NTIRE 2019 Challenge on Image Colorization: Report
Abstract
This paper reviews the NTIRE challenge on image colorization (estimating color information from the corresponding gray image) with focus on proposed solutions and results. It is the first challenge of its kind. The challenge had 2 tracks. Track 1 takes a single gray image as input. In Track 2, in addition to the gray input image, some color seeds (randomly samples from the latent color image) are also provided for guiding the colorization process. The operators were learnable through provided pairs of gray and color training images. The tracks had 188 registered participants, and 8 teams competed in the final testing phase.
Cite
Text
Gu et al. "NTIRE 2019 Challenge on Image Colorization: Report." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019. doi:10.1109/CVPRW.2019.00276Markdown
[Gu et al. "NTIRE 2019 Challenge on Image Colorization: Report." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.](https://mlanthology.org/cvprw/2019/gu2019cvprw-ntire/) doi:10.1109/CVPRW.2019.00276BibTeX
@inproceedings{gu2019cvprw-ntire,
title = {{NTIRE 2019 Challenge on Image Colorization: Report}},
author = {Gu, Shuhang and Timofte, Radu and Zhang, Richard and Suin, Maitreya and Purohit, Kuldeep and Rajagopalan, A. N. and Narayanan, S. Athi and Pinjari, Jameer Babu and Xiong, Zhiwei and Shi, Zhan and Chen, Chang and Liu, Dong and Sharma, Manoj and Makwana, Megh and Badhwar, Anuj and Singh, Ajay Pratap and Upadhyay, Avinash and Trivedi, Akkshita and Saini, Anil K. and Chaudhury, Santanu and Sharma, Prasen Kumar and Jain, Priyankar and Sur, Arijit and Özbulak, Gökhan},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2019},
pages = {2233-2240},
doi = {10.1109/CVPRW.2019.00276},
url = {https://mlanthology.org/cvprw/2019/gu2019cvprw-ntire/}
}