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...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	International journal of interactive multimedia and artificial intelligence Ročník 7; číslo 5; s. 93 - 99
Hlavní autori:	Zhang, Hongqi, Wei, Yixiong, Zhou, Hongqiao, Wu, Qianhao
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	IMAI Software 01.09.2022 Universidad Internacional de La Rioja (UNIR)
Predmet:	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
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	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