视频大模型

T2VEval: Benchmark Dataset and Objective Evaluation Method for T2V-generated Videos

T2VEval: 用于T2V生成视频的基准数据集和客观评估方法

Zelu Qi, Ping Shi, Shuqi Wang, Chaoyang Zhang, Fei Zhao, Zefeng Ying, Da Pan, Xi Yang, Zheqi He, Teng Dai

机构 * School of Information and Communication Engineering, Communication University of China, No.1 East Street, Dingfuzhuang, Chaoyang District, Beijing, China（信息与通信工程学院，中国传媒大学） ； Beijing Academy of Artificial Intelligence, No.150 Chengfu Road, Haidian District, Beijing, China（北京人工智能研究院） 纠错

专题命中 视频数据与评测 ：video generation(abstract)；text-to-video(abstract)；分类 cs.CV

AI总结 T2VEval提出了一种多分支融合方案，通过多维评估指标对T2V生成视频进行客观质量评估，提升视频生成模型的优化效果。

Comments This paper has been accepted by DISPLAYS