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

You might also read

Related Articles

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

Sort by
Same author

Occlusion-Aware Instance Segmentation Via BiLayer Network Architectures.

IEEE transactions on pattern analysis and machine intelligence·2023
Same author

GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector.

IEEE transactions on pattern analysis and machine intelligence·2023
Same author

Minifying photometric stereo via knowledge distillation-based feature translation.

Optics express·2022
Same author

Lightweight Depth Completion Network with Local Similarity-Preserving Knowledge Distillation.

Sensors (Basel, Switzerland)·2022
Same author

Dense Pixel-Level Interpretation of Dynamic Scenes With Video Panoptic Segmentation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2022
Same author

MCDAL: Maximum Classifier Discrepancy for Active Learning.

IEEE transactions on neural networks and learning systems·2022
Same journal

A Unified and Fast-Sampling Diffusion Bridge Framework via Stochastic Optimal Control.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Robust 3D Semantic Occupancy Prediction With Calibration-Free Spatial Transformation.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Image Restoration via Multi-domain Learning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

A Comprehensive Survey on Multimodal Recommender Systems: Taxonomy, Evaluation, and Future Directions.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

Related Experiment Video

Updated: Mar 8, 2026

Determining 3D Flow Fields via Multi-camera Light Field Imaging
14:25

Determining 3D Flow Fields via Multi-camera Light Field Imaging

Published on: March 6, 2013

17.2K

Automatic Trimap Generation and Consistent Matting for Light-Field Images.

Donghyeon Cho, Sunyeong Kim, Yu-Wing Tai

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |January 24, 2017
    PubMed
    Summary
    This summary is machine-generated.

    This study presents an automated method for generating accurate trimaps and consistent alpha mattes for light-field images. The approach ensures high-quality foreground object segmentation using depth, color, and epipolar plane image (EPI) consistency.

    More Related Videos

    Fabrication and Implementation of a Reference-Free Traction Force Microscopy Platform
    08:10

    Fabrication and Implementation of a Reference-Free Traction Force Microscopy Platform

    Published on: October 6, 2019

    7.0K
    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

    14.0K

    Related Experiment Videos

    Last Updated: Mar 8, 2026

    Determining 3D Flow Fields via Multi-camera Light Field Imaging
    14:25

    Determining 3D Flow Fields via Multi-camera Light Field Imaging

    Published on: March 6, 2013

    17.2K
    Fabrication and Implementation of a Reference-Free Traction Force Microscopy Platform
    08:10

    Fabrication and Implementation of a Reference-Free Traction Force Microscopy Platform

    Published on: October 6, 2019

    7.0K
    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

    14.0K

    Area of Science:

    • Computer Vision
    • Image Processing
    • Computer Graphics

    Background:

    • Accurate foreground object segmentation is crucial for various image and video processing tasks.
    • Existing methods for alpha matting often struggle with the complexities of light-field data.

    Purpose of the Study:

    • To develop an automatic approach for generating trimaps and consistent alpha mattes from light-field images.
    • To improve the quality and consistency of alpha mattes compared to existing techniques.

    Main Methods:

    • Initial binary segmentation using depth and color information.
    • Trimap estimation via guided image filtering and KL-divergence analysis of color distribution.
    • Alpha matte generation using epipolar plane image (EPI) consistency constraints and propagation from known regions.
    • Refinement using multi-image matting Laplacian with an additional EPI smoothness constraint.

    Main Results:

    • The proposed method successfully generates accurate trimaps and consistent alpha mattes for light-field images.
    • Experimental results demonstrate both visual and quantitative improvements in alpha matte quality.
    • A new dataset with ground truth alpha mattes for light-field images was created using the blue screen technique.

    Conclusions:

    • The developed automatic approach effectively addresses the challenges of alpha matting in light-field imagery.
    • The method provides a robust solution for producing high-fidelity foreground object segmentation.
    • The findings contribute to advancing the field of light-field image processing and analysis.