Towards Holistic Visual Quality Assessment of AI-Generated Videos: A LLM-Based Multi-Dimensional Evaluation Model

TL;DR

This paper presents a multi-dimensional, LLM-based model for automatic visual quality assessment of AI-generated videos, addressing defects like noise and jitter by decomposing quality into technical, motion, and semantic aspects.

Contribution

It introduces a novel multi-dimensional evaluation framework using LLMs with prompt engineering and LoRA fine-tuning for improved quality assessment of AI-generated videos.

Findings

Achieved second place in NTIRE 2025 challenge for AI-generated video quality assessment.

Effectively models technical, motion, and semantic quality dimensions.

Demonstrates the potential of LLMs in multi-dimensional video quality evaluation.

Abstract

The development of AI-Generated Video (AIGV) technology has been remarkable in recent years, significantly transforming the paradigm of video content production. However, AIGVs still suffer from noticeable visual quality defects, such as noise, blurriness, frame jitter and low dynamic degree, which severely impact the user's viewing experience. Therefore, an effective automatic visual quality assessment is of great importance for AIGV content regulation and generative model improvement. In this work, we decompose the visual quality of AIGVs into three dimensions: technical quality, motion quality, and video semantics. For each dimension, we design corresponding encoder to achieve effective feature representation. Moreover, considering the outstanding performance of large language models (LLMs) in various vision and language tasks, we introduce a LLM as the quality regression module. To better enable the LLM to establish reasoning associations between multi-dimensional features and visual quality, we propose a specially designed multi-modal prompt engineering framework. Additionally, we incorporate LoRA fine-tuning technology during the training phase, allowing the LLM to better adapt to specific tasks. Our proposed method achieved \textbf{second place} in the NTIRE 2025 Quality Assessment of AI-Generated Content Challenge: Track 2 AI Generated video, demonstrating its effectiveness. Codes can be obtained at https://github.com/QiZelu/AIGVEval.