AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Rel-Zero: Harnessing Patch-Pair Invariance for Robust Zero-Watermarking Against AI Editing

Pengzhen Chen, Yanwei Liu, Xiaoyan Gu, Xiaojun Chen, Wu Liu, Weiping Wang

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: Robust diffusion watermarking · 1 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 ViT-B/16 features instead of ResNet-18 (ablation)Rel-Zero · ControlNet-InpaintingTPR@0.1%FPR: 84.13 -> 97.43Improved
use ViT-B/16 features instead of ResNet-50 (ablation)Rel-Zero · ControlNet-InpaintingTPR@0.1%FPR: 85.21 -> 97.43Improved
add Transformer layers to the MLP pair predictor (ablation)Rel-Zero · ControlNet-InpaintingTPR@0.1%FPR: 97.43 -> 92.11Hurt
add GAT layers to the MLP pair predictor (ablation)Rel-Zero · ControlNet-InpaintingTPR@0.1%FPR: 97.43 -> 94.45Hurt
increase number of top-K pairs up to 50 (ablation)Rel-Zero · all edit typesrobustnessImproved
increase patch size from 16x16 to 32x32 (ablation)Rel-Zero · all edit typesrobustnessHurt
use Rel-Zero instead of FGPCET under UltraEditzero-watermarking · UltraEditTPR@0.1%FPR: 7.25 -> 96.55Improved
use Rel-Zero instead of ConZWNet under ControlNet-Inpaintingzero-watermarking · ControlNet-InpaintingTPR@0.1%FPR: 2.41 -> 97.43Improved
use Rel-Zero instead of VINE under deterministic regenerationwatermarking · Deterministic RegenerationTPR@0.1%FPR: 99.98 -> 85.13Hurt
use Rel-Zero instead of VINE under Cropoutwatermarking · CropoutTPR@0.1%FPR: 54.87 -> 98.45Improved
use Rel-Zero instead of embedding watermarks for fidelityRel-Zero · fidelitySSIM/LPIPS: 1.000 SSIM, 0.000 LPIPSImproved

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