Single Image Internal Distribution Measurement Using Non-Local Variational Autoencoder

TL;DR

This paper introduces NLVAE, a self-supervised, non-local variational autoencoder that reconstructs high-resolution images from single low-resolution inputs without prior training, leveraging global context for improved super-resolution.

Contribution

The paper presents a novel, training-free, self-supervised super-resolution method using non-local variational autoencoders that captures global context for enhanced image reconstruction.

Findings

Outperforms baseline and state-of-the-art super-resolution methods.

Effective on seven benchmark datasets.

Produces high-quality synthetic images with detailed reconstruction.

Abstract

Deep learning-based super-resolution methods have shown great promise, especially for single image super-resolution (SISR) tasks. Despite the performance gain, these methods are limited due to their reliance on copious data for model training. In addition, supervised SISR solutions rely on local neighbourhood information focusing only on the feature learning processes for the reconstruction of low-dimensional images. Moreover, they fail to capitalize on global context due to their constrained receptive field. To combat these challenges, this paper proposes a novel image-specific solution, namely non-local variational autoencoder (\texttt{NLVAE}), to reconstruct a high-resolution (HR) image from a single low-resolution (LR) image without the need for any prior training. To harvest maximum details for various receptive regions and high-quality synthetic images, \texttt{NLVAE} is introduced as a self-supervised strategy that reconstructs high-resolution images using disentangled information from the non-local neighbourhood. Experimental results from seven benchmark datasets demonstrate the effectiveness of the \texttt{NLVAE} model. Moreover, our proposed model outperforms a number of baseline and state-of-the-art methods as confirmed through extensive qualitative and quantitative evaluations.