arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2201.09213cs.CVcs.AIcs.LG
收藏

FN-Net:通过过滤噪声去除离群值

FN-Net:Remove the Outliers by Filtering the Noise

Tsinghua University(清华大学)

Kai Lv

摘要:

建立两幅图像之间的对应关系是计算机视觉的一个重要研究方向。在估计两幅图像之间的关系时,经常会受到野值的干扰。本文提出了一种能够滤除野值噪声的卷积神经网络。它可以输出特征点对是内点的概率,并回归表示相机相对位姿的本质矩阵。异常值主要是由先前处理引入的噪声引起的。野值剔除可以看作是一个去噪问题,软阈值函数具有很好的去噪效果。为此,设计了一种基于软阈值函数的自适应去噪模块,去除离群点中的噪声成分,降低离群点被预测为内点的概率。在YFCC 100 M数据集上的实验结果表明,该方法在相对姿态估计方面优于现有技术。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑