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

Deconvolution

Deconvolution

Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...

You might also read

Related Articles

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

Sort by

Same author

Olfactory perception, odor interaction and aroma intensity prediction of terpenes in wine beverage.

NPJ science of food·2026

Same author

MRI-based quantification of intratumoral heterogeneity for differentiating glioblastoma from solitary brain metastasis: a two-center study.

European journal of radiology·2026

Same author

Physical Activity and Social Anxiety in Highly Sensitive Individuals: The Mediating Role of Cognitive Reappraisal.

Psychological reports·2026

Same author

Intravenous lidocaine reduces propofol requirements during endoscopic ultrasound: a randomized, double-blinded, controlled trial.

BMC anesthesiology·2026

Same author

Mechanisms of Microglial NLRP3 Inflammasome Activation by Methylmalonic Acid in Methylmalonic Acidemia.

Mediators of inflammation·2026

Same author

Severe Methotrexate toxicity after ectopic pregnancy: a case report managed with continuous renal replacement therapy.

Cancer chemotherapy and pharmacology·2026

Search research articles

Related Experiment Video

Updated: Aug 16, 2025

Studying Surfactant Effects on Hydrate Crystallization at Oil-Water Interfaces Using a Low-Cost Integrated Modular Peltier Device

Studying Surfactant Effects on Hydrate Crystallization at Oil-Water Interfaces Using a Low-Cost Integrated Modular Peltier Device

Published on: March 18, 2020

Physical-model guided self-distillation network for single image dehazing.

Yunwei Lan¹, Zhigao Cui¹, Yanzhao Su¹

¹Xi'an Research Institute of High Technology, Xi'an, China.

Frontiers in Neurorobotics

|December 19, 2022

Summary

This study introduces a novel network for image dehazing, combining physical models and self-distillation. The proposed method enhances image quality with clear textures and accurate colors, outperforming existing techniques.

Keywords:

attention mechanism computer vision deep learning image dehazing knowledge distillation

More Related Videos

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Published on: February 8, 2014

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

Related Experiment Videos

Last Updated: Aug 16, 2025

Studying Surfactant Effects on Hydrate Crystallization at Oil-Water Interfaces Using a Low-Cost Integrated Modular Peltier Device

Studying Surfactant Effects on Hydrate Crystallization at Oil-Water Interfaces Using a Low-Cost Integrated Modular Peltier Device

Published on: March 18, 2020

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Published on: February 8, 2014

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

Area of Science:

Computer Vision
Image Processing

Background:

Traditional image dehazing methods often produce artifacts due to parameter estimation errors.
Model-free methods offer better color fidelity but may lack detail.

Purpose of the Study:

To develop an improved single image dehazing method by integrating the strengths of model-based and model-free approaches.
To enhance image quality, preserving clear textures and color fidelity.

Main Methods:

Proposed a physical-model guided self-distillation network (PMGSDN).
Introduced an attention-guided feature extraction block (AGFEB) for deep feature extraction.
Incorporated early-exit branches with dark channel prior and self-distillation for feature transfer.

Main Results:

Achieved superior performance on I-HAZE and O-HAZE datasets with high PSNR and SSIM values.
Demonstrated effective dehazing on real-world images, yielding high-quality results.
The method produced dehazed images with clear textures and good color fidelity.

Conclusions:

The proposed PMGSDN effectively removes haze from images.
The network successfully combines physical model insights with deep learning for enhanced dehazing.