Research map / 3D vision / Face and shape
Depth-Aware Generative Adversarial Network for Talking Head Video Generation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 self-supervised depth-guided keypoint estimation (ablation) | DaGAN baseline · CelebV cross-identity reenactment | PRMSE: 5.39 -> 2.69 | Helped |
| add self-supervised depth-guided keypoint estimation (ablation) | DaGAN baseline · CelebV cross-identity reenactment | AUCON: 0.657 -> 0.852 | Helped |
| add cross-modal attention (ablation) | DaGAN baseline · CelebV cross-identity reenactment | AUCON: 0.657 -> 0.838 | Helped |
| replace depth-aware cross-modal attention with standard self-attention (ablation) | DaGAN · CelebV cross-identity reenactment | PRMSE: 2.33 -> 5.18 | Hurt |
| replace depth-aware cross-modal attention with standard self-attention (ablation) | DaGAN · CelebV cross-identity reenactment | AUCON: 0.873 -> 0.832 | Hurt |
| add face depth network and cross-modal attention (ablation) | FOMM · CelebV cross-identity reenactment | PRMSE: 3.90 -> 2.28 | Helped |
| add face depth network and cross-modal attention (ablation) | FOMM · CelebV cross-identity reenactment | AUCON: 0.667 -> 0.865 | Helped |
| add dense facial depth cues to generation | DaGAN · VoxCeleb1 self-reenactment | SSIM: 0.761 -> 0.804 | Helped |
| use DaGAN for cross-identity reenactment | CelebV · CelebV cross-identity reenactment | CSIM: 0.791 -> 0.723 | Hurt |
| use DaGAN for cross-identity reenactment | CelebV · CelebV cross-identity reenactment | PRMSE: 3.15 -> 2.33 | Helped |
| use DaGAN for cross-identity reenactment | CelebV · CelebV cross-identity reenactment | AUCON: 0.805 -> 0.873 | Helped |
Closest papers by meaning
- Hierarchical Cross-Modal Talking Face Generation With Dynamic Pixel-Wise Loss (CVPR 2019 · similarity 0.90)
- High-Fidelity and Freely Controllable Talking Head Video Generation (CVPR 2023 · similarity 0.90)
- IM-Portrait: Learning 3D-aware Video Diffusion for Photorealistic Talking Heads from Monocular VideosC (CVPR 2025 · similarity 0.87)
- InsTaG: Learning Personalized 3D Talking Head from Few-Second Video (CVPR 2025 · similarity 0.87)
- Occlusion-Insensitive Talking Head Video Generation via Facelet Compensation (AAAI 2025 · similarity 0.86)
- FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models (CVPR 2024 · similarity 0.86)
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.