资源论文Pose Priors for Simultaneously Solving Alignment and Correspondence*

Pose Priors for Simultaneously Solving Alignment and Correspondence*

2020-03-30 | |  95 |   44 |   0

Abstract

Estimating a camera pose given a set of 3D-ob ject and 2D- image feature points is a well understood problem when correspondences are given. However, when such correspondences cannot be established a priori, one must simultaneously compute them along with the pose. Most current approaches to solving this problem are too computationally in- tensive to be practical. An interesting exception is the SoftPosit algo- rithm, that looks for the solution as the minimum of a suitable ob jective function. It is arguably one of the best algorithms but its iterative na- ture means it can fail in the presence of clutter, occlusions, or repetitive patterns. In this paper, we propose an approach that overcomes this limi- tation by taking advantage of the fact that, in practice, some prior on the camera pose is often available. We model it as a Gaussian Mixture Model that we progressively refine by hypothesizing new correspondences. This rapidly reduces the number of potential matches for each 3D point and lets us explore the pose space more thoroughly than SoftPosit at a sim- ilar computational cost. We will demonstrate the superior performance of our approach on both synthetic and real data.

上一篇:Beyond Nouns: Exploiting Prepositions and Comparative Adjectives for Learning Visual Classifiers*

下一篇:Unsupervised Classification and Part Localization by Consistency Amplification

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

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

  • Rating-Boosted La...

    The performance of a recommendation system reli...