AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

ROAR: Reducing Inversion Error in Generative Image Watermarking

Hanyi Wang, Han Fang, Shi-Lin Wang, Ee-Chien Chang

ICCV 2025 · Image generation › Autoregressive and latent generation · approach: Robust diffusion watermarking · 3 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 regeneration-based optimization (RO) only (ablation)Tree-Ring · Gaussian noise sigma=0.2TPR: 0.101 -> 0.525Improved
add distortion-adaptive restoration (AR) only (ablation)Tree-Ring · Gaussian noise sigma=0.2TPR: 0.101 -> 0.857Improved
add both RO and AR (ROAR) (ablation)Tree-Ring · Gaussian noise sigma=0.2TPR: 0.101 -> 1.000Improved
add AR only on unseen strong blur (ablation)Tree-Ring · Gaussian blur r=9TPR: 0.687 -> 0.731No clear effect
add RO for unseen blur (ablation)Tree-Ring · Gaussian blur r=9TPR: 0.687 -> 0.956Improved
plug ROAR into Gaussian ShadingGaussian Shading · SD v1.4/2.1, 9 distortionsBit accuracy (distorted): 0.885 -> 0.988Improved
plug ROAR into Tree-Ring and RingIDTree-Ring, RingID · SD v1.4/2.1, 9 distortionsTPR (distorted): 0.838 -> 1.000 (Tree-Ring)Improved
ROAR on image qualityGaussian Shading · SDFID: 25.20 -> 25.20No clear effect
mismatch inversion step vs inference step (ablation)ROAR with GS · Bit accuracybit accuracy: 1.000 -> 0.994 (worst case)No clear effect
increase RO optimization iterations beyond 20 (ablation)ROAR · TPR / bit accuracyextraction accuracyNo clear effect
stronger purification attack strengthGS-ROAR · purification attackTPR: 1.000 (s=0.3) -> 0.663 (s=0.7)Hurt

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