Multi-View Feature Engineering And Learning
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)(2015)
摘要
We frame the problem of local representation of imaging data as the computation of minimal sufficient statistics that are invariant to nuisance variability induced by viewpoint and illumination. We show that, under very stringent conditions, these are related to "feature descriptors" commonly used in Computer Vision. Such conditions can be relaxed if multiple views of the same scene are available. We propose a sampling-based and a point-estimate based approximation of such a representation, compared empirically on image-to-(multiple) image matching, for which we introduce a multi-view wide-baseline matching benchmark, consisting of a mixture of real and synthetic objects with ground truth camera motion and dense three-dimensional geometry.
更多查看译文
关键词
multiview feature engineering,multiview feature learning,imaging data,minimal sufficient statistics,nuisance variability,feature descriptor,computer vision,sampling-based approximation,point-estimate based approximation,image-to-multiple image matching,multiview wide-baseline matching benchmark,ground truth camera motion,three-dimensional geometry
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络