Research map / Video / Video generation
Every Smile Is Unique: Landmark-Guided Diverse Smile Generation
Read the paperCheck 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 |
|---|---|---|---|
| use landmark sequences instead of face-image embeddings (ablation) | CMM-Net (CRA-Net comparison) · UvA-NEMO Spont. | SSIM: 0.553 -> 0.854 | Helped |
| use landmark sequences instead of face-image embeddings (ablation) | CMM-Net (CRA-Net comparison) · UvA-NEMO Posed | SSIM: 0.471 -> 0.827 | Helped |
| use landmark sequences instead of face-image embeddings (ablation) | CMM-Net (CRA-Net comparison) · DISFA Spont. | SSIM: 0.749 -> 0.747 | No clear effect |
| use landmark sequences instead of face-image embeddings (ablation) | CMM-Net (CRA-Net comparison) · DISFA+ Posed | SSIM: 0.839 -> 0.810 | Hurt |
| use landmark sequences instead of face-image embeddings (ablation) | CMM-Net (CRA-Net comparison) · UvA-NEMO Spont. | AU curve distance: 4.452 -> 2.234 | Helped |
| use landmark sequences instead of face-image embeddings (ablation) | CMM-Net (CRA-Net comparison) · UvA-NEMO Posed | AU curve distance: 9.783 -> 1.472 | Helped |
| use landmark sequences instead of face-image embeddings (ablation) | CMM-Net (CRA-Net comparison) · DISFA | AU curve distance: 2.400 -> 2.035 | Helped |
| use landmark sequences instead of face-image embeddings (ablation) | CMM-Net (CRA-Net comparison) · DISFA+ | AU curve distance: 9.931 -> 1.812 | Helped |
| generate multiple modes using the multi-mode LSTMs (ablation) | CMM-Net · UvA-NEMO posed smile example | visual diversity | Helped |
| condition the landmark generator on expression labels (ablation) | CMM-Net · UvA-NEMO smile sequences | expression-specific dynamics | Helped |
Closest papers by meaning
- TEASER: Token Enhanced Spatial Modeling for Expressions Reconstruction (ICLR 2025 · similarity 0.85)
- DEEPTalk: Dynamic Emotion Embedding for Probabilistic Speech-Driven 3D Face Animation (AAAI 2025 · similarity 0.85)
- SMILE: Infusing Spatial and Motion Semantics in Masked Video Learning (CVPR 2025 · similarity 0.84)
- FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantization (CVPR 2024 · similarity 0.84)
- 3D Facial Expressions through Analysis-by-Neural-Synthesis (CVPR 2024 · similarity 0.84)
- Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion Model (ICML 2025 · similarity 0.83)
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.