Learning Compact Geometric Features
Marc Khoury,Qian-Yi Zhou,Vladlen Koltun +2 more
- pp 153-161
Reads0
Chats0
TLDR
It is shown that features with precision, compactness, and robustness can be learned from data, by optimizing deep networks that map high-dimensional histograms into low-dimensional Euclidean spaces.Abstract:
We present an approach to learning features that represent the local geometry around a point in an unstructured point cloud. Such features play a central role in geometric registration, which supports diverse applications in robotics and 3D vision. Current state-of-the-art local features for unstructured point clouds have been manually crafted and none combines the desirable properties of precision, compactness, and robustness. We show that features with these properties can be learned from data, by optimizing deep networks that map high-dimensional histograms into low-dimensional Euclidean spaces. The presented approach yields a family of features, parameterized by dimension, that are both more compact and more accurate than existing descriptors.read more
Citations
More filters
Posted Content
Open3D: A Modern Library for 3D Data Processing
TL;DR: Open3D is an open-source library that supports rapid development of software that deals with 3D data and is used in a number of published research projects and is actively deployed in the cloud.
Journal ArticleDOI
Image Matching from Handcrafted to Deep Features: A Survey
TL;DR: This survey introduces feature detection, description, and matching techniques from handcrafted methods to trainable ones and provides an analysis of the development of these methods in theory and practice, and briefly introduces several typical image matching-based applications.
Proceedings ArticleDOI
PPFNet: Global Context Aware Local Features for Robust 3D Point Matching
TL;DR: Qualitative and quantitative evaluations of the PPFNet network suggest increased recall, improved robustness and invariance as well as a vital step in the 3D descriptor extraction performance.
Proceedings ArticleDOI
Fully Convolutional Geometric Features
TL;DR: This work presents fully-convolutional geometric features, computed in a single pass by a 3D fully- Convolutional network, which achieve state-of-the-art accuracy without requiring prepossessing, are compact, and are 290 times faster than the most accurate prior method.
Proceedings ArticleDOI
Tangent Convolutions for Dense Prediction in 3D
TL;DR: Tangent convolutions as discussed by the authors is a new construction for convolutional networks on 3D data that operates directly on surface geometry and is applicable to unstructured point clouds and other noisy real-world data.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Journal ArticleDOI
A method for registration of 3-D shapes
Paul J. Besl,H.D. McKay +1 more
TL;DR: In this paper, the authors describe a general-purpose representation-independent method for the accurate and computationally efficient registration of 3D shapes including free-form curves and surfaces, based on the iterative closest point (ICP) algorithm, which requires only a procedure to find the closest point on a geometric entity to a given point.
Proceedings ArticleDOI
FaceNet: A unified embedding for face recognition and clustering
TL;DR: A system that directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure offace similarity, and achieves state-of-the-art face recognition performance using only 128-bytes perface.
Proceedings ArticleDOI
3D ShapeNets: A deep representation for volumetric shapes
TL;DR: This work proposes to represent a geometric 3D shape as a probability distribution of binary variables on a 3D voxel grid, using a Convolutional Deep Belief Network, and shows that this 3D deep representation enables significant performance improvement over the-state-of-the-arts in a variety of tasks.