Sgm-Nets: Semi-Global Matching With Neural Networks
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)(2017)
摘要
This paper deals with deep neural networks for predicting accurate dense disparity map with Semi-global matching (SGM). SGM is a widely used regularization method for real scenes because of its high accuracy and fast computation speed. Even though SGM can obtain accurate results, tuning of SGM's penalty-parameters, which control a smoothness and discontinuity of a disparity map, is uneasy and empirical methods have been proposed. We propose a learning based penalties estimation method, which we call SGM-Nets that consist of Convolutional Neural Networks. A small image patch and its position are input into SGM-Nets to predict the penalties for the 3D object structures. In order to train the networks, we introduce a novel loss function which is able to use sparsely annotated disparity maps such as captured by a LiDAR sensor in real environments. Moreover, we propose a novel SGM parameterization, which deploys different penalties depending on either positive or negative disparity changes in order to represent the object structures more discriminatively.Our SGM-Nets outperformed state of the art accuracy on KITTI benchmark datasets.
更多查看译文
关键词
SGMs penalty-parameters,learning based penalties estimation method,Convolutional Neural Networks,sparsely annotated disparity maps,positive disparity changes,negative disparity changes,semiglobal matching,deep neural networks,accurate dense disparity map,regularization method,SGM-Nets,SGM parameterization,3D object structures,LiDAR sensor,KITTI benchmark datasets
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要