FN-Net:Remove the Outliers by Filtering the Noise
This work addresses outlier rejection in computer vision for improved camera pose estimation, representing an incremental advancement in the field.
The paper tackles the problem of outlier interference in image correspondence for camera pose estimation by proposing a convolutional neural network that filters noise from outliers, achieving state-of-the-art results on the YFCC100M dataset.
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.