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 Concept Videos

Deconvolution01:20

Deconvolution

459
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
459
Tagging and Fusion Proteins01:24

Tagging and Fusion Proteins

8.2K
Proteins are involved in several cellular processes and biochemical reactions. Analyzing a specific protein of interest requires it to be isolated from the other proteins in the cell. This is achieved by overexpressing the specific gene in a suitable host to produce large quantities of the target protein. A tag or label is recombined with the gene to produce a fusion protein containing the target protein and the tag. The tags on these fusion proteins can then be used for easy detection and...
8.2K

You might also read

Related Articles

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

Sort by
Same author

GEOMETRY OF LONG-TAILED REPRESENTATION LEARNING: REBALANCING FEATURES FOR SKEWED DISTRIBUTIONS.

... International Conference on Learning Representationsยท2026
Same author

Setup-Independent Full Projector Compensation.

IEEE transactions on visualization and computer graphicsยท2026
Same author

DiffPC: Diffusion-Based Projector Photometric Compensation.

IEEE transactions on visualization and computer graphicsยท2026
Same author

Probing uric acid-related prognostic genes and their molecular mechanisms in prostate cancer based on transcriptomic data.

Discover oncologyยท2026
Same author

Allicin suppressed bladder cancer cell biological activities via regulation of the miR-26b-5p/PTEN axis in an <i>in vitro</i> study.

Archives of medical science : AMSยท2026
Same author

Cortical layer multi-parameter analysis of neurovascular impairments in AD/ADRD rodent model with in vivo optical imaging.

Translational neurodegenerationยท2025

Related Experiment Video

Updated: Dec 13, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

879

U2Fusion: A Unified Unsupervised Image Fusion Network.

Han Xu, Jiayi Ma, Junjun Jiang

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |August 6, 2020
    PubMed
    Summary

    This study introduces U2Fusion, an unsupervised deep learning network for image fusion. It unifies multi-modal, multi-exposure, and multi-focus tasks, eliminating the need for ground-truth data.

    More Related Videos

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    685

    Related Experiment Videos

    Last Updated: Dec 13, 2025

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    879
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    685

    Area of Science:

    • Computer Vision
    • Artificial Intelligence
    • Image Processing

    Background:

    • Deep learning for image fusion often requires extensive labeled data and task-specific metrics.
    • Existing methods struggle to maintain performance across diverse fusion tasks (e.g., multi-modal, multi-exposure, multi-focus).

    Purpose of the Study:

    • To propose a unified and unsupervised deep learning framework for diverse image fusion tasks.
    • To mitigate the reliance on ground-truth data and specialized metrics in image fusion.
    • To develop a versatile model capable of handling multiple fusion scenarios without performance degradation.

    Main Methods:

    • Developed U2Fusion, a novel end-to-end unsupervised image fusion network.
    • Implemented adaptive information preservation by estimating source image importance.
    • Trained the network to maintain adaptive similarity between fused results and source images.

    Main Results:

    • U2Fusion effectively handles multi-modal, multi-exposure, and multi-focus image fusion within a single framework.
    • The unsupervised approach significantly reduces the need for ground-truth data and custom metrics.
    • Experimental results demonstrate the effectiveness and universality of the proposed method.

    Conclusions:

    • U2Fusion offers a unified and unsupervised solution for various image fusion challenges.
    • The network's adaptive nature allows for robust performance across different fusion tasks.
    • The release of the RoadScene dataset provides a new benchmark for infrared and visible image fusion.