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

arXiv:2404.13573v1 Announce Type: new
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, …

abstract aigc artificial artificial intelligence arxiv assessment challenges common sense cs.cv distribution domain focus gap generated intelligence prompt quality sense text text-to-video textual type video video quality videos visual