AI Paper Atlas

Research map / Image generation / Image restoration

UDH: Universal Deep Hiding for Steganography, Watermarking, and Light Field Messaging

Chaoning Zhang, Philipp Benz, Adil Karjauv, Geng Sun, In So Kweon

NeurIPS 2020 · Image generation › Image restoration · approach: Dehazing and deraining · 87 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
cover-independent hiding (UDH) vs cover-dependent DDHdeep steganography · ImageNetcover PSNR: 35.87 -> 39.13Improved
UDH vs DDH under uniform noise on coverdeep steganography · noise 50/255secret APD: 5.9 -> 52.3Hurt
UDH vs DDH under constant shift on containerdeep steganography · shift 50/255secret APD: 32.4 -> 3.5Improved
train with combined distortions vs no distortions (ablation)UDH watermarking · JPEGsecret APD: 57.0 -> 23.6Improved
train with combined distortions vs no distortions (ablation)UDH watermarking · no distortionsecret APD: 3.5 -> 9.6Hurt
decrease patch size (more hidden bits) (ablation)UDH barcode hiding · JPEGbit accuracy: 91.5% -> 60.2%Hurt
UDH vs HiDDeNwatermarking · JPEGbit accuracy: 63.0% -> 91.5%Improved
UDH vs LFMphotographic steganography · unseen camera-display pairsBER: 13.62% -> 4.41%Improved
split mini-batch into groups with different distortions (ablation)UDH training · combined distortionsconvergence/performanceImproved

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