AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Robust-Wide: Robust Watermarking against Instruction-driven Image Editing

Runyi Hu, Jie Zhang, Ting Xu, Jiwei Li, Tianwei Zhang

ECCV 2024 · Image generation › Autoregressive and latent generation · approach: Robust diffusion watermarking · 22 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 PIDSG module (partial gradient through instruction-driven denoising sampling) during training (ablation)Robust-Wide · InstructPix2Pix edited imagesBER (%) with editing, 64 bits: 50.1558 -> 2.6579Improved
add L_ex2 loss (extract watermark from unedited watermarked image) (ablation)Robust-Wide · InstructPix2Pix edited imagesBER (%) with editing: 50.1219 -> 2.6579Improved
increase gradient backward steps k from 1 to 3 (ablation)Robust-Wide · InstructPix2Pix edited imagesBER (%): 4.0520 -> 2.6579Improved
increase lambda1 (embedding feature-space loss weight) to 0.1 (ablation)Robust-Wide · InstructPix2Pix edited imagesBER (%): 2.6579 -> 50.0364Hurt
increase lambda2 from 0.1 to 1 (ablation)Robust-Wide · InstructPix2Pix edited imagesBER (%): BER 2.6579 -> 0.9674; PSNR 41.9142 -> 35.2577Mixed
increase watermark length from 64 to 1024 bits (ablation)Robust-Wide · InstructPix2Pix edited imagesBER (%): 2.6579 -> 6.3036Hurt
apply Robust-Wide trained on InstructPix2Pix to MagicBrushRobust-Wide · MagicBrushaverage BER (%): 2.6579 -> 9.34 (vs 0.96 on ControlNet-InstructPix2Pix)Mixed
embed watermark with Robust-Wide before editingimage editability · InstructPix2Pix edited imagesCLIP-I: 0.8402 -> 0.8430No clear effect
apply brightness change before editingRobust-Wide · pixel-level distortionsBER (%): 2.6579 -> 12.2907Hurt

Later papers that compared with this method

4 later accepted papers report Robust-Wide 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