An End to End Network Architecture for Fundamental Matrix Estimation

TL;DR

This paper introduces a novel end-to-end neural network architecture that directly estimates the fundamental matrix from stereo images, integrating correspondence finding, outlier rejection, and matrix calculation into a unified model.

Contribution

The paper proposes a new end-to-end network with a specialized loss function and evaluation metric for accurate fundamental matrix estimation from stereo images.

Findings

Outperforms traditional methods in accuracy.

Achieves significant improvements over previous deep learning approaches.

Effective on both indoor and outdoor datasets.

Abstract

In this paper, we present a novel end-to-end network architecture to estimate fundamental matrix directly from stereo images. To establish a complete working pipeline, different deep neural networks in charge of finding correspondences in images, performing outlier rejection and calculating fundamental matrix, are integrated into an end-to-end network architecture. To well train the network and preserve geometry properties of fundamental matrix, a new loss function is introduced. To evaluate the accuracy of estimated fundamental matrix more reasonably, we design a new evaluation metric which is highly consistent with visualization result. Experiments conducted on both outdoor and indoor data-sets show that this network outperforms traditional methods as well as previous deep learning based methods on various metrics and achieves significant performance improvements.