. Retrieved from https:\/\/arxiv.org\/abs\/2402.05809"},{"key":"e_1_3_1_57_2","first-page":"6449","volume-title":"Proceedings of the 38th AAAI Conference on Artificial Intelligence","author":"Yan Shilin","year":"2024","unstructured":"Shilin Yan, Renrui Zhang, Ziyu Guo, Wenchao Chen, Wei Zhang, Hongyang Li, Yu Qiao, Hao Dong, Zhongjiang He, and Peng Gao. 2024. Referred by multi-modality: A unified temporal transformer for video object segmentation. In Proceedings of the 38th AAAI Conference on Artificial Intelligence, 6449\u20136457."},{"key":"e_1_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2023.3240087"},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3050850"},{"key":"e_1_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01130"},{"key":"e_1_3_1_61_2","first-page":"163","volume-title":"Artificial Neural Networks and Machine Learning (ICANN \u201923)","author":"Yin Xiangchen","year":"2023","unstructured":"Xiangchen Yin, Zhenda Yu, Zetao Fei, Wenjun Lv, and Xin Gao. 2023. PE-YOLO: Pyramid enhancement network for dark object detection. In Artificial Neural Networks and Machine Learning (ICANN \u201923). Springer Nature Switzerland, Cham, 163\u2013174."},{"key":"e_1_3_1_62_2","unstructured":"Xiangchen Yin Zhenda Yu Xin Gao Ran Ju Xiao Sun and Xinyu Zhang. 2023. 2023. DEFormer: DCT-driven enhancement transformer for low-light image and dark vision. arXiv:2309.06941. Retrieved from https:\/\/arxiv.org\/abs\/2309.06941"},{"key":"e_1_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"e_1_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3167175"},{"key":"e_1_3_1_65_2","unstructured":"Renhong Zhang Tianheng Cheng Shusheng Yang Haoyi Jiang Shuai Zhang Jiancheng Lyu Xin Li Xiaowen Ying Dashan Gao Wenyu Liu and Xinggang Wang. 2023. MobileInst: Video instance segmentation on the mobile. arXiv:2303.17594. Retrieved from https:\/\/arxiv.org\/abs\/2303.17594"},{"key":"e_1_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01407-x"},{"key":"e_1_3_1_67_2","unstructured":"Yuwei Zhang Yan Wu Yanming Liu and Xinyue Peng. 2024. CPA-enhancer: Chain-of-thought prompted adaptive enhancer for object detection under unknown degradations. arXiv:2403.11220. Retrieved from https:\/\/arxiv.org\/abs\/2403.11220"},{"key":"e_1_3_1_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350926"},{"key":"e_1_3_1_69_2","first-page":"1899","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Zhang Zhao","year":"2022","unstructured":"Zhao Zhang, Huan Zheng, Richang Hong, Mingliang Xu, Shuicheng Yan, and Meng Wang. 2022. Deep color consistent network for low-light image enhancement. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 1899\u20131908."},{"key":"e_1_3_1_70_2","unstructured":"Yian Zhao Wenyu Lv Shangliang Xu Jinman Wei Guanzhong Wang Qingqing Dang Yi Liu and Jie Chen. 2023. DETRs beat YOLOs on real-time object detection. arXiv:2304.08069. Retrieved from https:\/\/arxiv.org\/abs\/2304.08069"},{"key":"e_1_3_1_71_2","first-page":"204","volume-title":"Computer Vision (ECCV \u201924)","author":"Zhou Kun","year":"2025","unstructured":"Kun Zhou, Xinyu Lin, Wenbo Li, Xiaogang Xu, Yuanhao Cai, Zhonghang Liu, Xiaoguang Han, and Jiangbo Lu. 2025. Unveiling advanced frequency disentanglement paradigm for low-light image enhancement. In Computer Vision (ECCV \u201924). Ale\u0161 Leonardis, Elisa Ricci, Stefan Roth, Olga Russakovsky, Torsten Sattler, and G\u00fcl Varol (Eds.), Springer Nature Switzerland, Cham, 204\u2013221."}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3750732","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:45:11Z","timestamp":1757619911000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3750732"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,11]]},"references-count":70,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2025,9,30]]}},"alternative-id":["10.1145\/3750732"],"URL":"https:\/\/doi.org\/10.1145\/3750732","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"type":"print","value":"1551-6857"},{"type":"electronic","value":"1551-6865"}],"subject":[],"published":{"date-parts":[[2025,9,11]]},"assertion":[{"value":"2025-01-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-15","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}