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

Total Internal Reflection Fluorescence Microscopy01:05

Total Internal Reflection Fluorescence Microscopy

Total internal reflection fluorescence microscopy or TIRF is an advanced microscopic technique used to visualize fluorophores in samples close to a solid surface with a higher refractive index, such as a glass coverslip. TIRF only allows fluorophores in proximity to the solid surface to be excited. When light from a medium with a lower refractive index (such as air) hits the glass coverslip at a critical angle, the light undergoes total internal reflection stead of passing through the glass.

You might also read

Related Articles

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

Sort by
Same author

<i>In situ</i> glycosylation-directed H-aggregation of Type I photosensitizers for synergistic biofilm eradication and promoting diabetic wound healing.

Chemical science·2026
Same author

The microbiota-lymphocyte protective axis (MLPA): a novel paradigm for overcoming radiation-induced lymphopenia (RIL) and potentiating the efficacy of tumor immuno-combination therapy.

Cancer immunology, immunotherapy : CII·2026
Same author

Leaf Age-Dependent Volatile Cues Influence Host Location and Oviposition Preference of <i>Obolodiplosis robiniae</i> on <i>Robinia pseudoacacia</i>.

Insects·2026
Same author

Explainable, Generative and Agentic Artificial Intelligence for the Peripheral Blood Film.

International journal of laboratory hematology·2026
Same author

Cross-Level Topological Framework: Learning Explainable Region-Channel Representations from EEG Signals for Emotional Decoding.

IEEE journal of biomedical and health informatics·2026
Same author

Early prediction of severe Omicron pneumonia using a multimodal a.i. model integrating delta CT radiomics and laboratory indicators.

Scientific reports·2026

Related Experiment Video

Updated: May 31, 2026

Diffuse Reflectance Spectroscopy: Getting the Capillary Refill Test Under One's Thumb
06:50

Diffuse Reflectance Spectroscopy: Getting the Capillary Refill Test Under One's Thumb

Published on: December 2, 2017

Single-Image Reflection Removal via Iterative Prompt Learning of Reflection Level.

Binbin Song, Jiantao Zhou, Shuning Xu

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |May 28, 2026
    PubMed
    Summary

    This study introduces a new Iterative Reflection Level Reduction (IRLR) framework for single-image reflection removal (SIRR). The method uses learnable prompts and iterative training to significantly improve reflection removal performance and generalization.

    More Related Videos

    Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition
    09:37

    Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

    Published on: August 18, 2022

    Measuring Spatially- and Directionally-varying Light Scattering from Biological Material
    11:57

    Measuring Spatially- and Directionally-varying Light Scattering from Biological Material

    Published on: May 20, 2013

    Related Experiment Videos

    Last Updated: May 31, 2026

    Diffuse Reflectance Spectroscopy: Getting the Capillary Refill Test Under One's Thumb
    06:50

    Diffuse Reflectance Spectroscopy: Getting the Capillary Refill Test Under One's Thumb

    Published on: December 2, 2017

    Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition
    09:37

    Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

    Published on: August 18, 2022

    Measuring Spatially- and Directionally-varying Light Scattering from Biological Material
    11:57

    Measuring Spatially- and Directionally-varying Light Scattering from Biological Material

    Published on: May 20, 2013

    Area of Science:

    • Computer Vision
    • Artificial Intelligence
    • Image Processing

    Background:

    • Single-image reflection removal (SIRR) is crucial for recovering underlying background layers from images contaminated by reflections.
    • Existing deep learning methods for SIRR often overlook the impact of negative training samples and descriptive prompts for reflection severity, limiting performance and generalization.
    • There is a need for advanced training frameworks that can effectively handle varying degrees of reflection interference.

    Purpose of the Study:

    • To develop a novel training framework that synergistically combines learnable prompts and image data for optimizing deep SIRR networks.
    • To address the underexplored roles of negative training samples and reflection severity prompts in existing SIRR approaches.
    • To enhance the performance and generalization capabilities of single-image reflection removal techniques.

    Main Methods:

    • Proposed an Iterative Reflection Level Reduction (IRLR) framework, comprising a Restoration Network Training Module (RNTM) and a Reflection Level Learning Module (RLLM).
    • RNTM predicts the background layer guided by prompts from RLLM, while RLLM refines these prompts based on RNTM's outputs, enabling iterative reduction of reflection levels.
    • Introduced a reflection-level-aware strategy for adaptive supervision and constructed a dedicated dataset for pretraining reflection-level prompts.

    Main Results:

    • The proposed IRLR framework significantly outperforms state-of-the-art methods in single-image reflection removal.
    • Achieved average performance improvements of 0.82 dB in Peak Signal-to-Noise Ratio (PSNR) and 0.0120 in Structural Similarity Index Measure (SSIM) across multiple datasets.
    • Demonstrated enhanced generalization capability compared to existing deep SIRR approaches.

    Conclusions:

    • The synergistic combination of learnable prompts and iterative training within the IRLR framework effectively addresses limitations in current SIRR methods.
    • The proposed approach offers a significant advancement in restoring background layers from reflection-contaminated images.
    • The method shows strong potential for practical applications requiring high-quality image restoration.