Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Apr 20, 2026

Circumscribed Capsular Infarct Modeling Using a Photothrombotic Technique
08:25

Circumscribed Capsular Infarct Modeling Using a Photothrombotic Technique

Published on: June 2, 2016

8.3K

Context-aware patch-based image inpainting using Markov random field modeling.

Tijana Ružić, Aleksandra Pižurica

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |November 25, 2014
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    Combining deep learning with statistical shape modelling enables automated lower limb measurements with observer-level reliability using weight-bearing computed tomography.

    Journal of experimental orthopaedics·2026
    Same author

    Deconver: A Deconvolutional Network for Medical Image Segmentation.

    IEEE journal of biomedical and health informatics·2025
    Same author

    Quantifying 3D foot and ankle alignment using an AI-driven framework: a pilot study.

    Skeletal radiology·2025
    Same author

    Development and validation of a fully automated tool to quantify 3D foot and ankle alignment using weight-bearing CT.

    Gait & posture·2024
    Same author

    PCGen: A Fully Parallelizable Point Cloud Generative Model.

    Sensors (Basel, Switzerland)·2024
    Same author

    GPU Rasterization-Based 3D LiDAR Simulation for Deep Learning.

    Sensors (Basel, Switzerland)·2023

    This study presents a new context-aware image inpainting method using textural descriptors and a top-down splitting procedure. It significantly accelerates and improves patch-based inpainting, enhancing scratch, text, and object removal.

    Area of Science:

    • Computer Vision
    • Image Processing

    Background:

    • Patch-based image inpainting methods often face challenges with efficiency and accuracy.
    • Guiding patch search with contextual information is crucial for effective inpainting.

    Purpose of the Study:

    • To introduce a general, context-aware approach for accelerating patch-based image inpainting.
    • To enhance the performance of existing inpainting techniques, particularly global methods using Markov Random Field (MRF) priors.

    Main Methods:

    • A novel top-down image splitting procedure based on context to define variable-sized blocks.
    • Utilizing textural descriptors to guide the search for matching patches within nonlocal image regions.
    • Applying the approach to global image inpainting with MRF priors and solving via efficient low-complexity inference.

    Related Experiment Videos

    Last Updated: Apr 20, 2026

    Circumscribed Capsular Infarct Modeling Using a Photothrombotic Technique
    08:25

    Circumscribed Capsular Infarct Modeling Using a Photothrombotic Technique

    Published on: June 2, 2016

    8.3K

    Main Results:

    • Demonstrated effectiveness in various inpainting applications, including scratch, text, and object removal.
    • Significant improvements in both speed and performance compared to traditional methods.
    • Validation of the approach's ability to accelerate and enhance related global MRF-based inpainting methods.

    Conclusions:

    • The proposed context-aware patch-based inpainting approach offers a general and effective solution.
    • The method significantly enhances the efficiency and performance of image inpainting tasks.
    • This technique provides a valuable advancement for digital image restoration and manipulation.