MétaCan
Menu
Back to cohort
Record W7132943755

Intrinsic image decomposition via deformable reflectance models

2007· dissertation· W7132943755 on OpenAlexaff
Stephen C Fung

Bibliographic record

VenueTSpace · 2007
Typedissertation
Language
FieldComputer Science
TopicImage Enhancement Techniques
Canadian institutionsCanadian HeritageUniversity of TorontoLibrary and Archives Canada
Fundersnot available
KeywordsReflectivityGenerative modelImage (mathematics)Artificial neural networkProbabilistic logicDisplacement (psychology)DecompositionImage-based lighting
DOInot available

Abstract

fetched live from OpenAlex

When looking at even a single image, humans are usually able to infer multiple characteristics of a scene, such as its lighting, reflectance, shape, and depth. However, this remains a difficult problem in computer vision due to its fundamental ambiguity. This thesis describes a generative probabilistic model aimed at describing intrinsic characteristics of a scene. Given a small repeating image pattern, called a texton, our model uses displacements to map the texton to a prototype reflectance image. The reflectance model then accounts for colour variation. We model the lighting of the scene using an image-dependent prior. A neural network trained on estimated ground-truth lighting data computes this prior. We show results of lighting and reflectance decompositions, and also show a technique of realistically replacing or inserting reflectance content into an image after learning its displacement and lighting effects.

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 imitation

Not 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.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.001
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.003
Threshold uncertainty score0.008

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0000.001
Bibliometrics0.0010.000
Science and technology studies0.0000.001
Scholarly communication0.0010.002
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0020.001

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.

Opus teacher head0.020
GPT teacher head0.387
Teacher spread0.367 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

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".

Quick stats

Citations0
Published2007
Admission routes1
Has abstractyes

Explore more

Same venueTSpaceSame topicImage Enhancement TechniquesFrench-language works237,207