TY - GEN
T1 - AIM 2019 challenge on real-world image super-resolution
T2 - 17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019
AU - Lugmayr, Andreas
AU - Danelljan, Martin
AU - Timofte, Radu
AU - Fritsche, Manuel
AU - Gu, Shuhang
AU - Purohit, Kuldeep
AU - Kandula, Praveen
AU - Suin, Maitreya
AU - Rajagopalan, A. N.
AU - Joon, Nam Hyung
AU - Won, Yu Seung
AU - Kim, Guisik
AU - Kwon, Dokyeong
AU - Hsu, Chih-Chung
AU - Lin, Chia Hsiang
AU - Huang, Yuanfei
AU - Sun, Xiaopeng
AU - Lu, Wen
AU - Li, Jie
AU - Gao, Xinbo
AU - Bell-Kligler, Sefi
PY - 2019/10
Y1 - 2019/10
N2 - This paper reviews the AIM 2019 challenge on real world super-resolution. It focuses on the participating methods and final results. The challenge addresses the real world setting, where paired true high and low-resolution images are unavailable. For training, only one set of source input images is therefore provided in the challenge. In Track 1: Source Domain the aim is to super-resolve such images while preserving the low level image characteristics of the source input domain. In Track 2: Target Domain a set of high-quality images is also provided for training, that defines the output domain and desired quality of the super-resolved images. To allow for quantitative evaluation, the source input images in both tracks are constructed using artificial, but realistic, image degradations. The challenge is the first of its kind, aiming to advance the state-of-the-art and provide a standard benchmark for this newly emerging task. In total 7 teams competed in the final testing phase, demonstrating new and innovative solutions to the problem.
AB - This paper reviews the AIM 2019 challenge on real world super-resolution. It focuses on the participating methods and final results. The challenge addresses the real world setting, where paired true high and low-resolution images are unavailable. For training, only one set of source input images is therefore provided in the challenge. In Track 1: Source Domain the aim is to super-resolve such images while preserving the low level image characteristics of the source input domain. In Track 2: Target Domain a set of high-quality images is also provided for training, that defines the output domain and desired quality of the super-resolved images. To allow for quantitative evaluation, the source input images in both tracks are constructed using artificial, but realistic, image degradations. The challenge is the first of its kind, aiming to advance the state-of-the-art and provide a standard benchmark for this newly emerging task. In total 7 teams competed in the final testing phase, demonstrating new and innovative solutions to the problem.
UR - http://www.scopus.com/inward/record.url?scp=85082469433&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85082469433&partnerID=8YFLogxK
U2 - 10.1109/ICCVW.2019.00442
DO - 10.1109/ICCVW.2019.00442
M3 - Conference contribution
T3 - Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019
SP - 3575
EP - 3583
BT - Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 27 October 2019 through 28 October 2019
ER -