AI Paper Atlas

Research map / Image generation / GANs

Reality Transform Adversarial Generators for Image Splicing Forgery Detection and Localization

Xiuli Bi, Zhipeng Zhang, Bin Xiao

ICCV 2021 · Image generation › GANs · approach: GAN-based image manipulation · 40 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
add fake-to-realistic transform generator G_T with adversarial training (ablation)RTAG localization generator G_M · CASIA v2.0mAP / F: mAP 0.606 -> 0.707; F 0.704 -> 0.818Improved
use multi-decoder-single-task instead of single decoder for all tasks (ablation)G_M · CASIA v2.0mAP / F: mAP 0.622 -> 0.707; F 0.731 -> 0.818Improved
add reconstruction decoder (ablation)RTAG · CASIA v2.0mAP / F: mAP 0.684 -> 0.707; F 0.772 -> 0.818Improved
add edge decoder (ablation)RTAG · CASIA v2.0mAP / F: mAP 0.689 -> 0.707; F 0.775 -> 0.818Improved
learn alpha in WCT blocks instead of fixing it manually (1, 0.5, 0.2) (ablation)G_T · qualitativevisual qualityImproved
use RTAG instead of best prior method C2RNetsplicing localization · NIST 2016mAP: 0.097 -> 0.531Improved
use RTAG instead of MAGsplicing localization · FantasticRealitymAP: 0.780 -> 0.910Improved

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