The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gao, Xiangbo, Wu, Mingyang, Yang, Siyuan, Yu, Jiongze, Taghavi, Pardis, Lin, Fangzhou, Tu, Zhengzhong
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908916693073920
author Gao, Xiangbo
Wu, Mingyang
Yang, Siyuan
Yu, Jiongze
Taghavi, Pardis
Lin, Fangzhou
Tu, Zhengzhong
author_facet Gao, Xiangbo
Wu, Mingyang
Yang, Siyuan
Yu, Jiongze
Taghavi, Pardis
Lin, Fangzhou
Tu, Zhengzhong
contents While recent generative video models have achieved remarkable visual realism and are being explored as world models, true physical simulation requires mastering both space and time. Current models can produce visually smooth kinematics, yet they lack a reliable internal motion pulse to ground these motions in a consistent, real-world time scale. This temporal ambiguity stems from the common practice of indiscriminately training on videos with vastly different real-world speeds, forcing them into standardized frame rates. This leads to what we term chronometric hallucination: generated sequences exhibit ambiguous, unstable, and uncontrollable physical motion speeds. To address this, we propose Visual Chronometer, a predictor that recovers the Physical Frames Per Second (PhyFPS) directly from the visual dynamics of an input video. Trained via controlled temporal resampling, our method estimates the true temporal scale implied by the motion itself, bypassing unreliable metadata. To systematically quantify this issue, we establish two benchmarks, PhyFPS-Bench-Real and PhyFPS-Bench-Gen. Our evaluations reveal a harsh reality: state-of-the-art video generators suffer from severe PhyFPS misalignment and temporal instability. Finally, we demonstrate that applying PhyFPS corrections significantly improves the human-perceived naturalness of AI-generated videos. Our project page is https://xiangbogaobarry.github.io/Visual_Chronometer/.
format Preprint
id arxiv_https___arxiv_org_abs_2603_14375
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamics
Gao, Xiangbo
Wu, Mingyang
Yang, Siyuan
Yu, Jiongze
Taghavi, Pardis
Lin, Fangzhou
Tu, Zhengzhong
Computer Vision and Pattern Recognition
Artificial Intelligence
While recent generative video models have achieved remarkable visual realism and are being explored as world models, true physical simulation requires mastering both space and time. Current models can produce visually smooth kinematics, yet they lack a reliable internal motion pulse to ground these motions in a consistent, real-world time scale. This temporal ambiguity stems from the common practice of indiscriminately training on videos with vastly different real-world speeds, forcing them into standardized frame rates. This leads to what we term chronometric hallucination: generated sequences exhibit ambiguous, unstable, and uncontrollable physical motion speeds. To address this, we propose Visual Chronometer, a predictor that recovers the Physical Frames Per Second (PhyFPS) directly from the visual dynamics of an input video. Trained via controlled temporal resampling, our method estimates the true temporal scale implied by the motion itself, bypassing unreliable metadata. To systematically quantify this issue, we establish two benchmarks, PhyFPS-Bench-Real and PhyFPS-Bench-Gen. Our evaluations reveal a harsh reality: state-of-the-art video generators suffer from severe PhyFPS misalignment and temporal instability. Finally, we demonstrate that applying PhyFPS corrections significantly improves the human-perceived naturalness of AI-generated videos. Our project page is https://xiangbogaobarry.github.io/Visual_Chronometer/.
title The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamics
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2603.14375