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 Videos

Simultaneous structure and texture image inpainting.

Marcelo Bertalmio1, Luminita Vese, Guillermo Sapiro

  • 1Dept. de Tecnologia, Univ. of Pompeu-Fabra, Barcelona, Spain.

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|February 2, 2008
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

An Evidence-Grounded Research Assistant for Functional Genomics and Drug Target Assessment.

bioRxiv : the preprint server for biology·2026
Same author

A wearable-based aging clock associates with disease and behavior.

Nature communications·2025
Same author

A Neural Model for V1 That Incorporates Dendritic Nonlinearities and Backpropagating Action Potentials.

The Journal of neuroscience : the official journal of the Society for Neuroscience·2025
Same author

Use of computer vision analysis for labeling inattention periods in EEG recordings with visual stimuli.

Scientific reports·2025
Same author

Peer support: Current status and future opportunities for college mental health promotion.

Journal of American college health : J of ACH·2025
Same author

Validation of a Mobile App for Remote Autism Screening in Toddlers.

NEJM AI·2025
Same journal

Style-Aware Contrastive Test-Time Adaptation: A Dual-Cache Model for Robust Vision-Language Alignment.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Semantic Frame Interpolation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Physics-Guided Cross-Modal Decoupling with Test-Time Adaptation for Hyperspectral Image Restoration.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
See all related articles

This paper introduces a novel algorithm for simultaneously filling missing image data by decomposing images into structure and texture components. This approach effectively reconstructs both image structure and texture for improved image inpainting and synthesis.

Area of Science:

  • Computer Vision
  • Image Processing
  • Digital Signal Processing

Background:

  • Image inpainting and texture synthesis are crucial for reconstructing missing image data.
  • Existing methods often struggle to simultaneously address both structural and textural information effectively.
  • A unified approach is needed to handle diverse image characteristics in missing regions.

Purpose of the Study:

  • To present a novel algorithm for simultaneous filling-in of texture and structure in missing image regions.
  • To combine image decomposition, inpainting, and texture synthesis for enhanced image reconstruction.
  • To demonstrate the advantages of the proposed approach on real-world images.

Main Methods:

  • Decompose the image into two functions: a bounded variation function for structure and a texture/noise function.

Related Experiment Videos

  • Reconstruct the structure component using image inpainting algorithms.
  • Reconstruct the texture component using texture synthesis techniques.
  • Recombine the reconstructed components to form the final image.

    • Main Results:

    • The algorithm successfully fills in missing image information by addressing both structure and texture simultaneously.
    • Demonstrated superior performance compared to methods that handle structure and texture separately.
    • Examples on real images validate the effectiveness and advantages of the proposed combined approach.

    Conclusions:

    • The proposed method offers a robust solution for image inpainting by integrating decomposition, inpainting, and texture synthesis.
    • This unified approach allows for the simultaneous application of specialized algorithms suited for different image characteristics.
    • The technique shows significant promise for various image restoration and manipulation applications.