AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

RAIN: Redundancy-Aware Latent Injection for Quality-Preserving Image Watermarking

Yehan Sun, Rongrong Ni, Chuangchuang Tan, Huan Liu, Wenhao Ni, Renshuai Tao, Yao Zhao

AAAI 2026 · Image generation › Autoregressive and latent generation · approach: Robust diffusion watermarking · 0 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 redundancy-aware guidance (ablation)RAIN · ablation, 10k iterationsimage PSNR: 20.44 -> 24.20Improved
add redundancy-aware guidance with alignment (ablation)RAIN · ablation, 10k iterationsimage PSNR: 23.88 -> 26.45Improved
add distribution alignment initialization (ablation)RAIN · ablation, 10k iterationswatermark recovery PSNR: 35.57 -> 41.58Improved
add distribution alignment initialization (ablation)RAIN · ablation, 2k iterationswatermark recovery PSNR: 14.26 -> 35.44Improved
add distribution alignment initialization (ablation)RAIN · ablation, 2k iterationswatermark extraction ACC: 0.00 -> 0.71Improved
add distribution alignment initialization (ablation)RAIN · ablationconvergence iterations: 25k -> 13kImproved
add redundancy guidance (ablation)RAIN · ablation, 10k iterationswatermark recovery PSNR: 35.57 -> 35.94Improved
use both redundancy guidance and alignment (ablation)RAIN · ablation, 10k iterationswatermark ACC: 0.70 -> 0.85Improved
use RAIN instead of fine-tuning-based baselinesRAIN · COCO2017FID change from original: -0.0226 vs +3.2809 (RoSteALS)Improved
apply to other SD versions without retrainingRAIN · SD1-4, SD1-5, SD2-0, SD2-1PSNR: 39.9330 -> 40.6300No clear effect
use RAIN under crop attackRAIN · robustnessACCHurt

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