Microfacet-based photometric stereo for surfaces with isotropic reflectance
Bibliographic record
Abstract
A precise, stable, and invertible model for surface reflectance is the key to the success of calibrated photometric stereo.Though models addressing low frequency reflectance have been proposed for a broad group of non-Lambertian surfaces, an effective solution directly targeting highly specular reflectance remains elusive.This thesis introduces an analytical isotropic microfacet-based reflectance model, based on which there is a physically interpretable approximation that can be tailored for highly specular surfaces.With this approximation, it shows that a surface recovery problem is essentially an ellipsoid of revolution fitting problem, and a fast, non-iterative and globally optimal solver is derived to attack the latter.Additionally, the introduced model also justifies the fact that, if specularity is not captured by any directional light, a very smooth surface can also appear to be diffusive.This fact leads to a design of an iterative solver for surface estimation with general isotropic reflectance, where the formulation handling specularity is taken as a special instance.Empirical results on images of both synthetic appearances and real objects can validate this model and demonstrate that the proposed solution can stably deliver the state-of-the-art performance.i My deep gratitude goes to my thesis adviser professor Michael Langer for his guidance on my thesis work and for opening the door for me to the joyful research experience in computer vision.The days I spent at School of Computer Science of McGill has made a significant impact on a
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.004 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| 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 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".