AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

TrustMark: Robust Watermarking and Watermark Removal for Arbitrary Resolution Images

Tu Bui, Shruti Agarwal, John Collomosse

ICCV 2025 · Image generation › Autoregressive and latent generation · approach: Robust diffusion watermarking · 19 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 GAN loss (ablation)TrustMark without GAN, FFL, Epost · DIV2KPSNR (dB): +0.7dBImproved
add 1x1-conv post-process module Epost (ablation)TrustMark without GAN, FFL, Epost · DIV2KPSNR (dB): +1.6dBImproved
add focal frequency loss (FFL) (ablation)TrustMark without GAN, FFL, Epost · DIV2KPSNR (dB): +1.7dBImproved
add GAN, Epost and FFL together (ablation)TrustMark · DIV2KPSNR (dB) and bit accuracy: 36.30 -> 40.20 PSNR, 0.959 -> 0.973 accuracyImproved
combine Epost with GAN or FFL (ablation)TrustMark · DIV2KPSNR (dB): boosts PSNR by 3dBImproved
use VGG, GoogleNet, ConvNext or EfficientNet as extractor instead of ResNet family (ablation)TrustMark extractor · DIV2Ktraining convergence: training not successfulHurt
add noise simulation during training (no noise vs high severity) (ablation)TrustMark · DIV2KPSNR (dB): 53.2dB -> 40.2dB PSNR, bit accuracy reduces by only 3%Hurt
increase alpha_max to 30 (ablation)TrustMark · DIV2KPSNR and bit accuracy: PSNR improves by more than 8dB while bit accuracy drops by less than 5%Mixed
increase watermark length from 32 to 200 bits (ablation)TrustMark · DIV2KPSNR and bit accuracy: PSNR and bit accuracy both drop by 7.5dB and 11%Hurt
add ReMark removal before re-watermarkingTrustMark · DIV2KPSNR (dB): 40.20 -> 48.48 PSNR, bit accuracy 0.970 -> 0.553Improved
add high-severity noise simulation against I-FGSM attack (ablation)TrustMark · DIV2Kattack iterations: under 50 iterations without noise vs more than 3000 iterations for 32% of imagesImproved
apply Resolution Scaling across 20% to 100% of 2K resolution (ablation)TrustMark · DIV2KPSNR and bit accuracy: PSNR varies only by ±0.02dB, bit accuracy by ±10−4No 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