arXiv cs.AI· Danqing Shi, Lan Jiang, Jake Lyons, Miri Zilka·· 14 小时前AI 评分31
用眼动追踪评估 AI 生成视频的视觉真实感
Evaluating Visual Realism of AI-Generated Videos with Eye Tracking
AI 导读
研究通过两项 Visual Turing Test 实验、90 名参与者对 438 个 AI 生成视频采集 4,286 次有效眼动追踪试次，发现注视模式与人类显式反馈一致。基于此提出首个计算方法 GazeEval，从眼动数据预测视频被感知的视觉真实感，准确率达 71.3%，并公开研究数据。
正文 · 原文
Abstract:Human evaluation of AI-generated videos has so far relied on explicit human feedback, such as judgments or ratings. While these signals capture the conclusions viewers reach, they fail to offer insights into the perception that leads to them. This paper investigates eye tracking as a complementary human evaluation signal for AI-generated videos. We conducted two Visual Turing Test (VTT) experiments with a total of 90 participants on videos generated by latest generative models, in which participants watched each video twice and then gave their feedback. Across the experiments, we collected 4,286 valid eye-tracking trials on 438 videos. Our analysis indicates that gaze patterns offer informative evaluation signals that align with explicit human feedback. Building on the findings, we propose the first computational method GazeEval to predict the perceived visual realism of AI-generated videos from eye-tracking data. It achieves 71.3% accuracy in prediction, providing evidence that eye tracking data carries informative signals about how people evaluate a video. We release the study data to support further research on eye tracking for evaluating AI-generated video.
| Subjects: | Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2610.38825 [cs.HC] |
| (or arXiv:2610.38825v1 [cs.HC] for this version) | |
| https://doi.org/10.48550/arXiv.2610.38825 arXiv-issued DOI via DataCite |
Submission history
From: Danqing Shi [view email]
[v1]
Wed, 28 Oct 2026 20:20:43 UTC (15,355 KB)
来源：arXiv cs.AI · arxiv.org