Learning Descriptors for Object Recognition and 3D Pose Estimation

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)(2015)

引用 533|浏览71
暂无评分
摘要
Detecting poorly textured objects and estimating their 3D pose reliably is still a very challenging problem. We introduce a simple but powerful approach to computing descriptors for object views that efficiently capture both the object identity and 3D pose. By contrast with previous manifold-based approaches, we can rely on the Euclidean distance to evaluate the similarity between descriptors, and therefore use scalable Nearest Neighbor search methods to efficiently handle a large number of objects under a large range of poses. To achieve this, we train a Convolutional Neural Network to compute these descriptors by enforcing simple similarity and dissimilarity constraints between the descriptors. We show that our constraints nicely untangle the images from different objects and different views into clusters that are not only well-separated but also structured as the corresponding sets of poses: The Euclidean distance between descriptors is large when the descriptors are from different objects, and directly related to the distance between the poses when the descriptors are from the same object. These important properties allow us to outperform state-of-the-art object views representations on challenging RGB and RGB-D data.
更多
查看译文
关键词
learning descriptors,object recognition,3D pose estimation,textured objects detection,object views,object identity,Euclidean distance,descriptors similarity,nearest neighbor search methods,convolutional neural network,dissimilarity constraints
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