Research map / Image generation / Editing and style transfer
FLNet: Landmark Driven Fetching and Learning Network for Faithful Talking Facial Animation Synthesis
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 |
|---|---|---|---|
| Combine landmark-guided fetching from five source images with appearance-based learning | Talking facial animation synthesis · TIMIT | L1: 7.99 vs 8.31 | Helped |
| Combine landmark-guided fetching from five source images with appearance-based learning | Talking facial animation synthesis · TIMIT | FID: 17.07 vs 30.50 | Helped |
| Combine landmark-guided fetching from five source images with appearance-based learning | Talking facial animation synthesis · FaceForensics | L1: 10.20 vs 11.05 | Helped |
| Combine landmark-guided fetching from five source images with appearance-based learning | Talking facial animation synthesis · FaceForensics | FID: 20.62 vs 23.98 | Helped |
| Use five source images rather than one (ablation) | FLNet · Talking facial animation | visual detail fidelity | Helped |
| Use five source images rather than three (ablation) | FLNet · Talking facial animation | visual detail fidelity | Helped |
| Add the warping-based fetching stream (ablation) | Appearance-only FLNet · Talking facial animation | visual detail fidelity | Helped |
| Add the appearance-based learning stream (ablation) | Warping-only FLNet · Talking facial animation | hidden-region fidelity | Helped |
Closest papers by meaning
- Synergizing Motion and Appearance: Multi-Scale Compensatory Codebooks for Talking Head Video Generation (CVPR 2025 · similarity 0.87)
- MimicTalk: Mimicking a personalized and expressive 3D talking face in minutes (NeurIPS 2024 · similarity 0.87)
- Faces that Speak: Jointly Synthesising Talking Face and Speech from Text (CVPR 2024 · similarity 0.87)
- FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio (CVPR 2024 · similarity 0.87)
- Mimic: Speaking Style Disentanglement for Speech-Driven 3D Facial Animation (AAAI 2024 · similarity 0.86)
- Probabilistic Speech-Driven 3D Facial Motion Synthesis: New Benchmarks Methods and Applications (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.