E3CM: Epipolar-Constrained Cascade Correspondence Matching

TL;DR

E3CM introduces a novel, training-free correspondence matching method that leverages epipolar constraints and a cascade structure, outperforming traditional and deep learning approaches without requiring annotated data.

Contribution

The paper presents E3CM, a new epipolar-constrained cascade matching approach that does not need training data, improving robustness and accuracy in correspondence matching tasks.

Findings

E3CM outperforms existing methods in accuracy and robustness.

The method requires no annotated training data.

Source code is publicly available for reproducibility.

Abstract

Accurate and robust correspondence matching is of utmost importance for various 3D computer vision tasks. However, traditional explicit programming-based methods often struggle to handle challenging scenarios, and deep learning-based methods require large well-labeled datasets for network training. In this article, we introduce Epipolar-Constrained Cascade Correspondence (E3CM), a novel approach that addresses these limitations. Unlike traditional methods, E3CM leverages pre-trained convolutional neural networks to match correspondence, without requiring annotated data for any network training or fine-tuning. Our method utilizes epipolar constraints to guide the matching process and incorporates a cascade structure for progressive refinement of matches. We extensively evaluate the performance of E3CM through comprehensive experiments and demonstrate its superiority over existing methods. To promote further research and facilitate reproducibility, we make our source code publicly available at https://mias.group/E3CM.