Reconstruction of images taken by a pair of non-regular sampling sensors using correlation based matching

TL;DR

This paper proposes a stereo image reconstruction method using non-regular sampling sensors and correlation-based matching, improving image quality by leveraging multi-view information.

Contribution

It introduces a stereo reconstruction framework that enhances image quality by combining non-regular sampling with cross-view correlation, surpassing single-view methods.

Findings

Average PSNR gain of 0.74 dB over single-view algorithms

Effective use of multi-view correlation improves reconstruction quality

Cost-effective alternative to multi-camera systems

Abstract

Multi-view image acquisition systems with two or more cameras can be rather costly due to the number of high resolution image sensors that are required. Recently, it has been shown that by covering a low resolution sensor with a non-regular sampling mask and by using an efficient algorithm for image reconstruction, a high resolution image can be obtained. In this paper, a stereo image reconstruction setup for multi-view scenarios is proposed. A scene is captured by a pair of non-regular sampling sensors and by incorporating information from the adjacent view, the reconstruction quality can be increased. Compared to a state-of-the-art single-view reconstruction algorithm, this leads to a visually noticeable average gain in PSNR of 0.74 dB.