Towards Generative and Expressive 3D Facial Animations
Bibliographic record
Abstract
Expressive 3D facial animation is a key component for realistic avatars in immersive XR. While face motion capture can produce high-quality results, this approach is impractical in settings without on-device capture hardware for real-time tracking and does not address the growing demand for conversational AI avatars. In parallel, there is rapid progress in 2D talking head generation, producing expressive videos of faces driven by audio. However, these methods are for flat-screen media and cannot be directly applied to XR avatars. In this work, we leverage advances in 2D generative methods and explore a video-to-3D facial animation pipeline. We extract ARKit blendshape parameters and head poses from generated or real videos, and apply them to 3D rigs. To improve efficiency, we further investigate training an audio-to-rig model directly, bypassing pixel-space generation. Early experiments demonstrate both feasibility and challenges. We discuss how such generative pipelines could enable flexible, emotionally expressive avatars for XR, with applications to conversational AI, NPCs, and telepresence.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".