VAE-CoGAN: Unpaired image-to-image translation for low-level vision

Low-level vision problems, such as single image haze removal and single image rain removal, usually restore a clear image from an input image using a paired dataset. However, for many problems, the paired training dataset will not be available. In this paper, we propose an unpaired image-to-image tr...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Signal, image and video processing Ročník 17; číslo 4; s. 1019 - 1026
Hlavní autori: Zhang, Juan, Lang, Xiaoqi, Huang, Bo, Jiang, Xiaoyan
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: London Springer London 01.06.2023
Springer Nature B.V
Predmet:
Algorithms
Computer Imaging
Computer Science
Computer vision
Datasets
Deep learning
Generative adversarial networks
Image Processing and Computer Vision
Image restoration
Multimedia Information Systems
Optimization
Original Paper
Pattern Recognition and Graphics
Rain
Signal,Image and Speech Processing
Synthetic data
Vision
Variational autoencoder
Generative adversarial networks
Derain
Dehaze
ISSN:1863-1703, 1863-1711
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Low-level vision problems, such as single image haze removal and single image rain removal, usually restore a clear image from an input image using a paired dataset. However, for many problems, the paired training dataset will not be available. In this paper, we propose an unpaired image-to-image translation method based on coupled generative adversarial networks (CoGAN) called VAE-CoGAN to solve this problem. Different from the basic CoGAN, we propose a shared-latent space and variational autoencoder (VAE) in framework. We use synthetic datasets and the real-world images to evaluate our method. The extensive evaluation and comparison results show that the proposed method can be effectively applied to numerous low-level vision tasks with favorable performance against the state-of-the-art methods.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1863-1703
1863-1711
DOI:10.1007/s11760-022-02307-y