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: Jan 3, 2026

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Published on: February 8, 2014

Semi-Supervised Image Dehazing.

Lerenhan Li, Yunlong Dong, Wenqi Ren

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society

|November 22, 2019

Summary

This summary is machine-generated.

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

Liver transcriptome analysis revealed multiple immune processes and lipid metabolism pathways involved in the defense response of the turbot (Scophthalmus maximus) against Aeromonas salmonicida.

Comparative biochemistry and physiology. Part D, Genomics & proteomics·2026

Same author

High-Quality Entity Segmentation and Grounding.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

Long&short Exposures Guided Diffusion Model for Realistic Local Motion Deblurring.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

Liquid crystal smart window based on the synergistic effect of the focal conic state and ionic turbulence.

Optics letters·2026

Same author

Enhanced space-variant deblurring of spacecraft images via detail-preserving techniques.

Scientific reports·2026

Same author

Toward Robust Alignment for Video Dehazing With Temporal Lookup Table.

IEEE transactions on image processing : a publication of the IEEE Signal Processing 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 semi-supervised learning algorithm for single image dehazing using a deep Convolutional Neural Network (CNN). The method effectively removes haze from images, generalizing well to real-world data.

Area of Science:

Computer Vision
Artificial Intelligence
Machine Learning

Background:

Image dehazing is crucial for improving visual quality and subsequent analysis.
Existing methods often struggle with generalization to real-world hazy images.

Purpose of the Study:

To develop an effective semi-supervised learning algorithm for single image dehazing.
To improve the generalization capability of dehazing models to real-world images.

Main Methods:

A deep Convolutional Neural Network (CNN) with both supervised and unsupervised learning branches was designed.
Supervised branch utilized mean squared, perceptual, and adversarial losses.
Unsupervised branch leveraged dark channel and gradient priors for constraint.

Related Experiment Videos

Last Updated: Jan 3, 2026

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Published on: February 8, 2014

Main Results:

The algorithm was trained end-to-end on both synthetic and real-world data.
Demonstrated strong performance against state-of-the-art methods on benchmark and real datasets.
Showcased effective generalization beyond synthetic training data.

Conclusions:

The proposed semi-supervised approach offers a robust solution for single image dehazing.
The method achieves superior performance and generalization for real-world applications.