VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation

The recent years have witnessed great advances in video generation. However, the development of automatic video metrics is lagging significantly behind. None of the existing metrics are able to provide reliable scores over generated videos. The main barrier is the lack of largescale human-annotated datasets. In this paper, we release VIDEOFEEDBACK, the first largescale dataset containing human-provided multiaspect score over 37.6K synthesized videos from 11 existing video generative models. We train VIDEOSCORE (initialized from Mantis) based on VIDEOFEEDBACK to enable automatic video quality assessment. Experiments show that the Spearman correlation between VIDEOSCORE and humans can reach 77.1 on VIDEOFEEDBACK-test, beating the prior best metrics by about 50 points. Further results on other held-out EvalCrafter, GenAI-Bench, and VBench show that VIDEOSCORE has consistently much higher correlation with human judges than other metrics. Due to these results, we believe VIDEOSCORE can serve as a great proxy for human raters to (1) rate different video models to track progress (2) simulate fine-grained human feedback in Reinforcement Learning with Human Feedback (RLHF) to improve current video generation models.