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 Videos

Dynamic Video Deblurring Using a Locally Adaptive Blur Model.

Tae Hyun Kim, Seungjun Nah, Kyoung Mu Lee

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |October 14, 2017
    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

    Particle Diffusion Matching: Random Walk Correspondence Search for the Alignment of Standard and Ultra-Widefield Fundus Images.

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

    LucidDreamer: Domain-Free Generation of 3D Gaussian Splatting Scenes.

    IEEE transactions on visualization and computer graphics·2025
    Same author

    Active Diffusion Matching: Score-Based Iterative Alignment of Cross-Modal Retinal Images.

    IEEE transactions on bio-medical engineering·2025
    Same author

    FQ-UWF: Unpaired Generative Image Enhancement for Fundus Quality Ultra-Widefield Retinal Images.

    Bioengineering (Basel, Switzerland)·2024
    Same author

    Learning Controllable ISP for Image Enhancement.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2023
    Same author

    Learning to Learn Task-Adaptive Hyperparameters for Few-Shot Learning.

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

    Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

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

    RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

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

    CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

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

    DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

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

    Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

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

    Learning Shape Anchors for Holistic Indoor Scene Understanding.

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

    This study introduces a novel video deblurring algorithm for dynamic scenes, effectively handling general blurs from motion and defocus. The method achieves superior deblurring and optical flow estimation, outperforming existing techniques.

    Area of Science:

    • Computer Vision
    • Image Processing

    Background:

    • Current video deblurring methods assume static scenes, limiting their effectiveness in dynamic environments.
    • Dynamic scenes introduce complex blurs from moving objects, camera shake, and defocus.

    Purpose of the Study:

    • To develop a video deblurring algorithm capable of handling general blurs in dynamic scenes.
    • To jointly estimate optical flows, defocus blur maps, and latent frames within a unified energy model.

    Main Methods:

    • Estimating pixel-wise varying non-uniform blur kernels to address diverse blur sources.
    • Inferring bidirectional optical flows for motion blur compensation.
    • Estimating Gaussian blur maps to mitigate defocus blur.

    Main Results:

    Related Experiment Videos

    • Significant improvements in general blur removal and optical flow estimation.
    • Enhanced depth-of-field extension in deblurred frames.
    • Demonstrated qualitative superiority over state-of-the-art methods on challenging videos.

    Conclusions:

    • The proposed method effectively addresses limitations of static-scene deblurring.
    • It offers a robust solution for deblurring videos captured in dynamic and complex environments.
    • A new dataset for evaluating non-uniform deblurring methods has been introduced.