Research map / 3D vision / Face and shape
MemoryTalker: Personalized Speech-Driven 3D Facial Animation via Audio-Guided Stylization
Hyung Kyu Kim, Sangmin Lee, Hak Gu Kim
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 1-stage motion memory training (ablation) | MemoryTalker baseline · VOCASET | LVE (x1e-5): 0.460 -> 0.313 | Improved |
| add 1-stage motion memory training (ablation) | MemoryTalker baseline · VOCASET | FVE (x1e-6): 0.638 -> 0.531 | Improved |
| add 2-stage stylized motion memory (ablation) | MemoryTalker 1-stage · VOCASET | LVE (x1e-5): 0.313 -> 0.293 | Improved |
| add 2-stage stylized motion memory (ablation) | MemoryTalker 1-stage · VOCASET | FVE (x1e-6): 0.531 -> 0.506 | Improved |
| add lip vertex loss L_lip (ablation) | MemoryTalker · VOCASET | LDTW (x1e-5): 0.435 -> 0.418 | Improved |
| add triplet speaking style loss L_style (ablation) | MemoryTalker · VOCASET | LDTW (x1e-5): 0.431 -> 0.418 | Improved |
| use two-stage instead of end-to-end training (ablation) | MemoryTalker · VOCASET | FID (x1e-1): 3.142 -> 3.045 | Improved |
| use mel-spectrogram instead of ASR features for style encoder (ablation) | MemoryTalker · VOCASET | LVE (x1e-5): 0.300 -> 0.293 | Improved |
| use audio-only style instead of mesh-driven style | MemoryTalker · VOCASET | FVE (x1e-6): 0.673 -> 0.506 | Improved |
| vary memory slot size 16, 24, 32, 48, 64 (ablation) | MemoryTalker · VOCASET | LVE | Mixed |
| use MemoryTalker instead of UniTalker | UniTalker · BIWI Test-B | LVE (x1e-4): 0.196 -> 0.187 | Improved |
| use MemoryTalker on seen identities instead of UniTalker | UniTalker · BIWI Test-A (seen identities) | LVE (x1e-3): 0.283 -> 0.266 | Improved |
Later papers that compared with this method
1 later accepted paper reports MemoryTalker as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Seeing Speech: Learning Visible Articulatory Dynamics for Speech-Driven 3D Facial Animation (NeurIPS 2026 · better on 5 of 5 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CodeTalker — CodeTalker: Speech-Driven 3D Facial Animation With Discrete Motion Prior (CVPR 2023) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Probabilistic Speech-Driven 3D Facial Motion Synthesis: New Benchmarks Methods and Applications (CVPR 2024 · similarity 0.91)
- Mimic: Speaking Style Disentanglement for Speech-Driven 3D Facial Animation (AAAI 2024 · similarity 0.91)
- DEEPTalk: Dynamic Emotion Embedding for Probabilistic Speech-Driven 3D Face Animation (AAAI 2025 · similarity 0.90)
- ProsodyTalker: 3D Visual Speech Animation via Prosody Decomposition (AAAI 2025 · similarity 0.90)
- FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models (CVPR 2024 · similarity 0.89)
- Seeing Speech: Learning Visible Articulatory Dynamics for Speech-Driven 3D Facial Animation (NeurIPS 2026 · similarity 0.89)
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.
