NTIRE 2024 Quality Assessment of AI-Generated Content Challenge
Abstract
This paper reports on the NTIRE 2024 Quality Assessment of AI-Generated Content Challenge, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2024. This challenge is to address a major challenge in the field of image and video processing, namely, Image Quality Assessment (IQA) and Video Quality Assessment (VQA) for AI-Generated Content (AIGC). The challenge is divided into the image track and the video track. The image track uses the AIGIQA-20K, which contains 20,000 AI-Generated Images (AIGIs) generated by 15 popular generative models. The image track has a total of 318 registered participants. A total of 1,646 submissions are received in the development phase, and 221 submissions are received in the test phase. Finally, 16 participating teams submitted their models and fact sheets. The video track uses the T2VQA-DB, which contains 10,000 AI-Generated Videos (AIGVs) generated by 9 popular Text-to-Video (T2V) models. A total of 196 participants have registered in the video track. A total of 991 submissions are received in the development phase, and 185 submissions are received in the test phase. Finally, 12 participating teams submitted their models and fact sheets. Some methods have achieved better results than baseline methods, and the winning methods in both tracks have demonstrated superior prediction performance on AIGC.
Cite
@article{arxiv.2404.16687,
title = {NTIRE 2024 Quality Assessment of AI-Generated Content Challenge},
author = {Xiaohong Liu and Xiongkuo Min and Guangtao Zhai and Chunyi Li and Tengchuan Kou and Wei Sun and Haoning Wu and Yixuan Gao and Yuqin Cao and Zicheng Zhang and Xiele Wu and Radu Timofte and Fei Peng and Huiyuan Fu and Anlong Ming and Chuanming Wang and Huadong Ma and Shuai He and Zifei Dou and Shu Chen and Huacong Zhang and Haiyi Xie and Chengwei Wang and Baoying Chen and Jishen Zeng and Jianquan Yang and Weigang Wang and Xi Fang and Xiaoxin Lv and Jun Yan and Tianwu Zhi and Yabin Zhang and Yaohui Li and Yang Li and Jingwen Xu and Jianzhao Liu and Yiting Liao and Junlin Li and Zihao Yu and Yiting Lu and Xin Li and Hossein Motamednia and S. Farhad Hosseini-Benvidi and Fengbin Guan and Ahmad Mahmoudi-Aznaveh and Azadeh Mansouri and Ganzorig Gankhuyag and Kihwan Yoon and Yifang Xu and Haotian Fan and Fangyuan Kong and Shiling Zhao and Weifeng Dong and Haibing Yin and Li Zhu and Zhiling Wang and Bingchen Huang and Avinab Saha and Sandeep Mishra and Shashank Gupta and Rajesh Sureddi and Oindrila Saha and Luigi Celona and Simone Bianco and Paolo Napoletano and Raimondo Schettini and Junfeng Yang and Jing Fu and Wei Zhang and Wenzhi Cao and Limei Liu and Han Peng and Weijun Yuan and Zhan Li and Yihang Cheng and Yifan Deng and Haohui Li and Bowen Qu and Yao Li and Shuqing Luo and Shunzhou Wang and Wei Gao and Zihao Lu and Marcos V. Conde and Xinrui Wang and Zhibo Chen and Ruling Liao and Yan Ye and Qiulin Wang and Bing Li and Zhaokun Zhou and Miao Geng and Rui Chen and Xin Tao and Xiaoyu Liang and Shangkun Sun and Xingyuan Ma and Jiaze Li and Mengduo Yang and Haoran Xu and Jie Zhou and Shiding Zhu and Bohan Yu and Pengfei Chen and Xinrui Xu and Jiabin Shen and Zhichao Duan and Erfan Asadi and Jiahe Liu and Qi Yan and Youran Qu and Xiaohui Zeng and Lele Wang and Renjie Liao},
journal= {arXiv preprint arXiv:2404.16687},
year = {2024}
}