Salvato in:
Dettagli Bibliografici
Autori principali: Metzer, Gal, Polaczek, Sagi, Mahdavi-Amiri, Ali, Giryes, Raja, Cohen-Or, Daniel
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2604.22554
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908991085346816
author Metzer, Gal
Polaczek, Sagi
Mahdavi-Amiri, Ali
Giryes, Raja
Cohen-Or, Daniel
author_facet Metzer, Gal
Polaczek, Sagi
Mahdavi-Amiri, Ali
Giryes, Raja
Cohen-Or, Daniel
contents Transformations produced by image and video generation models often evolve in a highly non-linear manner: long stretches where the content barely changes are followed by sudden, abrupt semantic jumps. To analyze and correct this behavior, we introduce a Semantic Progress Function, a one-dimensional representation that captures how the meaning of a given sequence evolves over time. For each frame, we compute distances between semantic embeddings and fit a smooth curve that reflects the cumulative semantic shift across the sequence. Departures of this curve from a straight line reveal uneven semantic pacing. Building on this insight, we propose a semantic linearization procedure that reparameterizes (or retimes) the sequence so that semantic change unfolds at a constant rate, yielding smoother and more coherent transitions. Beyond linearization, our framework provides a model-agnostic foundation for identifying temporal irregularities, comparing semantic pacing across different generators, and steering both generated and real-world video sequences toward arbitrary target pacing.
format Preprint
id arxiv_https___arxiv_org_abs_2604_22554
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Video Analysis and Generation via a Semantic Progress Function
Metzer, Gal
Polaczek, Sagi
Mahdavi-Amiri, Ali
Giryes, Raja
Cohen-Or, Daniel
Computer Vision and Pattern Recognition
Transformations produced by image and video generation models often evolve in a highly non-linear manner: long stretches where the content barely changes are followed by sudden, abrupt semantic jumps. To analyze and correct this behavior, we introduce a Semantic Progress Function, a one-dimensional representation that captures how the meaning of a given sequence evolves over time. For each frame, we compute distances between semantic embeddings and fit a smooth curve that reflects the cumulative semantic shift across the sequence. Departures of this curve from a straight line reveal uneven semantic pacing. Building on this insight, we propose a semantic linearization procedure that reparameterizes (or retimes) the sequence so that semantic change unfolds at a constant rate, yielding smoother and more coherent transitions. Beyond linearization, our framework provides a model-agnostic foundation for identifying temporal irregularities, comparing semantic pacing across different generators, and steering both generated and real-world video sequences toward arbitrary target pacing.
title Video Analysis and Generation via a Semantic Progress Function
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.22554