On the Content Bias in Frechet Video Distance
Frechet Video Distance (FVD) a prominent metric for evaluating video generation models is known to conflict with human perception occasionally. In this paper we aim to explore the extent of FVD's bias toward frame quality over temporal realism and identify its sources. We first quantify the FVD's sensitivity to the temporal axis by decoupling the frame and motion quality and find that the FVD only increases slightly with larger temporal corruption. We then analyze the generated videos and show that via careful sampling from a large set of generated videos that do not contain motions one can drastically decrease FVD without improving the temporal quality. Both studies suggest FVD's basis towards the quality of individual frames. We show that FVD with features extracted from the recent large-scale self-supervised video models is less biased toward image quality. Finally we revisit a few real-world examples to validate our hypothesis.
Code (0)
등록된 구현이 없습니다.
Tasks
Video GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Adapting Frechet Audio Distance for Generative Music Evaluation
The growing popularity of generative music models underlines the need for perceptually relevant, objective music quality metrics. The Frechet Audio Distance (FAD) is commonly used for this purpose even though its correla…
FADFrechet Music Distance: A Metric For Generative Symbolic Music Evaluation
In this paper we introduce the Frechet Music Distance (FMD), a novel evaluation metric for generative symbolic music models, inspired by the Frechet Inception Distance (FID) in computer vision and Frechet Audio Distance …
FADMusic GenerationMusic ModelingOn the Content Bias in Fréchet Video Distance
Fr\'echet Video Distance (FVD), a prominent metric for evaluating video generation models, is known to conflict with human perception occasionally. In this paper, we aim to explore the extent of FVD's bias toward per-fra…
Video GenerationAddressing Emotion Bias in Music Emotion Recognition and Generation with Frechet Audio Distance
The complex nature of musical emotion introduces inherent bias in both recognition and generation, particularly when relying on a single audio encoder, emotion classifier, or evaluation metric. In this work, we conduct a…
Emotion RecognitionFADMusic Emotion RecognitionMusic GenerationTARO: Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning for Synchronized Video-to-Audio Synthesis
This paper introduces Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning (TARO), a novel framework for high-fidelity and temporally coherent video-to-audio synthesis. Built upon flow-based transform…
Audio SynthesisFAD