Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911696312860672 |
|---|---|
| author | Tang, Yuqi Shi, Yang Zhang, Zhuoran Wang, Qixun Bai, Xuehai Ding, Yue Chen, Ruizhe Zeng, Bohan Chen, Xinlong Zhu, Xuanyu Li, Bozhou Wang, Yuran Dai, Yifan Tong, Chengzhuo Liu, Xinyu Ji, Yiyan Wei, Yujie Dong, Yuhao Yan, Shilin Wang, Fengxiang Zhang, Yi-Fan Wang, Haotian Zhang, Yuanxing Wan, Pengfei |
| author_facet | Tang, Yuqi Shi, Yang Zhang, Zhuoran Wang, Qixun Bai, Xuehai Ding, Yue Chen, Ruizhe Zeng, Bohan Chen, Xinlong Zhu, Xuanyu Li, Bozhou Wang, Yuran Dai, Yifan Tong, Chengzhuo Liu, Xinyu Ji, Yiyan Wei, Yujie Dong, Yuhao Yan, Shilin Wang, Fengxiang Zhang, Yi-Fan Wang, Haotian Zhang, Yuanxing Wan, Pengfei |
| contents | Recent video generative models have greatly improved the realism of AI-generated videos, yet their outputs still exhibit artifacts such as temporal inconsistencies, structural distortions, and semantic incoherence. While Multimodal Large Language Models (MLLMs) show strong visual understanding capabilities, their ability to perceive and reason about such artifacts remains unclear. Existing benchmarks often lack systematic evaluation of artifact-aware perception and fine-grained diagnostic reasoning, especially across diverse AI-generated video domains beyond photorealistic content. To address this gap, we introduce Artifact-Bench, a comprehensive benchmark for evaluating MLLMs on AI-generated video artifact detection and analysis. We first establish a three-level hierarchical taxonomy of realism artifacts, covering photorealistic, animated, and CG-style videos. Based on this taxonomy, Artifact-Bench defines three complementary tasks: real vs. AI-generated video classification, pairwise realism comparison, and fine-grained artifact identification. Experiments on 19 leading MLLMs reveal substantial limitations in artifact perception and reasoning, with many models approaching random or even below-random performance in challenging settings. We further observe significant misalignment between MLLM judgments and human perceptual preferences, highlighting their limited reliability as general evaluators for AI-generated video realism. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_18984 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos Tang, Yuqi Shi, Yang Zhang, Zhuoran Wang, Qixun Bai, Xuehai Ding, Yue Chen, Ruizhe Zeng, Bohan Chen, Xinlong Zhu, Xuanyu Li, Bozhou Wang, Yuran Dai, Yifan Tong, Chengzhuo Liu, Xinyu Ji, Yiyan Wei, Yujie Dong, Yuhao Yan, Shilin Wang, Fengxiang Zhang, Yi-Fan Wang, Haotian Zhang, Yuanxing Wan, Pengfei Computer Vision and Pattern Recognition Recent video generative models have greatly improved the realism of AI-generated videos, yet their outputs still exhibit artifacts such as temporal inconsistencies, structural distortions, and semantic incoherence. While Multimodal Large Language Models (MLLMs) show strong visual understanding capabilities, their ability to perceive and reason about such artifacts remains unclear. Existing benchmarks often lack systematic evaluation of artifact-aware perception and fine-grained diagnostic reasoning, especially across diverse AI-generated video domains beyond photorealistic content. To address this gap, we introduce Artifact-Bench, a comprehensive benchmark for evaluating MLLMs on AI-generated video artifact detection and analysis. We first establish a three-level hierarchical taxonomy of realism artifacts, covering photorealistic, animated, and CG-style videos. Based on this taxonomy, Artifact-Bench defines three complementary tasks: real vs. AI-generated video classification, pairwise realism comparison, and fine-grained artifact identification. Experiments on 19 leading MLLMs reveal substantial limitations in artifact perception and reasoning, with many models approaching random or even below-random performance in challenging settings. We further observe significant misalignment between MLLM judgments and human perceptual preferences, highlighting their limited reliability as general evaluators for AI-generated video realism. |
| title | Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.18984 |