Local Patch Encoding-Based Method for Single Image Super-Resolution

TL;DR

This paper introduces a novel single image super-resolution method based on local patch encoding, which classifies patches and reconstructs high-resolution images efficiently, showing promising experimental results.

Contribution

The paper proposes a new LPE-based super-resolution approach that replaces traditional dictionary learning with patch classification and projection matrices, enhancing efficiency and extendibility.

Findings

Effective super-resolution on multiple image sets

Comparable or superior to existing methods in quality

Efficient reconstruction process

Abstract

Recent learning-based super-resolution (SR) methods often focus on dictionary learning or network training. In this paper, we discuss in detail a new SR method based on local patch encoding (LPE) instead of traditional dictionary learning. The proposed method consists of a learning stage and a reconstructing stage. In the learning stage, image patches are classified into different classes by means of the proposed LPE, and then a projection matrix is computed for each class by utilizing a simple constraint. In the reconstructing stage, an input LR patch can be simply reconstructed by computing its LPE code and then multiplying the corresponding projection matrix. Furthermore, we discuss the relationship between the proposed method and the anchored neighborhood regression methods; we also analyze the extendibility of the proposed method. The experimental results on several image sets demonstrate the effectiveness of the LPE-based methods.