资源论文Optimal Relative Pose with Unknown Correspondences

Optimal Relative Pose with Unknown Correspondences

2019-12-20 | |  57 |   38 |   0

Abstract

Previous work on estimating the epipolar geometry oftwo views relies on being able to reliably match featurepoints based on appearance. In this paper, we go onestep further and show that it is feasible to compute boththe epipolar geometry and the correspondences at the sametime based on geometry only. We do this in a globally opti-mal manner. Our approach is based on an efficient branch and bound technique in combination with bipartite matching to solve the correspondence problem. We rely on several recent works to obtain good bounding functions to battle thecombinatorial explosion of possible matchings. It is experi-mentally demonstrated that more difficult cases can be handled and that more inlier correspondences can be obtained by being less restrictive in the matching phase.

上一篇:Fast ConvNets Using Group-wise Brain Damage

下一篇:End-to-End Learning of Deformable Mixture of Parts and Deep Convolutional Neural Networks for Human Pose Estimation

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Joint Pose and Ex...

    Facial expression recognition (FER) is a challe...