AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

MIRROR: Manifold Ideal Reference ReconstructOR for AI-Generated Image Detection

Ruiqi Liu, Manni Cui, Ziheng Qin, Zhiyuan Yan, Ruoxin Chen, Yi Han, Zhiheng Li, Junkai Chen, ZhiJin Chen, Kaiqing Lin, Jialiang Shen, Lubin Weng and 2 more

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

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes MIRROR, an AI-generated image detector that anchors detection on the stationary real-image distribution rather than on forgery artifacts, to generalise to unseen generators.

Problem

AI-generated image (AIGI) detectors typically rely on artifact classification and fail to generalise to new generators as generative models become more photorealistic.

Approach

Anchor detection on the stationary real-image distribution (modelled as a manifold with a reconstruction reference) instead of chasing the non-stationary forgery distribution, yielding a more generalisable signal.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
build memory bank from real images only instead of generated-only (ablation)MIRROR · Standard benchmarks (avg)B.Acc: 90.5 -> 94.0Improved
build memory bank from real images only instead of real+generated mix (ablation)MIRROR · Standard benchmarks (avg)B.Acc: 87.1 -> 94.0Improved
add reconstruction perplexity signal to classifier baseline (ablation)MIRROR baseline · Standard benchmarks (avg)B.Acc: 88.4 -> 90.1Improved
add comparison residual signal to classifier baseline (ablation)MIRROR baseline · Standard benchmarks (avg)B.Acc: 88.4 -> 92.5Improved
use full Reference-Comparison (both signals) instead of direct classification (ablation)MIRROR · Human-AIGI (avg)accuracy: 83.7 -> 89.8Improved
scale memory bank size K beyond 4096 or below it (ablation)MIRROR · sensitivity analysisaccuracyMixed
vary top-k sparsity of prototype projection (ablation)MIRROR · sensitivity analysisaccuracyMixed
switch backbone from DINOv2 to DINOv3MIRROR · Standard benchmarks (avg)B.Acc: 92.4 -> 94.0Improved
switch backbone from DINOv2 to DINOv3MIRROR · In-the-wild (avg)B.Acc: 87.4 -> 91.2Improved
MIRROR vs B-Free on DRCT-2MMIRROR · DRCT-2MB.Acc: 99.2 -> 93.0Hurt
scale pretrained backbone from Base to Huge for artifact-based detectorsNPR, UnivFD, DDA · Human-AIGIaccuracyNo clear effect

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