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

Policy-Based Active Learning for Efficient Molecular Identification.

Journal of chemical information and modeling·2026

Same author

Multimodal Deep Learning with Routine Clinical Data for Recurrence Risk Stratification in HR<sup>+</sup>/HER2<sup>-</sup> Early Breast Cancer.

Research (Washington, D.C.)·2026

Same author

A systematic comparison of methodologies for the estimation of the serial interval.

Infectious Disease Modelling·2026

Same author

Learning With Partial and Noisy Correspondence in Graph Matching.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

Few-shot molecular property optimization <i>via</i> a domain-specialized large language model.

Chemical science·2026

Same author

Task-specific pre-training for molecular property prediction.

Briefings in bioinformatics·2026

Same journal

CLASH-CTTA: Class-Wise Shift-Aware Hierarchical Continual Test-Time Adaptation.

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

Same journal

Voxel-based Point Cloud Geometry Compression with Space-to-Channel Context.

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

Same journal

RIGI: Rectifying Image-to-3D Generation Inconsistency via Uncertainty-Aware Learning.

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

Same journal

DA-Cal: Towards Cross-Domain Calibration in Semantic Segmentation.

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

Same journal

Multi-Dimensional Quality Assessment for Single-Image-to-3D Contents: Dataset and Model.

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

Same journal

Enhancing Underwater Light Field Images via Global Geometry-Aware Diffusion Process.

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

See all related articles

Search research articles

Related Experiment Video

Updated: Sep 21, 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

Unsupervised Neural Rendering for Image Hazing.

Boyun Li, Yijie Lin, Jinfeng Bai

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

|June 3, 2022

Summary

This summary is machine-generated.

This study introduces HazeGEN, a novel unsupervised method for generating realistic hazy images. HazeGEN effectively estimates transmission maps and learns airlight distributions, advancing image rendering for applications like gaming and dehazing.

More Related Videos

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

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Related Experiment Videos

Last Updated: Sep 21, 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

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

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Area of Science:

Computer Vision
Image Processing
Artificial Intelligence

Background:

Image hazing is crucial for applications like gaming, filming, and image dehazing.
Existing methods often require paired data or suffer from domain shift issues.
Estimating transmission maps and learning airlight adaptively from single images are challenging problems.

Purpose of the Study:

To propose a novel neural rendering method for image hazing, named HazeGEN.
To address unsupervised estimation of transmission maps and adaptive learning of airlight from unpaired data.
To enable controllable and domain-shift-free hazy image generation.

Main Methods:

HazeGEN utilizes a knowledge-driven neural network for image hazing.
It estimates transmission maps by leveraging structural similarity between the map and the clean image.
A neural module adaptively learns airlight distribution by comparing rendered and exemplar hazy images.

Main Results:

HazeGEN successfully renders hazy images in an unsupervised, learnable, and controllable manner.
The method avoids the need for labor-intensive paired data collection.
Experimental results demonstrate competitive performance against existing methods.

Conclusions:

HazeGEN offers a significant advancement in unsupervised hazy image generation.
The approach overcomes limitations of previous methods, including domain shift.
This work paves the way for more realistic and efficient image hazing applications.