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: May 10, 2026

High-plex Imaging using Spectral Confocal Microscopy to Minimize Non-specific Tissue Fluorescence
10:28

High-plex Imaging using Spectral Confocal Microscopy to Minimize Non-specific Tissue Fluorescence

Published on: October 28, 2025

Face illumination manipulation using a single reference image by adaptive layer decomposition.

Xiaowu Chen, Hongyu Wu, Xin Jin

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |June 29, 2013
    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

    Multimodal analytical strategy for revealing the related compounds of color variation in Salvia miltiorrhiza after sweating.

    Journal of pharmaceutical and biomedical analysis·2026
    Same author

    An Environmentally Tolerant 5A Hydrogel with Photothermal Effect for Frostbite Treatment.

    Gels (Basel, Switzerland)·2026
    Same author

    Clinical Features and Key Prognostic Indicators of Growth Hormone-Secreting Pituitary Adenomas: A Retrospective Study of 344 Cases.

    Current oncology (Toronto, Ont.)·2026
    Same author

    Eravacycline-Cefiderocol Combination Therapy for Carbapenem-Resistant <i>Acinetobacter baumannii</i> Infective Endocarditis: A Case Report and Brief Review of the Literature.

    Infection and drug resistance·2026
    Same author

    CT-based habitat analysis combined with multi-channel deep learning for predicting early recurrence after pancreatic cancer resection: a multicenter study.

    Journal of translational medicine·2026
    Same author

    The Spatiotemporal Genetic Architecture of Seed Vigor in Upland Cotton.

    Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026

    This study introduces an image-based framework for face relighting and delighting using adaptive layer decomposition. The method effectively transfers illumination from a reference image to a target face without needing 3D information.

    Area of Science:

    • Computer Vision
    • Image Processing
    • Computer Graphics

    Background:

    • Realistic manipulation of facial illumination is challenging.
    • Existing methods often require 3D face models or detailed scene information.
    • Controlling illumination effects on human faces from single images is an active research area.

    Purpose of the Study:

    • To propose a novel image-based framework for human face relighting and delighting.
    • To enable illumination transfer using only a single reference image.
    • To achieve robust performance without requiring 3D geometry or material information.

    Main Methods:

    • Adaptive layer decomposition using weighted least squares (WLS) filter to separate large-scale and detail layers.
    • Guided filter with adaptive smoothing for transferring illumination effects.

    Related Experiment Videos

    Last Updated: May 10, 2026

    High-plex Imaging using Spectral Confocal Microscopy to Minimize Non-specific Tissue Fluorescence
    10:28

    High-plex Imaging using Spectral Confocal Microscopy to Minimize Non-specific Tissue Fluorescence

    Published on: October 28, 2025

  • Introduction of similar reflectance prior for normalizing non-normal lighting conditions (face delighting).

    • Main Results:

    • Convincing face relighting and delighting results achieved on diverse datasets.
    • The framework effectively normalizes illumination and transfers effects from reference images.
    • Preservation of facial identification structure and skin color demonstrated.

    Conclusions:

    • The proposed framework offers a robust and efficient solution for image-based face illumination manipulation.
    • It outperforms previous methods by being less sensitive to geometry differences.
    • Enables realistic control over facial appearance under varying lighting conditions.