Back to Search Start Over

NTIRE 2023 Quality Assessment of Video Enhancement Challenge

Authors :
Liu, Xiaohong
Min, Xiongkuo
Sun, Wei
Zhang, Yulun
Zhang, Kai
Timofte, Radu
Zhai, Guangtao
Gao, Yixuan
Cao, Yuqin
Kou, Tengchuan
Dong, Yunlong
Jia, Ziheng
Li, Yilin
Wu, Wei
Hu, Shuming
Deng, Sibin
Xiao, Pengxiang
Chen, Ying
Li, Kai
Zhao, Kai
Yuan, Kun
Sun, Ming
Cong, Heng
Wang, Hao
Fu, Lingzhi
Zhang, Yusheng
Zhang, Rongyu
Shi, Hang
Xu, Qihang
Xiao, Longan
Ma, Zhiliang
Agarla, Mirko
Celona, Luigi
Rota, Claudio
Schettini, Raimondo
Huang, Zhiwei
Li, Yanan
Wang, Xiaotao
Lei, Lei
Liu, Hongye
Hong, Wei
Chuang, Ironhead
Lin, Allen
Guan, Drake
Chen, Iris
Lou, Kae
Huang, Willy
Tasi, Yachun
Kao, Yvonne
Fan, Haotian
Kong, Fangyuan
Zhou, Shiqi
Liu, Hao
Lai, Yu
Chen, Shanshan
Wang, Wenqi
Wu, Haoning
Chen, Chaofeng
Zhu, Chunzheng
Guo, Zekun
Zhao, Shiling
Yin, Haibing
Wang, Hongkui
Meftah, Hanene Brachemi
Fezza, Sid Ahmed
Hamidouche, Wassim
Déforges, Olivier
Shi, Tengfei
Mansouri, Azadeh
Motamednia, Hossein
Bakhtiari, Amir Hossein
Aznaveh, Ahmad Mahmoudi
Publication Year :
2023

Abstract

This paper reports on the NTIRE 2023 Quality Assessment of Video Enhancement Challenge, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2023. This challenge is to address a major challenge in the field of video processing, namely, video quality assessment (VQA) for enhanced videos. The challenge uses the VQA Dataset for Perceptual Video Enhancement (VDPVE), which has a total of 1211 enhanced videos, including 600 videos with color, brightness, and contrast enhancements, 310 videos with deblurring, and 301 deshaked videos. The challenge has a total of 167 registered participants. 61 participating teams submitted their prediction results during the development phase, with a total of 3168 submissions. A total of 176 submissions were submitted by 37 participating teams during the final testing phase. Finally, 19 participating teams submitted their models and fact sheets, and detailed the methods they used. Some methods have achieved better results than baseline methods, and the winning methods have demonstrated superior prediction performance.

Details

Language :
English
Database :
OpenAIRE
Accession number :
edsair.doi.dedup.....3ee7b491469e09101b8811238090fb4d