{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T11:24:02Z","timestamp":1774524242103,"version":"3.50.1"},"reference-count":91,"publisher":"Association for Computing Machinery (ACM)","issue":"8","license":[{"start":{"date-parts":[[2024,6,29]],"date-time":"2024-06-29T00:00:00Z","timestamp":1719619200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62071155 and 92270116"],"award-info":[{"award-number":["62071155 and 92270116"]}],"id":[{"id":"10.13039\/501100001809","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":[[2024,8,31]]},"abstract":"<jats:p>Images captured under low-light conditions suffer from several combined degradation factors, including low brightness, low contrast, noise, and color bias. Many learning-based techniques attempt to learn the low-to-clear mapping between low-light and normal-light images. However, they often fall short when applied to low-light images taken in wide-contrast scenes because uneven illumination brings illumination-varying noise and the enhanced images are easily over-saturated in highlight areas. In this article, we present a novel two-stage method to tackle the problem of uneven illumination distribution in low-light images. Under the assumption that noise varies with illumination, we design an illumination-aware transformer network for the first stage of image restoration. In this stage, we introduce the Illumination-aware Attention Block featured with Illumination-aware Multi-head Self-attention, which incorporates different scales of illumination features to guide the attention module, thereby enhancing the denoising and reconstruction capabilities of the restoration network. In the second stage, we innovatively introduce a cubic auto-knee curve transfer with a global parameter predictor to alleviate the over-exposure caused by uneven illumination. We also adopt a white balance correction module to address color bias issues at this stage. Extensive experiments on various benchmarks demonstrate the advantages of our method over state-of-the-art methods qualitatively and quantitatively.<\/jats:p>","DOI":"10.1145\/3664653","type":"journal-article","created":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T11:13:59Z","timestamp":1715771639000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Illumination-Aware Low-Light Image Enhancement with Transformer and Auto-Knee Curve"],"prefix":"10.1145","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2510-0585","authenticated-orcid":false,"given":"Jinwang","family":"Pan","sequence":"first","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8857-1785","authenticated-orcid":false,"given":"Xianming","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3449-6537","authenticated-orcid":false,"given":"Yuanchao","family":"Bai","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0874-2175","authenticated-orcid":false,"given":"Deming","family":"Zhai","sequence":"additional","affiliation":[{"name":"Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5694-505X","authenticated-orcid":false,"given":"Junjun","family":"Jiang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3434-9967","authenticated-orcid":false,"given":"Debin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}]}],"member":"320","published-online":{"date-parts":[[2024,6,29]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01149"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2157513"},{"key":"e_1_3_3_4_2","article-title":"HDR imaging with spatially varying signal-to-noise ratios","author":"Chi Yiheng","year":"2023","unstructured":"Yiheng Chi, Xingguang Zhang, and Stanley H. Chan. 2023. HDR imaging with spatially varying signal-to-noise ratios. Retrieved from https:\/\/arXiv:2303.17253","journal-title":"R"},{"key":"e_1_3_3_5_2","unstructured":"Sony Corporation. 2015. Adjusting contrast (Black Level\/Black Gamma\/Knee). Retrieved from https:\/\/helpguide.sony.net\/di\/pp\/v1\/en\/contents\/TP0000909110.html"},{"key":"e_1_3_3_6_2","volume-title":"Proceedings of the 33rd British Machine Vision Conference (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 (BMVC\u201922). BMVA Press."},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00255"},{"key":"e_1_3_3_8_2","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly et\u00a0al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. Retrieved from https:\/\/arXiv:2010.11929","journal-title":"R"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413757"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803197"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.304"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3564607"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00185"},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3495258"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01667-9"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2639450"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3498341"},{"issue":"6","key":"e_1_3_3_18_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3618373","article-title":"Low-light image enhancement with wavelet-based diffusion models","volume":"42","author":"Jiang Hai","year":"2023","unstructured":"Hai Jiang, Ao Luo, Haoqiang Fan, Songchen Han, and Shuaicheng Liu. 2023. Low-light image enhancement with wavelet-based diffusion models. ACM Trans. Graph. 42, 6 (2023), 1\u201314.","journal-title":"ACM Trans. Graph."},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2024.3369321"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3051462"},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/83.597272"},{"key":"e_1_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/83.557356"},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_21"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2002.1010085"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022314423998"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3233989"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1364\/JOSA.61.000001"},{"key":"e_1_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2284059"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01042"},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01115"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.06.008"},{"key":"e_1_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01466-8"},{"key":"e_1_3_3_33_2","doi-asserted-by":"crossref","unstructured":"Chao Ma Chih-Yuan Yang Xiaokang Yang and Ming-Hsuan Yang. 2017. Learning a no-reference quality metric for single-image super-rolution. Comput. Vision Image Understand 158 (2017) 1\u201316.","DOI":"10.1016\/j.cviu.2016.12.009"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2442920"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00555"},{"key":"e_1_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/PG.2007.17"},{"key":"e_1_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"e_1_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"e_1_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE.2005.1429795"},{"key":"e_1_3_3_40_2","article-title":"Nod: Taking a closer look at detection under extreme low-light conditions with night object detection dataset","author":"Morawski Igor","year":"2021","unstructured":"Igor Morawski, Yu-An Chen, Yu-Sheng Lin, and Winston H. Hsu. 2021. Nod: Taking a closer look at detection under extreme low-light conditions with night object detection dataset. Retrieved from https:\/\/arXiv:2110.10364","journal-title":"R"},{"key":"e_1_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00625"},{"key":"e_1_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548135"},{"key":"e_1_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2017.014847"},{"key":"e_1_3_3_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0734-189X(87)80186-X"},{"key":"e_1_3_3_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/VBC.1990.109340"},{"key":"e_1_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2910412"},{"key":"e_1_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.881959"},{"key":"e_1_3_3_49_2","doi-asserted-by":"crossref","unstructured":"Kankanala Srinivas and Ashish Kumar Bhandari. 2023. Context-based novel histogram bin stretching algorithm for automatic contrast enhancement. ACM Trans. Multimedia Comput. Commun. Appl. 19 6 Article 204 (2023) 1\u201322.","DOI":"10.1145\/3597303"},{"key":"e_1_3_3_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2017.8305143"},{"key":"e_1_3_3_51_2","article-title":"Attention is all you need","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Adv. Neural Info. Process. Syst. 30 (2017).","journal-title":"Adv. Neural Info. Process. Syst."},{"key":"e_1_3_3_52_2","article-title":"Challenging Dataset for Enhancement","author":"Vonikakis Vasileios","year":"2021","unstructured":"Vasileios Vonikakis. 2021. Challenging Dataset for Enhancement. Retrieved November, 10, 2022 from https:\/\/sites.google.com\/site\/vonikakis\/datasets\/challenging-dataset-for-enhancement","journal-title":"R"},{"key":"e_1_3_3_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2005.1405691"},{"key":"e_1_3_3_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611909"},{"key":"e_1_3_3_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3008396"},{"key":"e_1_3_3_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00701"},{"key":"e_1_3_3_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2261309"},{"key":"e_1_3_3_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2261309"},{"key":"e_1_3_3_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00118"},{"key":"e_1_3_3_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547991"},{"key":"e_1_3_3_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01593"},{"key":"e_1_3_3_62_2","doi-asserted-by":"crossref","unstructured":"Xiao Wang Jun Chen Zheng Wang Wu Liu Shin\u2019ichi Satoh Chao Liang and Chia-Wen Lin. 2021. When pedestrian detection meets nighttime surveillance: a new benchmark. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (Yokohama Yokohama Japan) (IJCAI\u201920). Article 71 (2021) 7 Pages.","DOI":"10.24963\/ijcai.2020\/71"},{"key":"e_1_3_3_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01207"},{"key":"e_1_3_3_64_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20162"},{"key":"e_1_3_3_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01143"},{"key":"e_1_3_3_66_2","volume-title":"Proceedings of the 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 Proceedings of the British Machine Vision Conference."},{"key":"e_1_3_3_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00283"},{"issue":"11","key":"e_1_3_3_68_2","first-page":"8520","article-title":"Physics-based noise modeling for extreme low-light photography","volume":"44","author":"Wei Kaixuan","year":"2021","unstructured":"Kaixuan Wei, Ying Fu, Yinqiang Zheng, and Jiaolong Yang. 2021. Physics-based noise modeling for extreme low-light photography. IEEE Trans. Pattern Anal. Mach. Intell. 44, 11 (2021), 8520\u20138537.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"e_1_3_3_69_2","doi-asserted-by":"crossref","unstructured":"Kangle Wu Jun Huang Yong Ma Fan Fan and Jiayi Ma. 2024. Cycle-retinex: Unpaired low-light image enhancement via retinex-inline cyclegan. IEEE Trans. Multimedia 26 (2024) 1213\u20131228.","DOI":"10.1109\/TMM.2023.3278385"},{"key":"e_1_3_3_70_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00581"},{"key":"e_1_3_3_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00235"},{"key":"e_1_3_3_72_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01719"},{"key":"e_1_3_3_73_2","unstructured":"Jia Yan Jie Li and Xin Fu. 2019. No-reference quality assessment of contrast-distorted images using contrast enhancement. Retrieved from https:\/\/arXiv:1904.08879"},{"key":"e_1_3_3_74_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01187"},{"key":"e_1_3_3_75_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00313"},{"key":"e_1_3_3_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01130"},{"key":"e_1_3_3_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612145"},{"key":"e_1_3_3_78_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3167175"},{"key":"e_1_3_3_79_2","doi-asserted-by":"publisher","DOI":"10.1145\/3457905"},{"key":"e_1_3_3_80_2","doi-asserted-by":"crossref","unstructured":"Kaibing Zhang Cheng Yuan Jie Li Xinbo Gao and Minqi Li. 2023. Multi-branch and progressive network for low-light image enhancement. IEEE Trans. Image Process 32 (2023) 2295\u20132308.","DOI":"10.1109\/TIP.2023.3266171"},{"key":"e_1_3_3_81_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413951"},{"key":"e_1_3_3_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_3_83_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01407-x"},{"key":"e_1_3_3_84_2","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350926"},{"key":"e_1_3_3_85_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00194"},{"key":"e_1_3_3_86_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01154"},{"key":"e_1_3_3_87_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/199"},{"key":"e_1_3_3_88_2","doi-asserted-by":"publisher","DOI":"10.1145\/3590965"},{"key":"e_1_3_3_89_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"e_1_3_3_90_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7013"},{"key":"e_1_3_3_91_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2987874"},{"key":"e_1_3_3_92_2","doi-asserted-by":"crossref","unstructured":"Wenbin Zou Hongxia Gao Tian Ye Liang Chen Weipeng Yang Shasha Huang Hongsheng Chen and Sixiang Chen. 2023. VQCNIR: Clearer night image restoration with vector-quantized codebook. Retrieved from https:\/\/arXiv:2312.08606","DOI":"10.1609\/aaai.v38i7.28623"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664653","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664653","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:29Z","timestamp":1750295849000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664653"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,29]]},"references-count":91,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2024,8,31]]}},"alternative-id":["10.1145\/3664653"],"URL":"https:\/\/doi.org\/10.1145\/3664653","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,29]]},"assertion":[{"value":"2023-12-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-28","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}