A hybrid approach of interpolations and CNN to obtain super-resolution

TL;DR

This paper introduces a hybrid CNN-based approach combining traditional interpolations to enhance image resolution, achieving high-quality super-resolution with low computational cost and outperforming some existing methods.

Contribution

The paper presents a novel end-to-end architecture that combines multiple interpolation techniques with CNNs for efficient super-resolution, maintaining high-frequency details.

Findings

Achieves comparable or better PSNR than state-of-the-art methods.

Preserves sharp details and high-frequency components.

Operates with low computational cost due to shallow CNN design.

Abstract

We propose a novel architecture that learns an end-to-end mapping function to improve the spatial resolution of the input natural images. The model is unique in forming a nonlinear combination of three traditional interpolation techniques using the convolutional neural network. Another proposed architecture uses a skip connection with nearest neighbor interpolation, achieving almost similar results. The architectures have been carefully designed to ensure that the reconstructed images lie precisely in the manifold of high-resolution images, thereby preserving the high-frequency components with fine details. We have compared with the state of the art and recent deep learning based natural image super-resolution techniques and found that our methods are able to preserve the sharp details in the image, while also obtaining comparable or better PSNR than them. Since our methods use only traditional interpolations and a shallow CNN with less number of smaller filters, the computational cost is kept low. We have reported the results of two proposed architectures on five standard datasets, for an upscale factor of 2. Our methods generalize well in most cases, which is evident from the better results obtained with increasingly complex datasets. For 4-times upscaling, we have designed similar architectures for comparing with other methods.