MétaCan
Menu
Back to cohort
Record W4285129685 · doi:10.1109/tmm.2022.3185929

Unsupervised Single-Image Reflection Removal

2022· article· en· W4285129685 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 Multimedia · 2022
Typearticle
Languageen
FieldComputer Science
TopicImage Enhancement Techniques
Canadian institutionsSimon Fraser University
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsComputer scienceArtificial intelligenceBenchmark (surveying)Convolutional neural networkReflection (computer programming)Image (mathematics)Process (computing)Deep learningFeature (linguistics)Pattern recognition (psychology)Artificial neural networkFeature extractionSupervised learningImage qualityComputer vision

Abstract

fetched live from OpenAlex

Reflections often degrade the quality of images by obstructing the background scenes. This is not desirable for everyday users, and it negatively impacts the performance of multimedia applications that process images with reflections. Most current methods for removing reflections utilize supervised learning models. These models require an extensive number of image pairs of the same scenes with and without reflections to perform well. However, collecting such image pairs is challenging and costly. Thus, most current supervised models are trained on small datasets that cannot cover the numerous possibilities of real-life images with reflections. In this paper, we propose an unsupervised method for single-image reflection removal. Instead of learning from a large dataset, we optimize the parameters of two cross-coupled deep convolutional neural networks on a target image to generate two exclusive background and reflection layers. In particular, we design a network model that embeds semantic features extracted from the input image and utilizes these features in the separation of the background layer from the reflection layer. We show through objective and subjective studies on benchmark datasets that the proposed method substantially outperforms current methods in the literature. The proposed method does not require large datasets for training, removes reflections from single images, and does not impose impractical constraints on the input images.

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 categoriesnone
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 score0.627
Threshold uncertainty score0.841

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0000.001
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 head0.028
GPT teacher head0.269
Teacher spread0.242 · 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