A hybrid MLP-PNN architecture for fast image superresolution

TL;DR

This paper introduces a hybrid neural network approach combining MLP and PNN for fast image superresolution, significantly reducing computational costs while maintaining high image quality.

Contribution

A novel hybrid MLP-PNN architecture for superresolution that decreases computational load and adapts to noise levels, with optimized kernel functions trained on synthetic data.

Findings

Effective super-resolution on real outdoor sequences

Reduced computational complexity compared to classical methods

Quantitative analysis of noise dependence

Abstract

Image superresolution methods process an input image sequence of a scene to obtain a still image with increased resolution. Classical approaches to this problem involve complex iterative minimization procedures, typically with high computational costs. In this paper is proposed a novel algorithm for super-resolution that enables a substantial decrease in computer load. First, a probabilistic neural network architecture is used to perform a scattered-point interpolation of the image sequence data. The network kernel function is optimally determined for this problem by a multi-layer perceptron trained on synthetic data. Network parameters dependence on sequence noise level is quantitatively analyzed. This super-sampled image is spatially filtered to correct finite pixel size effects, to yield the final high-resolution estimate. Results on a real outdoor sequence are presented, showing the quality of the proposed method.