文献类型：期刊文献

英文题名：NTIRE 2025 Challenge on Low Light Image Enhancement: Methods and Results

作者：Liu, Xiaoning[1]; Wu, Zongwei[2]; Vasluianu, Florin[2]; Yan, Hailong[1]; Ren, Bin[4]; Zhang, Yulun[3]; Gu, Shuhang[1]; Zhang, Le[1]; Zhu, Ce[1]; Timofte, Radu[2]; Shi, Kangbiao[5]; Feng, Yixu[5]; Hu, Tao[5]; Cao, Yu[6]; Wu, Peng[5]; Liang, Yijin[7]; Zhang, Yanning[5]; Yan, Qingsen[5]; Zhou, Han[8]; Dong, Wei[8]; Min, Yan[8]; Kishawy, Mohab[8]; Chen, Jun[8]; Yu, Pengpeng[9,10]; Park, Anjin[11]; Lee, Seung-Soo[12]; Park, Young-Joon[12]; Hu, Zixiao[25]; Liu, Junyv[25]; Zhang, Huilin[25]; Zhang, Jun[25]; Wan, Fei[13,14]; Xu, Bingxin[13,14]; Liu, Hongzhe[48]; Xu, Cheng[13,14]; Pan, Weiguo[48]; Dai, Songyin[48]; Yi, Xunpeng[15]; Yan, Qinglong[15]; Zhang, Yibing[15]; Ma, Jiayi[15]; Hu, Changhui[16]; Hu, Kerui[16]; Jing, Donghang[16]; Chen, Tiesheng[16]; Jin, Zhi[17,18]; Wu, Hongjun[17]; Huang, Biao[17]; Ling, Haitao[17]; Wu, Jiahao[17]; Zhan, Dandan[17]; Rao, G. Gyaneshwar[20,21]; Aralikatti, Vijayalaxmi Ashok[19,21]; Akalwadi, Nikhil[19,21]; Tabib, Ramesh Ashok[20,21]; Mudenagudi, Uma[20,21]; Lin, Ruirui[22]; Huang, Guoxi[22]; Anantrasirichai, Nantheera[22]; Yang, Qirui[23]; Brateanu, Alexandru[24]; Orhei, Ciprian[25]; Ancuti, Cosmin[25]; Feijoo, Daniel[26]; Benito, Juan C.[26]; García, álvaro[26]; Conde, Marcos V.[2,26]; Qin, Yang[27]; Yang, Yufeng[28]; Huang, Jiancheng[29]; Zhou, Donghao[30]; Chen, Shifeng[28]; Balmez, Raul[24]; Ancuti, Cosmin[25]; Orhei, Ciprian[25]; Ali, Anas M.[31]; Benjdira, Bilel[31]; Boulila, Wadii[31]; Mao, Tianyi[32]; Zheng, Huan[33]; Wei, Yanyan[32]; Tang, Shengeng[32]; Guo, Dan[32]; Zhang, Zhao[32]; Nathan, Sabari[34]; Uma, K.[35]; Sasithradevi, A.[36]; Bama, B. Sathya[37]; Roomi, S. Mohamed Mansoor[37]; Li, Ao[1]; Zhang, Xiangtao[1]; Liu, Zhe[1]; Tang, Yijie[38]; Tang, Jialong[39]; Fu, Zhicheng[40]; Chen, Gong[40]; Nasti, Joe[40]; Nicholson, John[40]; Xiao, Zeyu[41]; Li, Zhuoyuan[42]; Kulkarni, Ashutosh[43]; Patil, Prashant W.[44]; Vipparthi, Santosh Kumar[43]; Murala, Subrahmanyam[45]; Liu, Duan[46]; Li, Weile[46]; Lu, Hangyuan[46]; Liu, Rixian[46]; Wang, Tengfeng[47]; Liang, Jinxing[48]; Yu, Chenxin[48]

第一作者：Liu, Xiaoning

机构：[1] University of Electronic Science and Technology of China, China; [2] Computer Vision Lab, University of Würzburg, Germany; [3] Shanghai Jiao Tong University, China; [4] University of Trento, Italy; [5] School of Computer Science, Northwestern Polytechnical University, China; [6] Xi’an Institute of Optics and Precision Mechanics of CAS, China; [7] Shanghai Institute of Satellite Engineering, Shanghai, 201109, China; [8] McMaster University, Canada; [9] School of Electronics and Communication Engineering, Sun Yat-sen University, China; [10] Pengcheng Laboratory, China; [11] Intelligent Technology Research Center, Korea Photonics Technology Institute, Korea, Republic of; [12] Doowon Electronics and Telecom Co., LTD., Korea, Republic of; [13] Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, China; [14] College of Robotics, Beijing Union University, Beijing, China; [15] Electronic Information School, Wuhan University, China; [16] College of Automation, College of Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing, 210023, China; [17] School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Guangdong, Shenzhen, 518107, China; [18] Guangdong Provincial Key Laboratory of Fire Science and Intelligent Emergency Technology, Guangzhou, 510006, China; [19] School of Computer Science and Engineering, KLE Technological University, India; [20] School of Electronics and Communication Engineering, KLE Technological University, India; [21] Center of Excellence in Visual Intelligence [CEVI], KLE Technological University, India; [22] Visual Information Laboratory, University of Bristol, Bristol, United Kingdom; [23] School of Electrical and Information Engineering, Tianjin University, China; [24] University of Manchester, Manchester, United Kingdom; [25] Polytechnic University Timisoara, Timisoara, Romania; [26] Cidaut AI, Spain; [27] Nanjing University of Information Science and Technology, China; [28] Southern University of Science and Technology, Shenzhen, China; [29] Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, China; [30] The Chinese University of Hong Kong, Hong Kong; [31] Robotics and Internet-of-Things Laboratory, Prince Sultan University, Riyadh, Saudi Arabia; [32] School of Computer and Information, Hefei University of Technology, China; [33] University of Macau, China; [34] Couger, Japan; [35] Sasi Institute of Technology & Engineering, India; [36] Vellore Institute of Technology, India; [37] Thiagarajar college of engineering, India; [38] Chongqing University, China; [39] Zhejiang University, China; [40] Lenovo Research, China; [41] National University of Singapore, Singapore; [42] University of Science and Technology of China, China; [43] CVPR Lab, Indian Institute of Technology, Ropar, India; [44] MFSDSAI, Indian Institute of Technology, Guwahati, India; [45] CVPR Lab, School of Computer Science and Statistics, Trinity College Dublin, Dublin, Ireland; [46] Infomation Engineering College, Jinhua University of Vocational Technology, China; [47] School of Software Engineering, Chongqing University of Posts and Telecommunications, China; [48] School of Computer Science and Artificial Intelligence, Wuhan Textile University, China

第一机构：University of Electronic Science and Technology of China, China

年份：2025

外文期刊名：arXiv

收录：EI(收录号：20250559459)

语种：英文

外文关键词：Image enhancement

摘要：This paper presents a comprehensive review of the NTIRE 2025 Low-Light Image Enhancement (LLIE) Challenge, highlighting the proposed solutions and final outcomes. The objective of the challenge is to identify effective networks capable of producing brighter, clearer, and visually compelling images under diverse and challenging conditions. A remarkable total of 762 participants registered for the competition, with 28 teams ultimately submitting valid entries. This paper thoroughly evaluates the state-of-the-art advancements in LLIE, showcasing the significant progress. Copyright ? 2025, The Authors. All rights reserved.