Vertex-Based Facial Animation Transfer System for Models with Different Topology; A Tool for Maya
Bibliographic record
Abstract
The transfer of realistic facial animations between two 3D models is limited and/or too cumbersome for general use.In this paper, we target transfer of facial expression animation and facial animation sequences within the 3D software modelling tool Autodesk Maya to eliminate some of the issues that animators come across while creating animations, along with making their process much faster and efficient.While current animation transferring processes in Maya work well, the downfall of these methods is that they only work properly if the source and target models have same vertex count, vertex order, and topology; in other words, the model has to be the same, and there is a lot of manual work required beforehand.We propose a system that eliminates these issues in order to achieve smooth and realistic animations while maintaining a 3D modelagnostic focus; the system features facial animation transfer between different models, i.e. different topology, vertex ordering and vertex count.The system is purely vertexbased; this helps to speed up the process since no rigging is necessary.Furthermore, the system reduces the amount of manual effort in order to accomplish a smooth and realistic facial animation. ICP -Iterative Closest Point FACS -Facial Action Coding System RBF -Radial basis Function LBS -Linear Blend Skinning AU -Action Unit kCCA -kernel Canonical Correlation Analysis CCA -Canonical Correlation Analysis FRGC -Face Recognition Grand Challenge AVO -Audio-Visual Objects FAPS -Face Animation Parameters k-NN -k-Nearest Neighbour SDR -Software Defined Radio NET -Neighbour-Expression Transfer MU -Motion Unit MUP -Motion Unit Parameters DPCM -Differential Pulse Code Modulation DCT -Discrete Cosine Transform BIFS -Binary Format for Scenes FFD -Free Form Deformation
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.032 | 0.007 |
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".