When Composition Doesn't Add Up: Humans Identifying Defects in AI-Generated Images

arXiv:2608.25933 · cs.CV, cs.AI · Submitted 2026-08-26 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-08-26

Updated: 2026-08-26

Code: https://github.com/Future-IQA/CO-AID

Terminology

• Benchmark — 8× in this paper · explained in 2 episodes
• Conference on Computer Vision and Pattern Recognition — 4× in this paper
• Diffusion Model — 3× in this paper · explained in 8 episodes
• Diffusion Models — 3× in this paper · explained in 6 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Latent Diffusion Model — 1× in this paper · explained in 2 episodes
• Latent Diffusion Models — 1× in this paper · explained in 2 episodes

Sources

• Hierarchical Text-Conditional Image Generation with CLIP Latents
• Human Evaluation of Text-to-Image Models on a Multi-Task Benchmark
• How to Distinguish AI-Generated Images from Authentic Photographs

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models