Accurate and robust image superresolution by neural processing of local image representations

TL;DR

This paper introduces a new neural superresolution method that uses local image models and PCA to improve accuracy and robustness, reducing computational costs compared to classical Bayesian approaches.

Contribution

It advances superresolution by integrating local image models with neural processing and PCA, enhancing performance and robustness over previous hybrid architectures.

Findings

High accuracy in superresolution tasks

Robustness to noise demonstrated

Effect of input dimension on performance analyzed

Abstract

Image superresolution involves the processing of an image sequence to generate a still image with higher resolution. Classical approaches, such as bayesian MAP methods, require iterative minimization procedures, with high computational costs. Recently, the authors proposed a method to tackle this problem, based on the use of a hybrid MLP-PNN architecture. In this paper, we present a novel superresolution method, based on an evolution of this concept, to incorporate the use of local image models. A neural processing stage receives as input the value of model coefficients on local windows. The data dimensionality is firstly reduced by application of PCA. An MLP, trained on synthetic sequences with various amounts of noise, estimates the high-resolution image data. The effect of varying the dimension of the network input space is examined, showing a complex, structured behavior. Quantitative results are presented showing the accuracy and robustness of the proposed method.