INR Smooth: Interframe noise relation-based smooth video synthesis on diffusion models
PLOS One · 2025
DOI: 10.1371/journal.pone.0321193 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Cuihong Yu und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Changchun University of Science and Technology, Changchun, China. Hauptthemen laut MEDLINE: Video Recording, Models, Theoretical, Image Processing, Computer-Assisted. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Jilin Province.
Abstract (Originalsprache)
The text-to-video generation task can provide people with rich and diverse video content, but it also has some typical issues, such as content inconsistency between video frames or text alignment failure, which degrade the smoothness of video. And in the process of improving the video smoothing problems, the background texture and artistic expression are often lost because of the excessive smoothing. Based on the above problems, this paper proposes INR Smooth, a type of video smoothing strategy based on the relationship between interframe noise, which can improve the smoothness of most T2V generation tasks. Based on INR Smooth, two video smoothing editing methods are proposed in this paper. One is for T2V training models, based on the studied interframe noise relationship, noise constraints are carried out from the beginning and end of the video simultaneously, and video smoothing loss functions are constructed. The other is for T2V training-free models, this paper introduces DDIM Inversion additionally to ensure text alignment, so as to improve the smoothness. Through experimental comparison, it is found that the proposed methods can significantly improve text alignment, temporal consistency, and has outstanding performance in the smooth transition of real scenes and the portrayal of artistic styles. The proposed training-free method and zero-shot fine-tuning training method for video smoothing do not add additional computing resources. The source codes and video demos are available at https://github.com/Cuihong-Yu/INR-Smooth .
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Computer Science and Technology, Changchun University of Science and Technology, Changchun, China.
ORCID-Profile: Cuihong Yu, Cheng Han
Förderung
- Natural Science Foundation of Jilin Province
Zitieren
APA
Yu, C., Han, C., & Zhang, C. (2025). INR Smooth: Interframe noise relation-based smooth video synthesis on diffusion models. PLOS One. https://doi.org/10.1371/journal.pone.0321193
Vancouver
Yu C, Han C, Zhang C. INR Smooth: Interframe noise relation-based smooth video synthesis on diffusion models. PLOS One. 2025. doi:10.1371/journal.pone.0321193
BibTeX
@article{Yu2025,
author = {Yu, Cuihong and Han, Cheng and Zhang, Chao},
title = {INR Smooth: Interframe noise relation-based smooth video synthesis on diffusion models},
journal = {PLOS One},
year = {2025},
doi = {10.1371/journal.pone.0321193}
}
EUVIMED