EXTRACTER: Efficient Texture Matching with Attention and Gradient Enhancing for Large Scale Image Super Resolution

TL;DR

EXTRACTER introduces an efficient texture matching method for large-scale image super-resolution, utilizing attention and gradient enhancement to improve accuracy and memory efficiency over existing reference-based approaches.

Contribution

The paper proposes a deep search method that reduces memory usage and accurately finds top texture matches for super-resolution, with gradient density enhancement.

Findings

Achieves competitive PSNR and SSIM metrics.

Reduces memory usage significantly compared to existing methods.

Provides more accurate texture matching for large images.

Abstract

Recent Reference-Based image super-resolution (RefSR) has improved SOTA deep methods introducing attention mechanisms to enhance low-resolution images by transferring high-resolution textures from a reference high-resolution image. The main idea is to search for matches between patches using LR and Reference image pair in a feature space and merge them using deep architectures. However, existing methods lack the accurate search of textures. They divide images into as many patches as possible, resulting in inefficient memory usage, and cannot manage large images. Herein, we propose a deep search with a more efficient memory usage that reduces significantly the number of image patches and finds the $k$ most relevant texture match for each low-resolution patch over the high-resolution reference patches, resulting in an accurate texture match. We enhance the Super Resolution result adding gradient density information using a simple residual architecture showing competitive metrics results: PSNR and SSMI.