Image Dehazing with Scattering Coefficient Estimation using CNN-based Image Regression

2021 ◽  
Vol 27 (11) ◽  
pp. 890-896
Author(s):  
Won Young Chung ◽  
Sun Young Kim ◽  
Chan Gook Park ◽  
Chang Ho Kang
Keyword(s):  
Scattering Coefficient ◽  
Image Dehazing ◽  
Coefficient Estimation

Image-Dehazing Method Based on Improved Dynamic Atmospheric Scattering Coefficient Function

2020 ◽  
Vol 57 (18) ◽  
pp. 181003
Author(s):  
郑毅 Zheng Yi ◽  
高强 Gao Qiang ◽  
王笛 Wang Di ◽  
胡辽林 Hu Liaolin
Keyword(s):  
Scattering Coefficient ◽  
Coefficient Function ◽  
Image Dehazing ◽  
Atmospheric Scattering

Single Image Dehazing by Predicting Atmospheric Scattering Parameters

2020 ◽  
Vol 2020 (1) ◽  
pp. 74-77
Author(s):  
Simone Bianco ◽  
Luigi Celona ◽  
Flavio Piccoli
Keyword(s):  
Reference Image ◽  
Single Image ◽  
Scattering Parameters ◽  
Image Dehazing ◽  
Atmospheric Scattering ◽  
Local Structures ◽  
Full Reference ◽  
Reconstruction Quality ◽  
Single Image Dehazing

In this work we propose a method for single image dehazing that exploits a physical model to recover the haze-free image by estimating the atmospheric scattering parameters. Cycle consistency is used to further improve the reconstruction quality of local structures and objects in the scene as well. Experimental results on four real and synthetic hazy image datasets show the effectiveness of the proposed method in terms of two commonly used full-reference image quality metrics.

Estimating Pigment Concentrations from Spectral Images Using an Encoder‐Decoder Neural Network

2020 ◽  
Vol 64 (3) ◽  
pp. 30502-1-30502-15
Author(s):  
Kensuke Fukumoto ◽  
Norimichi Tsumura ◽  
Roy Berns
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Absorption Coefficient ◽  
Spectral Data ◽  
High Accuracy ◽  
Pigment Concentration ◽  
Scattering Coefficient ◽  
A Value ◽  
Input And Output ◽  
Pigment Concentrations

Abstract A method is proposed to estimate the concentration of pigments mixed in a painting, using the encoder‐decoder model of neural networks. The model is trained to output a value that is the same as its input, and its middle output extracts a certain feature as compressed information about the input. In this instance, the input and output are spectral data of a painting. The model is trained with pigment concentration as the middle output. A dataset containing the scattering coefficient and absorption coefficient of each of 19 pigments was used. The Kubelka‐Munk theory was applied to the coefficients to obtain many patterns of synthetic spectral data, which were used for training. The proposed method was tested using spectral images of 33 paintings, which showed that the method estimates, with high accuracy, the concentrations that have a similar spectrum of the target pigments.

Sign in / Sign up

Export Citation Format

Share Document