Single Image Internal Distribution Measurement Using Non-Local Variational Autoencoder
This addresses the limitation of data dependency in deep learning-based super-resolution for applications like image enhancement, though it is an incremental improvement by introducing a novel method for a known bottleneck.
The paper tackles the problem of single image super-resolution without requiring prior training data by proposing a non-local variational autoencoder (NLVAE) that uses self-supervised learning to reconstruct high-resolution images from low-resolution ones, achieving superior performance over baseline and state-of-the-art methods on seven benchmark datasets.
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.