AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Vision-Infused Deep Audio Inpainting

Hang Zhou, Ziwei Liu, Xudong Xu, Ping Luo, Xiaogang Wang

ICCV 2019 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual source localization · 79 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 audio-visual synchronizing loss (ablation)VIAI-AV · MUSICES audio inpaintingPSNR: 21.8 -> 23.2Improved
add audio-visual synchronizing loss (ablation)VIAI-AV · MUSICES audio inpaintingSSIM: 0.62 -> 0.64Improved
add probe loss (ablation)VIAI-AV · MUSICES audio inpaintingPSNR: 22.5 -> 23.2Improved
add probe loss (ablation)VIAI-AV · MUSICES audio inpaintingSSIM: 0.63 -> 0.64Improved
use adaptive weight eta1(t) instead of fixed eta1(0) (ablation)VIAI-A · MUSICES audio inpaintingPSNR: 21.8 -> 22.2Improved
use adaptive weight eta1(t) instead of fixed eta1(inf) (ablation)VIAI-A · MUSICES audio inpaintingPSNR: 21.6 -> 22.2Improved
use interpolation initialization instead of fixed-value initialization (ablation)VIAI-A · MUSICES audio inpaintingPSNR: 21.5 -> 22.2Improved
add WaveNet conditioning on past results (ablation)VIAI-AV · MUSICES user studyaudio quality MOS: 3.00 -> 3.93Improved
add synchronizing loss (user study) (ablation)VIAI-AV · MUSICES user studyaudio quality MOS: 2.90 -> 3.93Improved
add visual information to the inpainterVIAI-A to VIAI-AV · MUSICES audio inpaintingPSNR: 22.2 -> 23.2Improved
add visual information to the inpainterVIAI-A to VIAI-AV · MUSICES audio inpaintingOPS: 52.4 -> 56.3Improved
add visual information to the inpainterVIAI-A to VIAI-AV · MUSICES audio inpaintingSDR: 6.54 -> 6.63No clear effect

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