Temporal Realism Evaluation of Generated Videos Using Compressed-Domain Motion Vectors

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cakiroglu, Mert Onur, Altun, Idil Bilge, Lu, Zhihe, Dalkilic, Mehmet, Kurban, Hasan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912715501469696
author Cakiroglu, Mert Onur
Altun, Idil Bilge
Lu, Zhihe
Dalkilic, Mehmet
Kurban, Hasan
author_facet Cakiroglu, Mert Onur
Altun, Idil Bilge
Lu, Zhihe
Dalkilic, Mehmet
Kurban, Hasan
contents Temporal realism remains a central weakness of current generative video models, as most evaluation metrics prioritize spatial appearance and offer limited sensitivity to motion. We introduce a scalable, model-agnostic framework that assesses temporal behavior using motion vectors (MVs) extracted directly from compressed video streams. Codec-generated MVs from standards such as H.264 and HEVC provide lightweight, resolution-consistent descriptors of motion dynamics. We quantify realism by computing Kullback-Leibler, Jensen-Shannon, and Wasserstein divergences between MV statistics of real and generated videos. Experiments on the GenVidBench dataset containing videos from eight state-of-the-art generators reveal systematic discrepancies from real motion: entropy-based divergences rank Pika and SVD as closest to real videos, MV-sum statistics favor VC2 and Text2Video-Zero, and CogVideo shows the largest deviations across both measures. Visualizations of MV fields and class-conditional motion heatmaps further reveal center bias, sparse and piecewise constant flows, and grid-like artifacts that frame-level metrics do not capture. Beyond evaluation, we investigate MV-RGB fusion through channel concatenation, cross-attention, joint embedding, and a motion-aware fusion module. Incorporating MVs improves downstream classification across ResNet, I3D, and TSN backbones, with ResNet-18 and ResNet-34 reaching up to 97.4% accuracy and I3D achieving 99.0% accuracy on real-versus-generated discrimination. These findings demonstrate that compressed-domain MVs provide an effective temporal signal for diagnosing motion defects in generative videos and for strengthening temporal reasoning in discriminative models. The implementation is available at: https://github.com/KurbanIntelligenceLab/Motion-Vector-Learning
format Preprint
id arxiv_https___arxiv_org_abs_2511_13897
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Temporal Realism Evaluation of Generated Videos Using Compressed-Domain Motion Vectors
Cakiroglu, Mert Onur
Altun, Idil Bilge
Lu, Zhihe
Dalkilic, Mehmet
Kurban, Hasan
Computer Vision and Pattern Recognition
Temporal realism remains a central weakness of current generative video models, as most evaluation metrics prioritize spatial appearance and offer limited sensitivity to motion. We introduce a scalable, model-agnostic framework that assesses temporal behavior using motion vectors (MVs) extracted directly from compressed video streams. Codec-generated MVs from standards such as H.264 and HEVC provide lightweight, resolution-consistent descriptors of motion dynamics. We quantify realism by computing Kullback-Leibler, Jensen-Shannon, and Wasserstein divergences between MV statistics of real and generated videos. Experiments on the GenVidBench dataset containing videos from eight state-of-the-art generators reveal systematic discrepancies from real motion: entropy-based divergences rank Pika and SVD as closest to real videos, MV-sum statistics favor VC2 and Text2Video-Zero, and CogVideo shows the largest deviations across both measures. Visualizations of MV fields and class-conditional motion heatmaps further reveal center bias, sparse and piecewise constant flows, and grid-like artifacts that frame-level metrics do not capture. Beyond evaluation, we investigate MV-RGB fusion through channel concatenation, cross-attention, joint embedding, and a motion-aware fusion module. Incorporating MVs improves downstream classification across ResNet, I3D, and TSN backbones, with ResNet-18 and ResNet-34 reaching up to 97.4% accuracy and I3D achieving 99.0% accuracy on real-versus-generated discrimination. These findings demonstrate that compressed-domain MVs provide an effective temporal signal for diagnosing motion defects in generative videos and for strengthening temporal reasoning in discriminative models. The implementation is available at: https://github.com/KurbanIntelligenceLab/Motion-Vector-Learning
title Temporal Realism Evaluation of Generated Videos Using Compressed-Domain Motion Vectors
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.13897