Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Super-resolution Fluorescence Microscopy

Super-resolution Fluorescence Microscopy

Super-resolution fluorescence microscopy (SRFM) provides a better resolution than conventional fluorescence microscopy by reducing the point spread function (PSF). PSF is the light intensity distribution from a point that causes it to appear blurred. Due to PSF, each fluorescing point appears bigger than its actual size, and it is the PSF interference of nearby fluorophores that causes the blurred image. Various approaches to achieving higher resolution through SRFM have recently been...

You might also read

Related Articles

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

Sort by

Same author

Association between inflammatory cytokine gene polymorphisms and asthma susceptibility in Chinese Han children: a retrospective case-control study for potential diagnostic biomarkers.

American journal of translational research·2026

Same author

Synergistic nanomedicine overcomes hypoxia-driven DNA repair to potentiate radiotherapy for lung adenocarcinoma.

Theranostics·2026

Same author

Lars2 Deficiency-Induced Mitochondrial Dysfunction Drives the Emergence of a Pro-Inflammatory Stroke-Specific Microglial Subpopulation.

Aging and disease·2025

Same author

Treatment of Rheumatoid Arthritis Based on the Inherent Bioactivity of Black Phosphorus Nanosheets.

Aging and disease·2024

Same author

Lipid droplets in the nervous system: involvement in cell metabolic homeostasis.

Neural regeneration research·2024

Same author

Comprehensive transcript-level analysis reveals transcriptional reprogramming during the progression of Alzheimer's disease.

Frontiers in aging neuroscience·2023

Search research articles

Related Experiment Video

Updated: Sep 23, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Multi-level landmark-guided deep network for face super-resolution.

Cheng Zhuang¹, Minqi Li¹, Kaibing Zhang²

¹School of Electronics and Information, Xi'an Polytechnic University, Xi'an, 710048, China.

Neural Networks : the Official Journal of the International Neural Network Society

|May 17, 2022

Summary

This study introduces a novel multi-level landmark-guided deep network (MLGDN) for face super-resolution (FSR). The MLGDN effectively utilizes facial landmarks to generate high-quality, artifact-free super-resolved face images.

Keywords:

Facial component Facial landmarks Recursive feedback deep network Super-resolution reconstruction

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Related Experiment Videos

Last Updated: Sep 23, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Area of Science:

Computer Vision
Deep Learning
Image Processing

Background:

Deep learning methods for face super-resolution (FSR) have advanced significantly.
Existing methods often fail to fully exploit crucial facial prior knowledge, like landmarks, leading to artifacts in high-magnification results.

Purpose of the Study:

To propose a novel multi-level landmark-guided deep network (MLGDN) for enhanced FSR.
To address the limitations of current methods in exploiting facial landmarks for artifact reduction.

Main Methods:

Developed a recursive back-projection network with a feedback mechanism for coarse-to-fine FSR.
Incorporated an attention fusion module and a feature modulation module to strengthen and refine facial features.
Ensured facial landmarks are shared across different network levels for improved detail reconstruction.

Main Results:

The proposed MLGDN demonstrated superior performance in quantitative and qualitative evaluations.
Achieved more impressive super-resolution (SR) results compared to state-of-the-art competitors.
Generated more faithful facial details with reduced artifacts, especially under large magnification.

Conclusions:

The MLGDN effectively leverages multi-level facial landmark information for superior FSR.
The network architecture successfully enhances facial component representation and feature refinement.
Results indicate a significant improvement in generating high-fidelity super-resolved face images.