AI Paper Atlas

Research map / Video / Video generation

SIDGAN: High-Resolution Dubbed Video Generation via Shift-Invariant Learning

Urwa Muaz, Wondong Jang, Rohun Tripathi, Santhosh Mani, Wenbin Ouyang, Ravi Teja Gadde, Baris Gecer, Sergio Elizondo, Reza Madad, Naveen Nair

ICCV 2023 · Video › Video generation · approach: Talking face generation · 5 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 contextual loss (ablation)SIDGAN · HDTFFID: 14.97 -> 12.15Improved
use contextual loss instead of perceptual loss (ablation)SIDGAN · HDTFFID: 15.29 -> 12.15Improved
use APS-SyncNet instead of vanilla SyncNet for Sync-Loss (ablation)SIDGAN · HDTFFID: 12.61 -> 12.15Improved
use APS-SyncNet instead of vanilla SyncNet for Sync-Loss (ablation)SIDGAN · HDTFLSE-C: 7.76 -> 8.05Improved
add pyramid generator with multi-resolution supervision (ablation)SIDGAN · HDTFFID: 13.01 -> 12.15Improved
SIDGAN vs Wav2Lip on SyncNet-based lip-sync metricsdubbed video generation · AVSpeech testLSE-C: 8.03 (Wav2Lip) vs 6.31 (SIDGAN)Hurt
SIDGAN vs Wav2Lip-384 baseline on image qualityhigh-resolution dubbing · AVSpeech testFID: 61.25 -> 22.69Improved
SIDGAN vs baselines in user studydubbed video generation · HDTF user studyOverall rating: 2.57 -> 3.41 (vs PC-AVS)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