Patch-Based Image Hallucination for Super Resolution with Detail Reconstruction from Similar Sample Images

TL;DR

This paper introduces a novel patch-based image hallucination algorithm that synthesizes high-frequency details for super-resolution, outperforming existing methods and producing more realistic, detailed images from low-resolution inputs.

Contribution

The paper presents the first patch-based method capable of reconstructing high-frequency details in super-resolution, utilizing similar images from personal collections or online databases.

Findings

Superior visual quality compared to state-of-the-art methods

Statistically significant improvements verified by user study

Robust performance across diverse images

Abstract

Image hallucination and super-resolution have been studied for decades, and many approaches have been proposed to upsample low-resolution images using information from the images themselves, multiple example images, or large image databases. However, most of this work has focused exclusively on small magnification levels because the algorithms simply sharpen the blurry edges in the upsampled images - no actual new detail is typically reconstructed in the final result. In this paper, we present a patch-based algorithm for image hallucination which, for the first time, properly synthesizes novel high frequency detail. To do this, we pose the synthesis problem as a patch-based optimization which inserts coherent, high-frequency detail from contextually-similar images of the same physical scene/subject provided from either a personal image collection or a large online database. The resulting image is visually plausible and contains coherent high frequency information. We demonstrate the robustness of our algorithm by testing it on a large number of images and show that its performance is considerably superior to all state-of-the-art approaches, a result that is verified to be statistically significant through a randomized user study.