ML Anthology

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

Andreas Lugmayr, Nam Hyung Joon, Yu Seung Won, Guisik Kim, Dokyeong Kwon, Chih-Chung Hsu, Chia-Hsiang Lin, Yuanfei Huang, Xiaopeng Sun, Wen Lu, Jie Li, Martin Danelljan, Xinbo Gao, Sefi Bell-Kligler, Assaf Shocher, Michal Irani, Radu Timofte, Manuel Fritsche, Shuhang Gu, Kuldeep Purohit, Praveen Kandula, Maitreya Suin, A. N. Rajagopalan
ICCVW 2019 pp. 3575-3583
doi:10.1109/ICCVW.2019.00442 /iccvw/2019/lugmayr2019iccvw-aim/

Abstract

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.

PDF ICCVW Semantic Scholar

Cite

Text

Lugmayr et al. "AIM 2019 Challenge on Real-World Image Super-Resolution: Methods and Results." IEEE/CVF International Conference on Computer Vision Workshops, 2019. doi:10.1109/ICCVW.2019.00442

Markdown

[Lugmayr et al. "AIM 2019 Challenge on Real-World Image Super-Resolution: Methods and Results." IEEE/CVF International Conference on Computer Vision Workshops, 2019.](https://mlanthology.org/iccvw/2019/lugmayr2019iccvw-aim/) doi:10.1109/ICCVW.2019.00442

BibTeX

@inproceedings{lugmayr2019iccvw-aim,
  title     = {{AIM 2019 Challenge on Real-World Image Super-Resolution: Methods and Results}},
  author    = {Lugmayr, Andreas and Joon, Nam Hyung and Won, Yu Seung and Kim, Guisik and Kwon, Dokyeong and Hsu, Chih-Chung and Lin, Chia-Hsiang and Huang, Yuanfei and Sun, Xiaopeng and Lu, Wen and Li, Jie and Danelljan, Martin and Gao, Xinbo and Bell-Kligler, Sefi and Shocher, Assaf and Irani, Michal and Timofte, Radu and Fritsche, Manuel and Gu, Shuhang and Purohit, Kuldeep and Kandula, Praveen and Suin, Maitreya and Rajagopalan, A. N.},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2019},
  pages     = {3575-3583},
  doi       = {10.1109/ICCVW.2019.00442},
  url       = {https://mlanthology.org/iccvw/2019/lugmayr2019iccvw-aim/}
}