| title | Verus-Insight: Towards Explainable Artifact Detection in AI-Generated Videos |
|---|---|
| authors | Zhuoran Zhang, Yang Shi, Qixun Wang, Tengfei Liu, Yuqi Tang, Xuanyu Zhu, Yizhuo Jia, Jingyun Hua, Shixuan Liu, Xianghua Ying, Haotian Wang, Yuanxing Zhang, Pengfei Wan, Wenjing Yang |
| date | 2026-10-22 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.30866 |
| upvotes | 17 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Recent advances in video generation have made synthetic videos increasingly realistic, placing greater demands on reliable AI-generated video detection. Existing artifact-based detectors typically identify generation artifacts as evidence for source prediction, yet they may either fail to recognize subtle artifacts or reach the correct source decision without faithfully identifying the evidence underlying it. In this work, we systematically investigate how to design and train effective artifact detectors and formulate artifact detection as a structured process comprising three complementary capabilities: Inspection Planning, which determines what should be examined; Evidence Verification, which verifies whether the inspected content exhibits genuine generation artifacts; and Evidence Aggregation, which integrates the verified evidence into the final source decision. Building on this formulation, we introduce Verus-Insight, trained with human-anchored full-process supervision and progressive capability training to strengthen both fine-grained artifact detection and video-level detection. We further introduce Verus-Bench, a benchmark with fine-grained human annotations of perceptible artifacts for evaluating artifact detection. Extensive experiments across diverse benchmarks demonstrate that Verus-Insight achieves strong performance in both fine-grained artifact analysis and AI-generated video detection, with substantial gains in recovering human-perceived artifacts. Further analyses reveal that the three capabilities are complementary yet distinct, and that Verus-Insight more reliably converts relevant inspection targets into supported artifact evidence without increasing spurious artifact claims. |
cite
@misc{zhang2026verus,
title={Verus-Insight: Towards Explainable Artifact Detection in AI-Generated Videos},
author={Zhuoran Zhang and Yang Shi and Qixun Wang and Tengfei Liu and Yuqi Tang and Xuanyu Zhu and Yizhuo Jia and Jingyun Hua and Shixuan Liu and Xianghua Ying and Haotian Wang and Yuanxing Zhang and Pengfei Wan and Wenjing Yang},
year={2026},
eprint={2610.30866},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.30866}
}