Adaptive Patch Based Convolutional Neural Network for Robust Dehazing

We present a novel deep learning-based dehazing method using adaptive patch splits. Our method applies quad-tree decomposition to an input image, yielding multiple patches with adaptive sizes. Then, each patch is fed into a Convolutional Neural Network (CNN) and classified into a single transmission...

Full description

Saved in:
Bibliographic Details
Published in2018 25th IEEE International Conference on Image Processing (ICIP) pp. 2845 - 2849
Main Authors Kim, Guisik, Ha, Suhyeon, Kwon, Junseok
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.10.2018
Subjects
Adaptive Patch Classification
Adaptive systems
Atmospheric modeling
Convolutional neural networks
Dehazing
Estimation
Machine learning
Quad-tree Decomposition
Robustness
Training
Online AccessGet full text

Cover

More Information
Summary:We present a novel deep learning-based dehazing method using adaptive patch splits. Our method applies quad-tree decomposition to an input image, yielding multiple patches with adaptive sizes. Then, each patch is fed into a Convolutional Neural Network (CNN) and classified into a single transmission value, in which a transmission map comprises transmission values from all patches. Homogeneous regions in the image are typically decomposed into large patches. Thus the method can save computational cost. Non-homogeneous regions are divided into small patches, which helps preserve local details in a transmission map. To train CNN, we synthesize numerous hazy images from haze-free images. Experimental results demonstrate our method surpasses state- of-the-art deep learning based algorithms quantitatively and qualitatively.
ISSN:2381-8549
DOI:10.1109/ICIP.2018.8451252