High-Quality and Large-Scale Image Downscaling for Modern Display Devices

TL;DR

This paper introduces LSID, a novel large-scale image downscaling technique that uses co-occurrence learning to preserve structural and perceptual details, outperforming existing methods in quality and fidelity.

Contribution

The study presents a new content-adaptive downscaling method leveraging co-occurrence profiles to maintain high-frequency details at large scales, addressing limitations of traditional techniques.

Findings

Achieves up to 39.22 dB PSNR on DIV2K dataset.

Attains PIQE score of 26.35 on DIV2K for 8x downscaling.

Outperforms contemporary approaches in visual quality and structural preservation.

Abstract

In modern display technology and visualization tools, downscaling images is one of the most important activities. This procedure aims to maintain both visual authenticity and structural integrity while reducing the dimensions of an image at a large scale to fit the dimension of the display devices. In this study, we proposed a new technique for downscaling images that uses co-occurrence learning to maintain structural and perceptual information while reducing resolution. The technique uses the input image to create a data-driven co-occurrence profile that captures the frequency of intensity correlations in nearby neighborhoods. A refined filtering process is guided by this profile, which acts as a content-adaptive range kernel. The contribution of each input pixel is based on how closely it resembles pair-wise intensity values with it's neighbors. We validate our proposed technique on four datasets: DIV2K, BSD100, Urban100, and RealSR to show its effective downscaling capacity. Our technique could obtain up to 39.22 dB PSNR on the DIV2K dataset and PIQE up to 26.35 on the same dataset when downscaling by 8x and 16x, respectively. Numerous experimental findings attest to the ability of the suggested picture downscaling method to outperform more contemporary approaches in terms of both visual quality and performance measures. Unlike most existing methods, which did not focus on the large-scale image resizing scenario, we achieve high-quality downscaled images without texture loss or edge blurring. Our method, LSID (large scale image downscaling), successfully preserves high-frequency structures like edges, textures, and repeating patterns by focusing on statistically consistent pixels while reducing aliasing and blurring artifacts that are typical of traditional downscaling techniques.