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: Nov 22, 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

812

Dynamic Selection Network for Image Inpainting.

Ning Wang, Yipeng Zhang, Lefei Zhang

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |January 8, 2021
    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

    Three-Dimensional Radiographic and Morphological Features of Ameloblastoma and Odontogenic Keratocyst: A Comparative Cone Beam Computed Tomography Study Using Automatic Segmentation.

    International dental journal·2026
    Same author

    β-Caryophyllene Competes With NINJA/IAAs for TOPLESS Family Corepressors to Regulate Plant Physiological Activities.

    Plant, cell & environment·2026
    Same author

    Characterization of a novel phage BUCT800 against Acinetobacter baumannii and its biofilm removal efficiency.

    Archives of virology·2026
    Same author

    Characterization and complete genomic sequence of a novel phage BUCT805 infecting <i>Serratia marcescens</i> and its anti-biofilm activities.

    Microbiology spectrum·2026
    Same author

    Generalized and group spherical linear interpolation for token-level context compression.

    Neural networks : the official journal of the International Neural Network Society·2026
    Same author

    MambaFPN: A SSM-based feature pyramid network for object detection.

    Neural networks : the official journal of the International Neural Network Society·2026
    Same journal

    Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

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

    AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

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

    BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

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

    GoP-based Quality Enhancement on Video Compression.

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

    Align then Tensorize: Multi-Level Consistent Anchor Graph Learning for Scalable Multi-View Clustering.

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

    Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    See all related articles

    This study introduces a novel dynamic selection network (DSNet) for image inpainting, improving realistic content generation. The DSNet effectively utilizes valid image regions, outperforming existing methods.

    Area of Science:

    • Computer Vision
    • Deep Learning
    • Image Processing

    Background:

    • Image inpainting is crucial for restoring corrupted images.
    • Deep learning models, particularly convolutional neural networks, are widely used.
    • Existing methods struggle with random corruptions due to static convolutions and monotonous normalization.

    Purpose of the Study:

    • To propose a novel dynamic selection network (DSNet) for improved image inpainting.
    • To address limitations of static convolutions and monotonous normalization in deep learning models.
    • To enhance the utilization of valid image information during the inpainting process.

    Main Methods:

    • Introduced a novel dynamic selection network (DSNet).
    • Developed Validness Migratable Convolution (VMC) for flexible feature extraction.

    More Related Videos

    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    9.7K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    654

    Related Experiment Videos

    Last Updated: Nov 22, 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

    812
    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    9.7K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    654
  • Implemented Regional Composite Normalization (RCN) for selective feature normalization.
  • Main Results:

    • DSNet effectively distinguishes corrupted from valid image regions.
    • VMC dynamically selects spatial sampling locations, enhancing feature extraction.
    • RCN selectively normalizes feature regions, combining multiple normalization techniques.
    • The proposed method outperforms state-of-the-art approaches on public datasets.

    Conclusions:

    • DSNet offers a significant advancement in image inpainting.
    • The dynamic selection mechanism improves the generation of realistic and detailed images.
    • The VMC and RCN modules contribute to adaptive feature utilization and normalization.