NTIRE 2023 Video Colorization Challenge

Kang, Xiaoyang; Lin, Xianhui; Zhang, Kai; Hui, Zheng; Xiang, Wangmeng; He, Jun-Yan; Li, Xiaoming; Ren, Peiran; Xie, Xuansong; Timofte, Radu; Yang, Yixin; Pan, Jinshan; Peng, Zhongzheng; Zhang, Qiyan; Dong, Jiangxin; Tang, Jinhui; Li, Jinjing; Lin, Chichen; Li, Qipei; Liang, Qirong; Gang, Ruipeng; Liu, Xiaofeng; Feng, Shuang; Liu, Shuai; Wang, Hao; Feng, Chaoyu; Bai, Furui; Zhang, Yuqian; Shao, Guangqi; Wang, Xiaotao; Lei, Lei; Chen, Siqi; Zhang, Yu; Xu, Hanning; Liu, Zheyuan; Zhang, Zhao; Luo, Yan; Zuo, Zhichao

Xiaoyang Kang, Xianhui Lin, Kai Zhang, Zheng Hui, Wangmeng Xiang, Jun-Yan He, Xiaoming Li, Peiran Ren, Xuansong Xie, Radu Timofte, Yixin Yang, Jinshan Pan, Zhongzheng Peng, Qiyan Zhang, Jiangxin Dong, Jinhui Tang, Jinjing Li, Chichen Lin, Qipei Li, Qirong Liang, Ruipeng Gang, Xiaofeng Liu, Shuang Feng, Shuai Liu, Hao Wang, Chaoyu Feng, Furui Bai, Yuqian Zhang, Guangqi Shao, Xiaotao Wang, Lei Lei, Siqi Chen, Yu Zhang, Hanning Xu, Zheyuan Liu, Zhao Zhang, Yan Luo, Zhichao Zuo; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2023, pp. 1570-1581

Abstract

This paper reviews the video colorization challenge on the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2023. The target of this challenge is converting grayscale videos into color videos with better colorization performance and temporal consistency. The challenge consists of two tracks. For Track 1, the goal is achieving the best FID (Frechet Inception Distance) while being constrained to maintain or improve over the baseline method in terms of the temporal-consistency metric. The Color Distribution Consistency (CDC) index is used as the temporal consistency evaluation metric in this challenge. For Track 2, the target is to obtain a solution with the best CDC result while being constrained to maintain or improve over the baseline method in terms of FID. We use DeOldify-video as the baseline method for two tracks. For the final testing phase of both tracks, six teams submitted fact sheets and executable code of their solutions. This report brings together descriptions and discussions of all these solutions.

Related Material

[pdf]

[bibtex]

@InProceedings{Kang_2023_CVPR, author = {Kang, Xiaoyang and Lin, Xianhui and Zhang, Kai and Hui, Zheng and Xiang, Wangmeng and He, Jun-Yan and Li, Xiaoming and Ren, Peiran and Xie, Xuansong and Timofte, Radu and Yang, Yixin and Pan, Jinshan and Peng, Zhongzheng and Zhang, Qiyan and Dong, Jiangxin and Tang, Jinhui and Li, Jinjing and Lin, Chichen and Li, Qipei and Liang, Qirong and Gang, Ruipeng and Liu, Xiaofeng and Feng, Shuang and Liu, Shuai and Wang, Hao and Feng, Chaoyu and Bai, Furui and Zhang, Yuqian and Shao, Guangqi and Wang, Xiaotao and Lei, Lei and Chen, Siqi and Zhang, Yu and Xu, Hanning and Liu, Zheyuan and Zhang, Zhao and Luo, Yan and Zuo, Zhichao}, title = {NTIRE 2023 Video Colorization Challenge}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {1570-1581} }