MétaCan
Menu
Back to cohort
Record W2588581370 · doi:10.1109/tcsii.2017.2669866

Iterative Graph-Based Filtering for Image Abstraction and Stylization

2017· article· en· W2588581370 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
fundA Canadian funder is recorded on the work.

Bibliographic record

VenueIEEE Transactions on Circuits & Systems II Express Briefs · 2017
Typearticle
Languageen
FieldComputer Science
TopicImage Enhancement Techniques
Canadian institutionsConcordia University
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsComputer scienceGraphArtificial intelligenceIterative methodComputer visionFilter (signal processing)Pattern recognition (psychology)AlgorithmTheoretical computer science

Abstract

fetched live from OpenAlex

In this brief, motivated by the recent advances in graph signal processing, we address the problem of image abstraction and stylization. A novel unified graph-based multi-layer framework is proposed to perform iterative filtering without requiring any weight updates. The proposed graph-based filtering approach is shown to be superior to other existing methods due to iteratively using the filtered Laplacian in order to enhance the smoothened image signal at each layer. In order to render real images into painterly style ones and create a simple stylized format from color images, the low-contrast regions of an image are first smoothened using the proposed iterative graph filters in either vertex or spectral domains. The abstracted image is then quantized and sharpened using the proposed iterative highpass graph filter. The effectiveness of the graph-based image stylization method is verified through several experiments. It is shown that the proposed method can yield significantly improved visual quality for stylized images as compared to other existing methods.

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.

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)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Science and technology studies, Scholarly communication
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: Bench or experimental
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.984
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
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 head0.026
GPT teacher head0.278
Teacher spread0.252 · 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