ED-Dehaze Net: Encoder and Decoder Dehaze Network

The presence of haze will significantly reduce the quality of images, such as resulting in lower contrast and blurry details. This paper proposes a novel end-to-end dehazing method, called Encoder and Decoder Dehaze Network (ED-Dehaze Net), which contains a Generator and a Discriminator. In particul...

Full description

Saved in:
Bibliographic Details
Published in:International journal of interactive multimedia and artificial intelligence Vol. 7; no. 5; pp. 93 - 99
Main Authors: Zhang, Hongqi, Wei, Yixiong, Zhou, Hongqiao, Wu, Qianhao
Format: Journal Article
Language:English
Published: IMAI Software 01.09.2022
Universidad Internacional de La Rioja (UNIR)
Subjects:
Decoders
encoder and decoder network
Encoders
generative adversarial network
image dehazing
Image Dehazing Encoder and Decoder Network Generative Adversarial Network Multi
Image processing
loss function
Methods
multi-scale convolution block
Neural networks
Scale Convolution Block Loss Function
China
ISSN:1989-1660, 1989-1660
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The presence of haze will significantly reduce the quality of images, such as resulting in lower contrast and blurry details. This paper proposes a novel end-to-end dehazing method, called Encoder and Decoder Dehaze Network (ED-Dehaze Net), which contains a Generator and a Discriminator. In particular, the Generator uses an Encoder-Decoder structure to effectively extract the texture and semantic features of hazy images. Between the Encoder and Decoder we use Multi-Scale Convolution Block (MSCB) to enhance the process of feature extraction. The proposed ED-Dehaze Net is trained by combining Adversarial Loss, Perceptual Loss and Smooth L1 Loss. Quantitative and qualitative experimental results showed that our method can obtain the state-of-the-art dehazing performance.
ISSN:1989-1660
1989-1660
DOI:10.9781/ijimai.2022.08.008