MétaCan
Menu
Back to cohort
Record W2767925918 · doi:10.5594/jmi.2017.2745378

Quality Control of Stereoscopic 3D Compositing Using Half-Occlusion Geometry

2017· article· en· W2767925918 on OpenAlexfundno aff
Jonathan Bouchard, James J. Clark

Bibliographic record

VenueSMPTE Motion Imaging Journal · 2017
Typearticle
Languageen
FieldComputer Science
TopicAdvanced Vision and Imaging
Canadian institutionsnot available
FundersMcGill University
KeywordsCompositingStereoscopyConsistency (knowledge bases)Computer scienceComputer visionAutomationQuality (philosophy)Artificial intelligencePerceptionComputer graphics (images)EngineeringImage (mathematics)Mechanical engineeringPhysics

Abstract

fetched live from OpenAlex

Proper depth perception and visual comfort of stereoscopic 3D (S3D) movies are greatly influenced by the consistency of depth cues. While a formal geometrical definition of stereo consistency can be derived, it is not made available to post-production artists through the commonly used compositing tools. This lack of automation is likely to let inconsistencies slip through quality control. In this paper, we show that many defects that can be introduced through S3D compositing can be detected in a unified manner by studying the geometry of half-occlusion (HO, regions visible in only one of the S3D views). The efficiency of the HO-based detection system is demonstrated on five commonly encountered problems: local and global pseudoscopy, rotoscopy mismatches, layer ordering issues, and window violations.

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 imitation

Not 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.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesScience and technology studies
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.865
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0020.000
Scholarly communication0.0010.002
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.031
GPT teacher head0.351
Teacher spread0.320 · 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 teacher head, not a consensus.

Study designSimulation or modeling
Domainnot available
GenreMethods

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

Citations1
Published2017
Admission routes1
Has abstractyes

Explore more

Same venueSMPTE Motion Imaging JournalSame topicAdvanced Vision and ImagingFrench-language works237,207