Detection of inconsistency between shape and motion in realistic female and male animation
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
Capturing the motion of a person and retargeting it to a virtual character with a different body shape is common practice in computer animation. This inconsistency between motion and shape often makes animations look unrealistic. It remains unclear which aspects of an animation affect how realistic it is perceived. Previous research has found detection of the inconsistency between motion and shape in biometric virtual characters to be at chance level for actions that involve object manipulation. Here, we test whether similar results are obtained for actions not involving objects and compare the detection of inconsistency in realistic female and male animation for actions with and without object manipulation. For creating our stimuli, we used the animations of five pairs of female and male performers with large differences in body weight from the bmlRUB database when throwing a ball, lifting a box, jumping, and walking. For each actor pair, we created inconsistent animations by combining the body shape from one actor with the motion from the other actor. For the consistent stimuli, the body shape and motion came from the same actor. In each trial of the experiment, participants observed one consistent and one inconsistent animation and selected which of the two they perceived to be inconsistent. Our results showed that for both female and male animations, participants’ detection rate was above chance for walking, and was at chance level for throwing. For lifting and jumping, the detection rate was at chance level for female animations and above chance level for male animations. Overall, detection rate was low which is promising news for realistic human animations but tended to be higher for male animations. Future research should investigate a broader range of actions to determine which are perceptually most affected by motion retargeting.
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