Selectively-densified mesh construction for virtual environments using salient points derived from a computational model of visual attention
Bibliographic record
Abstract
A possible solution to ensure real-time interaction with virtual environments, while not visibly degrading the quality of object models is to construct selectively-densified meshes, that preserve a higher density around the regions that characterize the most the object's shape and properties. The purpose of such an approach is to aim at improving the perceived quality of the models in those areas subjected to increased observation by users. In this paper, a classical computational visual attention model is employed on images collected from multiple viewpoints over the surface of an object to identify regions that attract visual attention. A novel approach is then proposed to allow the use of this model for the detection of salient points on the surface of 3D objects, including: an iterative technique to extract salient points from the saliency map, a procedure for the selection of viewpoints for saliency computation based on the best viewpoint for an object, and a projection algorithm to find the coordinates of the identified salient points in images on the surface of the 3D object. The areas around the identified salient points are constrained at maximum resolution in a selectively-densified mesh obtained using the QSlim simplification algorithm. The results are compared with existing solutions from the literature to demonstrate the superiority of the proposed approach.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".