AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

LOTA: Bit-Planes Guided AI-Generated Image Detection

Hongsong Wang, Renxi Cheng, Yang Zhang, Chaolei Han, Jie Gui

ICCV 2025 · Image generation › Autoregressive and latent generation · approach: Generalizable fake image detection · 7 citations (OpenAlex)

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
use bit-plane low-bit noise images instead of raw images (BGNIG) (ablation)LOTA-ngc · GenImage (train SD V1.5)average accuracy (%): 87.5 -> 96.8Improved
add maximum gradient patch selection (MGPS) (ablation)LOTA-ngc · GenImage (train SD V1.5)average accuracy (%): 90.9 -> 96.8Improved
use NBC/NGC classifier instead of a fully connected layer (ablation)LOTA · GenImage (train SD V1.5)average accuracy (%): 52.6 -> 96.8Improved
select highest-score patch instead of lowest-score (ablation)MGPS · GenImage (train SD V1.5)average accuracy (%): 89.6 -> 96.8Improved
select highest-score patch instead of random patch (ablation)MGPS · GenImage (train SD V1.5)average accuracy (%): 93.1 -> 96.8Improved
use 32x32 patch instead of 16x16, 48x48 or 64x64 (ablation)MGPS · GenImage (train SD V1.5)average accuracy (%): 92.7 / 91.4 / 90.8 -> 96.8Improved
compose the three lowest bit-planes instead of fewer or more (ablation)BGNIG · GenImage (train SD V1.5)average accuracy (%): 91.5 (bit 0) -> 96.8 (bits 0~2); 86.4 at bits 0~5Improved
use thresholding instead of scaling normalization (ablation)LOTA · GenImage (avg)average accuracy (%): 98.7 -> 98.9No clear effect
use noise-based instead of noise-guided classifier (ablation)LOTA · GenImage (avg)average accuracy (%): 93.2 -> 98.9Improved
replace multi-step reconstruction error with bit-plane noise for error extractionLOTA vs ESSP · GenImage (avg)average accuracy (%): 87.0 -> 98.9Improved
replace reconstruction-based error extraction with bit-plane extractionLOTA · error extraction timetime per image: 25.10 ms -> 1.52 ms (vs ESSP)Improved
apply Gaussian blur and JPEG compression at test timeLOTA vs LaRE2 and ESSP · GenImage (train SD V1.5)accuracy under degradationImproved

Later papers that compared with this method

1 later accepted paper reports LOTA as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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