EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Perspective on Quality Evaluation for AI-Generated Videos

Zhichao Zhang iD, Wei Sun iD, Guangtao Zhai iD

Sensors · 28.07.2025 · 25 (15) · 4668

DOI: 10.3390/s25154668 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 28.07.2025. Verfasst von Zhichao Zhang und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai 200030, China. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 103 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent breakthroughs in AI-generated content (AIGC) have transformed video creation, empowering systems to translate text, images, or audio into visually compelling stories. Yet reliable evaluation of these machine-crafted videos remains elusive because quality is governed not only by spatial fidelity within individual frames but also by temporal coherence across frames and precise semantic alignment with the intended message. The foundational role of sensor technologies is critical, as they determine the physical plausibility of AIGC outputs. In this perspective, we argue that multimodal large language models (MLLMs) are poised to become the cornerstone of next-generation video quality assessment (VQA). By jointly encoding cues from multiple modalities such as vision, language, sound, and even depth, the MLLM can leverage its powerful language understanding capabilities to assess the quality of scene composition, motion dynamics, and narrative consistency, overcoming the fragmentation of hand-engineered metrics and the poor generalization ability of CNN-based methods. Furthermore, we provide a comprehensive analysis of current methodologies for assessing AIGC video quality, including the evolution of generation models, dataset design, quality dimensions, and evaluation frameworks. We argue that advances in sensor fusion enable MLLMs to combine low-level physical constraints with high-level semantic interpretations, further enhancing the accuracy of visual quality assessment.

Schlagwörter

Stichwörter der Autor:innen

AI-generated videoMLLMvideo quality assessment

Autor:innen und Institutionen

  • Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai 200030, China.

ORCID-Profile: Zhichao Zhang, Wei Sun, Guangtao Zhai

Zitieren

APA

Zhang, Z., Sun, W., & Zhai, G. (2025). A Perspective on Quality Evaluation for AI-Generated Videos. Sensors, 25(15), 4668. https://doi.org/10.3390/s25154668

Vancouver

Zhang Z, Sun W, Zhai G. A Perspective on Quality Evaluation for AI-Generated Videos. Sensors. 2025;25(15):4668. doi:10.3390/s25154668

BibTeX
@article{Zhang2025,
  author = {Zhang, Zhichao and Sun, Wei and Zhai, Guangtao},
  title = {A Perspective on Quality Evaluation for AI-Generated Videos},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {15},
  pages = {4668},
  doi = {10.3390/s25154668}
}
Kostenlos starten →