PEAVS: Perceptual Evaluation of Audio-Visual Synchrony Grounded in Viewers' Opinion Scores
This addresses the problem of evaluating audio-visual synchronization for researchers and practitioners in generative modeling, though it is incremental as it builds on existing evaluation frameworks.
The paper tackles the lack of quantitative metrics for audio-visual synchronization in videos by developing PEAVS, a novel automatic metric that achieves a Pearson correlation of 0.79 with human labels at the set level and shows a 50% relative gain over existing methods.
Recent advancements in audio-visual generative modeling have been propelled by progress in deep learning and the availability of data-rich benchmarks. However, the growth is not attributed solely to models and benchmarks. Universally accepted evaluation metrics also play an important role in advancing the field. While there are many metrics available to evaluate audio and visual content separately, there is a lack of metrics that offer a quantitative and interpretable measure of audio-visual synchronization for videos "in the wild". To address this gap, we first created a large scale human annotated dataset (100+ hrs) representing nine types of synchronization errors in audio-visual content and how human perceive them. We then developed a PEAVS (Perceptual Evaluation of Audio-Visual Synchrony) score, a novel automatic metric with a 5-point scale that evaluates the quality of audio-visual synchronization. We validate PEAVS using a newly generated dataset, achieving a Pearson correlation of 0.79 at the set level and 0.54 at the clip level when compared to human labels. In our experiments, we observe a relative gain 50% over a natural extension of Fréchet based metrics for Audio-Visual synchrony, confirming PEAVS efficacy in objectively modeling subjective perceptions of audio-visual synchronization for videos "in the wild".