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

Search research articles

Related Experiment Video

Updated: Jun 6, 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

Asymmetric Large Kernel Distillation Network for efficient single image super-resolution.

Daokuan Qu^1,2, Yuyao Ke³

¹School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, Jiangsu, China.

Frontiers in Neuroscience

|November 26, 2024

Summary

This summary is machine-generated.

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

A unified multi-stream diffusion framework for robust video camouflaged object detection.

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

Same journal

Relationship between spontaneous EEG oscillations at 7 and 45 days of acute plateau exposure and the plateau acclimatization index.

Frontiers in neuroscience·2026

Same journal

Neuroprotective effects of paederoside against mitochondrial dysfunction in rotenone-induced cell models of Parkinson's disease.

Frontiers in neuroscience·2026

Same journal

Covariance-based analysis of spindle-band EEG during declarative and non-declarative odor cueing in sleep.

Frontiers in neuroscience·2026

Same journal

Correction: Physiological determinants of cortical P100 responses in pattern visual evoked potentials: a scoping review.

Frontiers in neuroscience·2026

Same journal

Transcranial magnetic stimulation and motor overflow: a systematic review in neurological disorders.

Frontiers in neuroscience·2026

Same journal

Editorial: Advancing neurodegenerative disease biomarkers: the role of neuroimaging in TDP-43 and tau proteinopathies.

Frontiers in neuroscience·2026

See all related articles

This study introduces a new Lightweight Asymmetric Large Kernel Distillation Network (ALKDNet) for efficient single-image super-resolution. ALKDNet enhances feature extraction, improving image reconstruction quality and achieving state-of-the-art performance.

Area of Science:

Computer Vision
Image Processing

Background:

Single-image super-resolution (SISR) has advanced with information distillation, leveraging multi-level features for high-resolution reconstruction.
Existing SISR methods often focus on enhancing distilled features rather than improving the feature extraction within the distillation module.

Purpose of the Study:

To address limitations in current SISR methods by enhancing feature extraction capabilities.
To introduce an efficient and effective super-resolution network through an asymmetric large-kernel convolution design.

Main Methods:

Proposed the Lightweight Asymmetric Large Kernel Distillation Network (ALKDNet).
Employed an asymmetric large-kernel convolution to expand the receptive field and capture long-range dependencies.
Utilized a lightweight architecture to maintain model complexity.

Keywords:

asymmetric large kernel convolution convolutional neural network efficient method information distillation single image super-resolution

More Related Videos

Super-resolution Imaging of Neuronal Dense-core Vesicles

Super-resolution Imaging of Neuronal Dense-core Vesicles

Published on: July 2, 2014

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Related Experiment Videos

Last Updated: Jun 6, 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

Super-resolution Imaging of Neuronal Dense-core Vesicles

Super-resolution Imaging of Neuronal Dense-core Vesicles

Published on: July 2, 2014

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Main Results:

ALKDNet demonstrated performance enhancements over existing super-resolution methods on benchmark datasets (Set5, Set14, BSD100, Urban100, Manga109).
Achieved average improvements of 0.10 dB in Peak Signal-to-Noise Ratio (PSNR) and 0.0013 in Structural Similarity Index Measure (SSIM).
Preserved computational efficiency while improving reconstruction accuracy.

Conclusions:

The proposed asymmetric large-kernel convolution effectively enhances feature extraction in information distillation for SISR.
ALKDNet offers a state-of-the-art solution for efficient and high-quality single-image super-resolution.