MétaCan
Menu
Back to cohort
Record W4390190371 · doi:10.1109/iccvw60793.2023.00092

TransInpaint: Transformer-based Image Inpainting with Context Adaptation

2023· article· en· W4390190371 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.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicGenerative Adversarial Networks and Image Synthesis
Canadian institutionsÉcole de Technologie Supérieure
Fundersnot available
KeywordsInpaintingArtificial intelligenceComputer scienceComputer visionTransformerEncoderImage (mathematics)Image texturePattern recognition (psychology)Filling-inImage processingEngineering

Abstract

fetched live from OpenAlex

Image inpainting aims to generate realistic content for missing regions of an image. Existing methods often struggle to produce visually coherent content for missing regions of an image, which results in blurry or distorted structures around the damaged areas. These methods rely on surrounding texture information and have difficulty in generating content that harmonizes well with the broader context of the image. To address this limitation, we propose a novel model that generates plausible content for missing regions while ensuring that the generated content is consistent with the overall context of the original image. In particular, we introduce a novel context-adaptive transformer for image inpainting (TransInpaint) that relies on the visible content and the position of the missing regions. Additionally, we design a texture enhancement network that combines skip features from the encoder with the coarse features produced by the generator, yielding a more comprehensive and robust representation of image content. Based on extensive evaluations on challenging datasets, our proposed TransInpaint outperforms the cutting-edge generative models for image inpainting in terms of quality, textures, and structures.

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: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.863
Threshold uncertainty score0.430

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 studies0.0000.000
Scholarly communication0.0000.001
Open science0.0000.000
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 head0.018
GPT teacher head0.213
Teacher spread0.195 · 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