Unverified50% confidenceFactExact time
Researchers have found that AI-generated images exhibit systematic biases at specific spatial frequencies
1
Sources
50%
Confidence
Long-term
Relevance
10/10/2026
First Seen
Sources
Related Entities
Related Claims
Unverified研究者通过分析图像频域特征（傅里叶变换下的频率分布异常）、面部生物力学一致性及全局光照方向来识别AI合成图像77% similarUnverifiedAI-generated images often exhibit statistical averaging characteristics of training data in local regions, such as overly uniform textures and overly regular spacing between repeating elements75% similarUnverified网格识别需同时估计网格间距和相位偏移两个参数，因AI生成图像的隐含网格常存在全局偏移、轻微旋转和局部混乱74% similarUnverifiedMultiple published studies indicate that the accuracy with which ordinary people distinguish real photographs from AI-generated images is often only slightly above random chance.74% similarUnverifiedAI可见性仪表盘用有限的预设问题推断整体可见性，存在极大的采样偏差73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/994039API
curl https://kongchang.com/api/v1/knowledge/claims/994039MCP
get_claim(id=994039)