Coupled adversarial variational autoencoder

Generating image is a hot research topic in the field of deep learning, and it is challenging for generating high quality image pairs. The image pair refers to the corresponding image tuples with the same high-level features and different low-level features, generating high-quality image pairs has i...

Full description

Saved in:
Bibliographic Details
Published in:Signal processing. Image communication Vol. 98; p. 116396
Main Authors: Hou, Yingzhen, Zhai, Junhai, Chen, Jiankai
Format: Journal Article
Language:English
Published: Amsterdam Elsevier B.V 01.10.2021
Elsevier BV
Subjects:
Adversarial learning
Adversarial variational autoencoder
Attribute transformation
Cognitive tasks
Deep learning
Image pairs
Image quality
Production methods
Resolution
Adversarial variational autoencoder
Adversarial learning
Image pairs
Resolution
Attribute transformation
ISSN:0923-5965, 1879-2677
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Generating image is a hot research topic in the field of deep learning, and it is challenging for generating high quality image pairs. The image pair refers to the corresponding image tuples with the same high-level features and different low-level features, generating high-quality image pairs has important applications in some specific fields. Currently, there are many methods to generate high quality images, but these methods cannot produce higher resolution image pairs. To address this problem, we proposed a novel model which consists of two adversarial variational autoencoders, each one aim at generating an image of pairs more accurately. We called this model CoAdVAE (coupled adversarial variational autoencoders), it can generate high quality image pairs due to introducing adversarial learning to the model. In the experiments, we applied the proposed model to three learning tasks, i.e., generating image pairs with different attributes, converting image attributes, and image dehazing. We show by experiments compared with related approaches on four datasets, Mnist, Celeba, AFHQ, and Fog_data that the proposed model can achieve the-state-of-the-art results. •A novel model named CoAdVAE is proposed to generate high quality image pairs.•A suitable loss function is proposed to jointly optimize the parameters of CoAdVAE.•It has been verified experimentally that the proposed model is effective and efficient.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0923-5965
1879-2677
DOI:10.1016/j.image.2021.116396