AI Paper Atlas

Research map / Video / Video generation

Hiding Video in Audio via Reversible Generative Models

Hyukryul Yang, Hao Ouyang, Vladlen Koltun, Qifeng Chen

ICCV 2019 · Video › Video generation · approach: Video-to-audio synthesis · 16 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 flip-rate and bit-importance optimized embedding instead of naive encodingWaveGlow steganography · DAVIS 128x128PSNR: 11.5683 -> 25.4318Improved
add optimized embedding instead of naive encodingWaveGlow steganography · DAVIS 128x128MS-SSIM: 0.4690 -> 0.9648Improved
add optimized embedding instead of naive encodingWaveGlow steganography · DAVIS 128x128audio samples per one-second video: 13680 -> 13440Improved
use binary codes in flow-based latent instead of continuous bottleneckvideo hiding in audio · DAVIS 128x128PSNR: 23.2836 -> 25.4318Improved
use binary codes in flow-based latent instead of continuous bottleneckvideo hiding in audio · DAVIS 128x128audio samples per one-second video: 30720 -> 13440Improved
use flow-based hiding instead of ConvNet spectrogram hidingvideo hiding in audio · DAVIS 128x128MS-SSIM: 0.9049 -> 0.9648Improved
use flow-based hiding instead of ConvNet spectrogram hidingvideo hiding in audio · DAVIS 128x128audio samples per one-second video: 330750 -> 13440Improved
increase ICN iterations from K=4 to K=8 (ablation)high-resolution video hiding · 480x848 videoMS-SSIM: 0.9631 -> 0.9838Mixed
encode cover audio into stereo with encoded audio and listenencoded audio · User studyshare cannot tell difference: 95.0%Improved

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