NTIRE 2019 Challenge on Real Image Super-Resolution: Methods and Results

被引：58

作者：

Cai, Jianrui ^{[1
]}

Gu, Shuhang ^{[2
]}

Timofte, Radu ^{[2
]}

Zhang, Lei ^{[1
,14
]}

Liu, Xiao ^{[3
]}

Ding, Yukang ^{[3
]}

He, Dongliang ^{[3
]}

Li, Chao ^{[3
]}

Fu, Yi ^{[3
]}

Wen, Shilei ^{[3
]}

Feng, Ruicheng ^{[4
]}

Gu, Jinjin ^{[5
]}

Qiao, Yu ^{[4
,6
]}

Dong, Chao ^{[4
]}

Park, Dongwon

Chun, Se Young ^{[7
]}

Yoon, Sanghoon ^{[8
]}

Kwak, Junhyung ^{[9
]}

Son, Donghee ^{[10
]}

Zamir, Syed Waqas

Arora, Aditya ^{[11
]}

Khan, Salman ^{[11
]}

Khan, Fahad Shahbaz ^{[11
]}

Shao, Ling ^{[11
]}

Wei, Zhengping

Liu, Lei ^{[12
]}

Cai, Hong ^{[12
]}

Li, Darui ^{[12
]}

Gao, Fujie ^{[12
]}

Hui, Zheng ^{[13
]}

Wang, Xiumei ^{[13
]}

Gao, Xinbo ^{[13
]}

Cheng, Guoan ^{[14
]}

Matsune, Ai ^{[14
]}

Li, Qiuyu ^{[14
]}

Zhu, Leilei ^{[14
]}

Zang, Huaijuan ^{[14
]}

Zhan, Shu

Qiu, Yajun ^{[15
]}

Wang, Ruxin ^{[15
]}

Li, Jiawei ^{[16
]}

Jing, Yongcheng ^{[17
]}

Song, Mingli ^{[17
]}

Liu, Pengju ^{[18
,19
]}

Zhang, Kai ^{[18
]}

Liu, Jingdong ^{[19
]}

Liu, Jiye ^{[18
]}

Zhang, Hongzhi ^{[18
,19
]}

Zuo, Wangmeng ^{[18
]}

Tang, Wenyi

机构：

[1] Hong Kong Polytech Univ, Hong Kong, Peoples R China

[2] Swiss Fed Inst Technol, Comp Vis Lab, Zurich, Switzerland

[3] Baidu Inc, Comp Vis Technol VIS Dept, Beijing, Peoples R China

[4] Chinese Acad Sci, Shenzhen Inst Adv Technol, SIAT SenseTime Joint Lab, Beijing, Peoples R China

[5] Chinese Univ Hong Kong, Sch Sci & Engn, Shenzhen, Peoples R China

[6] Chinese Univ Hong Kong, Hong Kong, Peoples R China

[7] Ulsan Natl Inst Sci & Technol UNIST, Ulsan, South Korea

[8] Kakao, Jeju Si, South Korea

[9] CASTIS Multimedia R&D Ctr, Seoul, South Korea

[10] NALBI Inc, Seoul, South Korea

[11] Incept Inst Artificial Intelligence, Abu Dhabi, U Arab Emirates

[12] LiveMe Inc, West Hollywood, CA USA

[13] Xidian Univ, Sch Elect Engn, Xian, Peoples R China

[14] Hefei Univ Technol, Sch Comp Sci & Informat Engn, Hefei, Peoples R China

[15] Yunnan Univ, Kunming, Yunnan, Peoples R China

[16] Alibaba Grp, Hangzhou, Peoples R China

[17] Zhejiang Univ, Coll Comp Sci & Technol, Hangzhou, Peoples R China

[18] Harbin Inst Technol, Sch Comp Sci & Technol, 92 West Da Zhi St, Harbin, Peoples R China

[19] Harbin Ultravis Technol, 6 Fuhua St, Harbin, Peoples R China

[20] East China Normal Univ ECNU, Multimedia & Comp Vis Lab, Shanghai, Peoples R China

[21] Agcy Def Dev, Seoul, South Korea

[22] BOE Technol Grp Co Ltd, Beijing, Peoples R China

[23] West Virginia Univ, Morgantown, WV 26506 USA

[24] Xidian Univ, Xian, Peoples R China

[25] Kiwi Image Technol Co Ltd, Xian, Peoples R China

[26] Zhejiang Univ, Sch Mech Engn, State Key Lab Fluid Power & Mechatron Syst, Hangzhou 310027, Peoples R China

[27] Zhejiang Univ, Sch Mech Engn, Key Lab Adv Mfg Technol Zhejiang Prov, Hangzhou 310027, Zhejiang, Peoples R China

[28] Beijing Kingsoft Cloud Technol Co Ltd, Beijing, Peoples R China

[29] Sun Yat Sen Univ, Guangzhou, Peoples R China

[30] Univ Sci & Technol China, Beijing, Peoples R China

[31] XiDian Univ, Kiwi Image Technol Co Ltd, Xian, Peoples R China

[32] Xiamen Univ, Sch Informat Sci & Engn, Xiamen, Peoples R China

[33] Hong Kong Polytech Univ, Dept Elect & Informat Engn, Hong Kong, Peoples R China

[34] Johns Hopkins Univ, Baltimore, MD 21218 USA

[35] Qualcomm Technol Inc, San Diego, CA USA

来源：

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2019) | 2019年

关键词：

D O I：

10.1109/CVPRW.2019.00274

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper reviewed the 3rd NTIRE challenge on single image super-resolution (restoration of rich details in a low resolution image) with a focus on proposed solutions and results. The challenge had 1 track, which was aimed at the real-world single image super-resolution problem with an unknown scaling factor. Participants were mapping low-resolution images captured by a DSLR camera with a shorter focal length to their high-resolution images captured at a longer focal length. With this challenge, we introduced a novel real-world super-resolution dataset (RealSR). The track had 403 registered participants, and 36 teams competed in the final testing phase. They gauge the state-of-the-art in real-world single image super-resolution.

引用

页码：2211 / 2223

页数：13

共 46 条

[21] Single-Image Super-Resolution Using Sparse Regression and Natural Image Prior [J].

Kim, Kwang In ;

Kwon, Younghee .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2010, 32 (06) :1127-1133

[22]

Kohler T., 2018, ARXIV180906420

[23] Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network [J].

Ledig, Christian ;

Theis, Lucas ;

Huszar, Ferenc ;

Caballero, Jose ;

Cunningham, Andrew ;

Acosta, Alejandro ;

Aitken, Andrew ;

Tejani, Alykhan ;

Totz, Johannes ;

Wang, Zehan ;

Shi, Wenzhe .

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :105-114

[24]

Lee S, 2019, 2019 1ST INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE IN INFORMATION AND COMMUNICATION (ICAIIC 2019), P58, DOI [10.1109/icaiic.2019.8668974, 10.1109/ICAIIC.2019.8668974]

[25] Enhanced Deep Residual Networks for Single Image Super-Resolution [J].

Lim, Bee ;

Son, Sanghyun ;

Kim, Heewon ;

Nah, Seungjun ;

Lee, Kyoung Mu .

2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2017, :1132-1140

[26]

Liu K. Z. L. L. P., 2018, COMP VIS PATT REC WO

[27] Probing dark matter particles at CEPC [J].

Liu, Zuowei ;

Xu, Yong-Heng ;

Zhang, Yu .

JOURNAL OF HIGH ENERGY PHYSICS, 2019, 2019 (06)

[28] Intelligent Mower Controlled By Single-chip-microcomputer [J].

Ma Zhenfeng ;

Yu Shanxin ;

Cheng Gong .

2018 INTERNATIONAL CONFERENCE ON BIG DATA AND ARTIFICIAL INTELLIGENCE (ICBDAI 2018), 2019, :65-69

[29]

Park D., 2019, ARXIV190310157

[30]

Park SC, 2003, IEEE SIGNAL PROC MAG, V20, P21, DOI 10.1109/MSP.2003.1203207

← 1 2 3 4 5 →