Synthese d'effets de deterioration pour un rendu realiste
Bibliographic record
Abstract
During the last decade, the level of realism expected for synthetic images used in video games, animated movies, or virtual reality systems has increased considerably. To properly replicate real world situations, realistic rendering systems must consider an impressive amount of detail. Among these details, effects produced by aging such as rust or scratches are particularly hard to handle, require a lot of manual work, and adding them is obviously time-consuming. Existing methods addressing this problem, such as physically-based and empirical simulations, are not suitable for artists since they require the manipulation of complex physical parameters, and are not polyvalent since they are often designed for a specific type of aging effect. The main objective of this research project is to provide artists with a versatile framework to generate new aging effects based on an image containing an example of the desired effect. To achieve this, a constrained texture synthesis algorithm has been adapted to such a context to produce new similar effects. From an aging recipe based on local properties, such as accessibility and curvature, the proposed approach allows an artist to define a general pattern characterizing the weathering of an object. Then, this recipe can be applied either to an object to generate one or more similar instances, yet not identical, or to several different objects to produce comparable aging. The last constituent of the project is to alter the previously defined process to make it independent of the sample color provided by the user. The standard approach exploiting RGB channels is replaced by the synthesis of an aging intensity. The system then interprets this intensity using control points defined by the user and a custom shader executed by the application to produce a color to display for each pixel forming the aging effects. The results obtained from the different contributions of this research project are very promising. The proposed approach produces high-quality results, and can greatly improve the realism of synthetic images. The process is very versatile since it works on a wide variety of aging effects and materials. Its use is perfectly suitable for artists and production studios since its parameters are simple and intuitive. Finally, required computation times are minimal and thus fit well in an iterative creation process.
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 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) | 0.003 | 0.001 |
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 teacher head, 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".