AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Detecting Compressed AI-Generated Images via Phase Spectrum Robustness

Kai Li, Wenqi Ren, Wei Wang, Xiaochun Cao

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: Generalizable fake image detection

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add phase-harmonized cross-modal interaction (PHCI) to CLIP-ViT baseline (ablation)CLIP-ViT baseline · GANs, quality-aware, 2-classmean accuracy (%): 64.6 -> 74.7Improved
add multi-domain modulation adapter (MDMA) (ablation)CLIP-ViT + PHCI · GANs, quality-aware, 2-classmean accuracy (%): 74.7 -> 76.0Improved
add difficulty-aware consistency loss (DACL) (ablation)CLIP-ViT + PHCI + MDMA · GANs, quality-aware, 2-classmean accuracy (%): 76.0 -> 77.4Improved
add PHCI on specific generators (BigGAN, CycleGAN, StarGAN, GauGAN) vs baseline (ablation)CLIP-ViT baseline · GANs, quality-aware, 2-classaccuracy on Att-GAN: Att-GAN 54.7 -> 58.5; StyleGAN2 60.8 -> 56.3Mixed
use CPTFormer instead of ODDN with 2-class training, compressed test imagesAI-generated image detector · GANs, quality-awaremean accuracy (%): 71.4 -> 77.4Improved
use CPTFormer instead of best baseline on diffusion modelsAI-generated image detector · Diffusion models, quality-awaremean accuracy (%): 61.4 -> 65.9Improved
use CPTFormer in random-quality compression setting for GANsAI-generated image detector · GANs, quality-agnostic, 2-classmean accuracy (%): 70.7 -> 76.3Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy