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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add contextual loss (ablation) | SIDGAN · HDTF | FID: 14.97 -> 12.15 | Improved |
| use contextual loss instead of perceptual loss (ablation) | SIDGAN · HDTF | FID: 15.29 -> 12.15 | Improved |
| use APS-SyncNet instead of vanilla SyncNet for Sync-Loss (ablation) | SIDGAN · HDTF | FID: 12.61 -> 12.15 | Improved |
| use APS-SyncNet instead of vanilla SyncNet for Sync-Loss (ablation) | SIDGAN · HDTF | LSE-C: 7.76 -> 8.05 | Improved |
| add pyramid generator with multi-resolution supervision (ablation) | SIDGAN · HDTF | FID: 13.01 -> 12.15 | Improved |
| SIDGAN vs Wav2Lip on SyncNet-based lip-sync metrics | dubbed video generation · AVSpeech test | LSE-C: 8.03 (Wav2Lip) vs 6.31 (SIDGAN) | Hurt |
| SIDGAN vs Wav2Lip-384 baseline on image quality | high-resolution dubbing · AVSpeech test | FID: 61.25 -> 22.69 | Improved |
| SIDGAN vs baselines in user study | dubbed video generation · HDTF user study | Overall rating: 2.57 -> 3.41 (vs PC-AVS) | Improved |
Closest papers by meaning
- Audio-driven Talking Face Generation with Stabilized Synchronization Loss (ECCV 2024 · similarity 0.90)
- OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers (NeurIPS 2025 · similarity 0.89)
- DiVAS: Video and Audio Synchronization with Dynamic Frame Rates (CVPR 2024 · similarity 0.88)
- KeyFace: Expressive Audio-Driven Facial Animation for Long Sequences via KeyFrame Interpolation (CVPR 2025 · similarity 0.88)
- Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakes (NeurIPS 2024 · similarity 0.87)
- SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis (CVPR 2024 · similarity 0.87)
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.
