Exploring AIGC Video Quality: A Focus on Visual Harmony, Video-Text Consistency and Domain Distribution Gap

TL;DR

This paper proposes a comprehensive framework for assessing AIGC video quality by evaluating visual harmony, video-text consistency, and domain distribution gap, addressing key challenges in AI-generated video evaluation.

Contribution

It introduces specific modules for each assessment dimension and demonstrates improved performance in quality evaluation, winning third place in a related competition.

Findings

Significant variation in quality across different models

Predicting generative source improves assessment accuracy

Proposed method outperforms existing approaches

Abstract

The recent advancements in Text-to-Video Artificial Intelligence Generated Content (AIGC) have been remarkable. Compared with traditional videos, the assessment of AIGC videos encounters various challenges: visual inconsistency that defy common sense, discrepancies between content and the textual prompt, and distribution gap between various generative models, etc. Target at these challenges, in this work, we categorize the assessment of AIGC video quality into three dimensions: visual harmony, video-text consistency, and domain distribution gap. For each dimension, we design specific modules to provide a comprehensive quality assessment of AIGC videos. Furthermore, our research identifies significant variations in visual quality, fluidity, and style among videos generated by different text-to-video models. Predicting the source generative model can make the AIGC video features more discriminative, which enhances the quality assessment performance. The proposed method was used in the third-place winner of the NTIRE 2024 Quality Assessment for AI-Generated Content - Track 2 Video, demonstrating its effectiveness. Code will be available at https://github.com/Coobiw/TriVQA.