FN-Net:Remove the Outliers by Filtering the Noise

TL;DR

This paper introduces FN-Net, a CNN-based method that effectively filters out outliers caused by noise in feature point matching, improving the accuracy of relative pose estimation between images.

Contribution

The paper presents a novel adaptive denoising module using a soft threshold function to reduce outlier noise in feature matching, enhancing pose estimation accuracy.

Findings

Outperforms state-of-the-art methods on YFCC100M dataset

Effectively filters out noise-induced outliers

Improves relative pose estimation accuracy

Abstract

Establishing the correspondence between two images is an important research direction of computer vision. When estimating the relationship between two images, it is often disturbed by outliers. In this paper, we propose a convolutional neural network that can filter the noise of outliers. It can output the probability that the pair of feature points is an inlier and regress the essential matrix representing the relative pose of the camera. The outliers are mainly caused by the noise introduced by the previous processing. The outliers rejection can be treated as a problem of noise elimination, and the soft threshold function has a very good effect on noise reduction. Therefore, we designed an adaptive denoising module based on soft threshold function to remove noise components in the outliers, to reduce the probability that the outlier is predicted to be an inlier. Experimental results on the YFCC100M dataset show that our method exceeds the state-of-the-art in relative pose estimation.