Fr\'echet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videos

TL;DR

This paper introduces FVMD, a new metric based on motion features for evaluating temporal and motion consistency in generated videos, aligning well with human perception.

Contribution

We propose FVMD, a novel motion-based metric for assessing video quality, addressing the gap in evaluating temporal and motion consistency in video generation.

Findings

FVMD effectively detects temporal noise in videos.

FVMD aligns better with human perception than existing metrics.

Motion features improve video quality assessment models.

Abstract

Significant advancements have been made in video generative models recently. Unlike image generation, video generation presents greater challenges, requiring not only generating high-quality frames but also ensuring temporal consistency across these frames. Despite the impressive progress, research on metrics for evaluating the quality of generated videos, especially concerning temporal and motion consistency, remains underexplored. To bridge this research gap, we propose Fr\'echet Video Motion Distance (FVMD) metric, which focuses on evaluating motion consistency in video generation. Specifically, we design explicit motion features based on key point tracking, and then measure the similarity between these features via the Fr\'echet distance. We conduct sensitivity analysis by injecting noise into real videos to verify the effectiveness of FVMD. Further, we carry out a large-scale human study, demonstrating that our metric effectively detects temporal noise and aligns better with human perceptions of generated video quality than existing metrics. Additionally, our motion features can consistently improve the performance of Video Quality Assessment (VQA) models, indicating that our approach is also applicable to unary video quality evaluation. Code is available at https://github.com/ljh0v0/FMD-frechet-motion-distance.