资源论文Viewpoint Induced Deformation Statistics and the Design of Viewpoint Invariant Features: Singularities and Occlusions

Viewpoint Induced Deformation Statistics and the Design of Viewpoint Invariant Features: Singularities and Occlusions

2020-03-27 | |  86 |   51 |   0

Abstract.
We study the set of domain deformations induced on im- ages of three-dimensional scenes by changes of the vantage point. We parametrize such deformations and derive empirical statistics on the pa- rameters, that show a kurtotic behavior similar to that of natural image and range statistics. Such a behavior would suggest that most defor- mations are locally smooth, and therefore could be captured by simple parametric maps, such as affine ones. However, we show that deforma- tions induced by singularities and occluding boundaries, although rare, are highly salient, thus warranting the development of dedicated de- scriptors. We therefore illustrate the development of viewpoint invariant descriptors for singularities, as well as for occluding boundaries. We test their performance on scenes where the current state of the art based on affine-invariant region descriptors fail to establish correspondence, high- lighting the features and shortcomings of our approach.

上一篇:Identification of Highly Similar 3D Objects Using Model Saliency

下一篇:Smooth Image Segmentation by Nonparametric Bayesian Inference

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...

  • Learning to learn...

    The move from hand-designed features to learned...

  • A Mathematical Mo...

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