Nonlocal Co-occurrence for Image Downscaling

TL;DR

This paper introduces a novel image downscaling method based on kernel filtering that uses learned pixel-pair co-occurrence similarities to preserve high-frequency details and avoid edge blurring.

Contribution

The work proposes a new downscaling technique utilizing learned co-occurrence similarities for kernel-based filtering, enhancing detail preservation in downscaled images.

Findings

Preserves high-frequency structures effectively.

Retains visually-important details without edge-blurring.

Works well across various downscaling factors.

Abstract

Image downscaling is one of the widely used operations in image processing and computer graphics. It was recently demonstrated in the literature that kernel-based convolutional filters could be modified to develop efficient image downscaling algorithms. In this work, we present a new downscaling technique which is based on kernel-based image filtering concept. We propose to use pairwise co-occurrence similarity of the pixelpairs as the range kernel similarity in the filtering operation. The co-occurrence of the pixel-pair is learned directly from the input image. This co-occurrence learning is performed in a neighborhood based fashion all over the image. The proposed method can preserve the high-frequency structures, which were present in the input image, into the downscaled image. The idea is further extended to the case of fractions factor of downscaling. The resulting images retain visually-important details and do not suffer from edge-blurring artifact. We demonstrate the effectiveness of our proposed approach with extensive experiments on a large number of images downscaled with various downscaling factors.