Research map / Video / Video generation
Speech-driven Facial Animation using Cascaded GANs for Learning of Motion and Texture
Dipanjan Das, Sandika Biswas, Sanjana Sinha, Brojeshwar Bhowmick
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 |
|---|---|---|---|
| use adaptive instance normalization instead of channel-wise concatenation (ablation) | t-GAN texture generator · TCD-TIMIT texture ablation | PSNR: 27.2 -> 28.3 | Improved |
| use adaptive instance normalization instead of channel-wise concatenation (ablation) | t-GAN texture generator · TCD-TIMIT texture ablation | LMD: 1.65 -> 1.57 | Improved |
| add feature loss (ablation) | t-GAN texture generator · TCD-TIMIT texture ablation | PSNR: 28.3 -> 28.9 | Improved |
| add adversarial loss (ablation) | t-GAN texture generator · TCD-TIMIT texture ablation | PSNR: 28.9 -> 30.7 | Improved |
| add adversarial loss (ablation) | t-GAN texture generator · TCD-TIMIT texture ablation | LMD: 1.5 -> 1.4 | Improved |
| add discriminator (GAN) to landmark generator l-GAN (ablation) | l-GAN · TCD-TIMIT | qualitative lip motion | Improved |
| use context window of 6 frames for DeepSpeech features (ablation) | l-GAN · TCD-TIMIT | LMD | Improved |
| add L2 regularization loss to the motion loss (ablation) | l-GAN · TCD-TIMIT | LMD | Improved |
| add direction loss to the motion loss (ablation) | l-GAN · TCD-TIMIT | convergence speed | Improved |
| add synthetic audio noise up to -30dB (ablation) | l-GAN lip sync · TCD-TIMIT | LMD | No clear effect |
| fine-tune for 10 epochs instead of 1 epoch (ablation) | t-GAN · GRID | PSNR: 21.5 -> 29.8 | Improved |
| fine-tune for 10 epochs instead of 1 epoch (ablation) | t-GAN · TCD-TIMIT | PSNR: 20.6 -> 30.7 | Improved |
Closest papers by meaning
- Realistic Speech-Driven Facial Animation with GANs (IJCV 2019 · similarity 0.93)
- FACIAL: Synthesizing Dynamic Talking Face With Implicit Attribute Learning (ICCV 2021 · similarity 0.92)
- Speech Driven Tongue Animation (CVPR 2022 · similarity 0.91)
- Probabilistic Speech-Driven 3D Facial Motion Synthesis: New Benchmarks Methods and Applications (CVPR 2024 · similarity 0.89)
- DEEPTalk: Dynamic Emotion Embedding for Probabilistic Speech-Driven 3D Face Animation (AAAI 2025 · similarity 0.88)
- ProsodyTalker: 3D Visual Speech Animation via Prosody Decomposition (AAAI 2025 · 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.
