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: Jul 13, 2026

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline
09:27

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

Published on: January 30, 2019

Image Restoration via Multi-domain Learning.

Xingyu Jiang, Ning Gao, Xiuhui Zhang

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |July 7, 2026
    PubMed
    Summary

    This study introduces a novel Transformer-based framework for image restoration, integrating multi-domain learning to address various image degradations. The new model enhances performance and efficiency for tasks like dehazing and deblurring.

    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

    Global Modeling Matters: A Fast, Lightweight, and Effective Baseline for Efficient Image Restoration.

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

    MTRAG: Multi-Target Referring and Grounding via Hybrid Semantic-Spatial Integration.

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

    You Only Look One Step: Accelerating Backpropagation in Diffusion Sampling With Gradient Shortcuts.

    IEEE transactions on pattern analysis and machine intelligence·2025
    Same author

    Image-to-Image Bayesian Flow Networks With Structurally Informative Priors.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025
    Same author

    Expectation-Maximization-Based Optimization of Neural Quantum States for Ab Initio Quantum Chemistry.

    Journal of chemical theory and computation·2025
    Same author

    Bi-level identification of governing equations for nonlinear physical systems.

    Nature computational science·2025

    Area of Science:

    • Computer Vision
    • Image Processing
    • Artificial Intelligence

    Background:

    • Natural images frequently suffer from degradations due to atmospheric and imaging conditions.
    • Image restoration is crucial for enhancing image quality but faces challenges with complex Transformer models.
    • Existing methods often overlook commonalities across different degradation types.

    Purpose of the Study:

    • To develop a novel, efficient image restoration framework.
    • To integrate multi-domain learning into Transformer architectures for improved restoration.
    • To address the limitations of current methods in handling diverse image degradations.

    Main Methods:

    • A novel restoration framework integrating multi-domain learning into Transformer architectures.

    Related Experiment Videos

    Last Updated: Jul 13, 2026

    Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline
    09:27

    Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

    Published on: January 30, 2019

  • A Spatial-Wavelet-Fourier multi-domain structure in the Token Mixer for multi-receptive field modeling.
  • Multi-scale learning in the Feed-Forward Network to fuse multi-domain features.

    • Main Results:

    • The proposed model demonstrates superior performance across ten diverse image restoration tasks.
    • Achieved a favorable trade-off between restoration quality, model size, computational cost, and inference speed.
    • Outperformed state-of-the-art methods in tasks including dehazing, deblurring, and low-light enhancement.

    Conclusions:

    • The proposed multi-domain learning approach effectively enhances Transformer-based image restoration.
    • The framework offers an efficient and high-performing solution for various image restoration challenges.
    • This work provides a new direction for developing more robust and versatile image restoration models.