AI Paper Atlas

Research map / Video / Video generation

Audio-driven Talking Face Generation with Stabilized Synchronization Loss

Dogucan Yaman, Fevziye Irem Eyiokur, Leonard Bärmann, HAZIM KEMAL EKENEL, Alexander Waibel

ECCV 2024 · Video › Video generation · approach: Talking face generation · 12 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 pretrained frozen audio encoder instead of jointly trained audio encoder (ablation)talking face generator with lip-sync loss · LRS2 testFID: 12.25 -> 9.82Improved
use Wav2Vec2 audio encoder instead of sync-pretrained audio encoder (ablation)talking face generator · LRS2 testFID: 9.82 -> 10.56Hurt
add silent-lip generator to produce closed-lip identity references (ablation)talking face generator · LRS2 testLMD: 2.325 -> 1.741Improved
replace lip-sync loss with stabilized synchronization loss (ablation)talking face generator · LRS2 testLSE-C: 7.752 -> 8.370Improved
replace lip-sync loss with stabilized synchronization loss (ablation)talking face generator · LRS2 testFID: 8.16 -> 5.27Improved
add vanilla triplet loss (ablation)talking face generator · LRS2 testFID: 5.27 -> 6.24Hurt
add adaptive triplet loss (ablation)talking face generator · LRS2 testFID: 5.27 -> 4.02Improved
replace SyncNet with AVSyncNet (ablation)talking face generator · LRS2 testFID: 4.02 -> 3.83Improved
add VQFR face restoration post-processing (ablation)full model · LRS2 testFID: 3.83 -> 5.23Hurt
choose VQFR over GPEN and GFPGAN for post-processing (ablation)full model · LRS2 testFID: 58.77 -> 5.23Improved
use silent-lip generator instead of VideoReTalking for silent face generation (ablation)silent identity reference generation · Silent face generation (LRS2)FID: 33.60 -> 4.41Improved

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