Edge-Informed Single Image Super-Resolution

TL;DR

This paper introduces an edge-informed single image super-resolution method that reformulates the problem as image inpainting, leveraging structure and texture separation to improve high-resolution image quality.

Contribution

It proposes a novel two-stage inpainting model for super-resolution that decouples structure and texture reconstruction, enhancing image quality over existing methods.

Findings

Outperforms basic interpolation schemes at multiple scale factors

Improves high-resolution image quality by decoupling structure and texture

Demonstrates effectiveness through quantitative and qualitative comparisons

Abstract

The recent increase in the extensive use of digital imaging technologies has brought with it a simultaneous demand for higher-resolution images. We develop a novel edge-informed approach to single image super-resolution (SISR). The SISR problem is reformulated as an image inpainting task. We use a two-stage inpainting model as a baseline for super-resolution and show its effectiveness for different scale factors (x2, x4, x8) compared to basic interpolation schemes. This model is trained using a joint optimization of image contents (texture and color) and structures (edges). Quantitative and qualitative comparisons are included and the proposed model is compared with current state-of-the-art techniques. We show that our method of decoupling structure and texture reconstruction improves the quality of the final reconstructed high-resolution image. Code and models available at: https://github.com/knazeri/edge-informed-sisr