You have requested a machine translation of selected content from our databases. This functionality is provided solely for your convenience and is in no way intended to replace human translation. Neither SPIE nor the owners and publishers of the content make, and they explicitly disclaim, any express or implied representations or warranties of any kind, including, without limitation, representations and warranties as to the functionality of the translation feature or the accuracy or completeness of the translations.
Translations are not retained in our system. Your use of this feature and the translations is subject to all use restrictions contained in the Terms and Conditions of Use of the SPIE website.
22 April 2020SRVAE: super resolution using variational autoencoders
The emergence of Generative Adversarial Network (GAN)-based single-image super-resolution (SISR) has allowed for finer textures in the super-resolved images, thus making them seem realistic to humans. However, GANbased models may depend on extensive high-quality data and are known to be very costly and unstable to train. On the other hand, Variational Autoencoders (VAEs) have inherent mathematical properties, and they are relatively cheap and stable to train; but VAEs produce blurry images that prevent them from being used for super-resolution. In this paper, we propose a first of its kind SISR method that takes advantage of a selfevaluating Variational Autoencoder (IntroVAE). Our network, called SRVAE, judges the quality of generated high-resolution (HR) images with the target images in an adversarial manner, which allows for high perceptual image generation. First, the encoder and the decoder of our introVAE-based method learn the manifold of HR images. In parallel, another encoder and decoder are simultaneously learning the reconstruction of the lowresolution (LR) images. Next, reconstructed LR images are fed to the encoder of the HR network to learn a mapping from LR images to corresponding HR versions. Using the encoder as a discriminator allows SRVAE to be a fast single-stream framework that performs super-resolution through generating photo-realistic images. Moreover, SRVAE has the same training stability and "nice" latent manifold structure as of VAEs, while playing a max-min adversarial game between the generator and the encoder like GANs. Our experiments show that our super-resolved images are comparable to the state-of-the-art GAN-based super-resolution.
The alert did not successfully save. Please try again later.
A. Ali Heydari, Asif Mehmood, "SRVAE: super resolution using variational autoencoders," Proc. SPIE 11400, Pattern Recognition and Tracking XXXI, 114000U (22 April 2020); https://doi.org/10.1117/12.2559808