A LBP Based Correspondence Identification Scheme for Multi-view Sensing Network

TL;DR

This paper introduces a real-time correspondence identification method for multi-view sensing using LBP and belief propagation, achieving high accuracy and efficiency for applications like 3D reconstruction.

Contribution

The paper presents a novel real-time correspondence identification scheme combining LBP, normalized cross correlation, and belief propagation, outperforming existing methods in accuracy and simplicity.

Findings

Outperforms state-of-the-art in accuracy and precision

Enables real-time multi-view correspondence identification

Suitable for practical applications like 3D reconstruction

Abstract

In this paper, we describes a correspondence identification method between two-views of regular RGB camera that can be run in real-time. The basic idea is first applying normalized cross correlation to retrieve a sparse set of matching pairs from image pair. Then loopy belief propagation scheme is applied to the the set of possible candidates to densely identify correspondences from different views. The experiment results demonstrate superb accuracy and precision that outperform the state-of-the-art in the computer vision field. Meanwhile, the implementation is simple enough that can be optimized for real-time performance. We have given the detailed comparison of existing approaches and show that this method can enable various practical applications from 3D reconstruction to image search.