Exaggeration of extremely detailed 3d faces
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Exaggeration is often used in art and entertainment to capture the interest and attention of an audience. We present an approach to automatically exaggerate the distinctive features of 3D faces which contain skin detail down to the pores. Mesh adaptation and model simplification are used to produce two low resolution approximations of the face. The detail of the original high resolution face is captured by achieving two sets of model parameterizations: the high resolution face with respect to the face obtained using model simplification (simplified model) and the simplified model with respect to the model obtained using mesh adaptation (working model). The working model is exaggerated using a vector-based algorithm that automatically identifies the prominent features with respect to an average face. The resulting model and the parameterizations drive a two-stage model reconstruction process that generates the high resolution exaggerated model which preserves the original level of detail. The results of our testing show that the proposed methodology is capable of producing exaggerated models from an initial face model comprising roughly 2,000,000 triangles.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it