Proceedings ArticleDOI
Learning to Sample
Oren Dovrat,Itai Lang,Shai Avidan +2 more
- pp 2760-2769
Reads0
Chats0
TLDR
In this article, a deep network is proposed to simplify 3D point clouds by taking a point cloud and producing a smaller point cloud that is optimized for a particular task, but the simplified point cloud is not guaranteed to be a subset of the original point cloud.Abstract:
Processing large point clouds is a challenging task. Therefore, the data is often sampled to a size that can be processed more easily. The question is how to sample the data? A popular sampling technique is Farthest Point Sampling (FPS). However, FPS is agnostic to a downstream application (classification, retrieval, etc.). The underlying assumption seems to be that minimizing the farthest point distance, as done by FPS, is a good proxy to other objective functions. We show that it is better to learn how to sample. To do that, we propose a deep network to simplify 3D point clouds. The network, termed S-NET, takes a point cloud and produces a smaller point cloud that is optimized for a particular task. The simplified point cloud is not guaranteed to be a subset of the original point cloud. Therefore, we match it to a subset of the original points in a post-processing step. We contrast our approach with FPS by experimenting on two standard data sets and show significantly better results for a variety of applications. Our code is publicly available.read more
Citations
More filters
Proceedings ArticleDOI
RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds
Qingyong Hu,Bo Yang,Linhai Xie,Stefano Rosa,Yulan Guo,Zhihua Wang,Niki Trigoni,Andrew Markham +7 more
TL;DR: This paper introduces RandLA-Net, an efficient and lightweight neural architecture to directly infer per-point semantics for large-scale point clouds, and introduces a novel local feature aggregation module to progressively increase the receptive field for each 3D point, thereby effectively preserving geometric details.
Proceedings ArticleDOI
PointFlow: 3D Point Cloud Generation With Continuous Normalizing Flows
TL;DR: PointFlow as discussed by the authors proposes a principled probabilistic framework to generate 3D point clouds by modeling them as a distribution of distributions, where the first level is the distribution of shapes and the second level is given a shape.
Book ChapterDOI
SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation
TL;DR: Li et al. as mentioned in this paper proposed Spatially-Adaptive Convolution (SAC) to adopt different filters for different locations according to the input image, which can be implemented as a series of element-wise multiplications, im2col, and standard convolution.
Proceedings ArticleDOI
SampleNet: Differentiable Point Cloud Sampling
Itai Lang,Asaf Manor,Shai Avidan +2 more
TL;DR: This work introduces a novel differentiable relaxation for point cloud sampling that approximates sampled points as a mixture of points in the primary input cloud and outperforms existing non-learned and learned sampling alternatives.
Journal ArticleDOI
Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds
TL;DR: Ziyan et al. as discussed by the authors proposed a spherical kernel for efficient graph convolution of 3D point clouds, which is applied to graph neural networks without edge-dependent filter generation, making it computationally attractive for large point clouds.
References
More filters
Journal ArticleDOI
An introduction to variable and feature selection
Isabelle Guyon,André Elisseeff +1 more
TL;DR: The contributions of this special issue cover a wide range of aspects of variable selection: providing a better definition of the objective function, feature construction, feature ranking, multivariate feature selection, efficient search methods, and feature validity assessment methods.
Proceedings ArticleDOI
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
TL;DR: This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing.
Journal ArticleDOI
Wrappers for feature subset selection
Ron Kohavi,George H. John +1 more
TL;DR: The wrapper method searches for an optimal feature subset tailored to a particular algorithm and a domain and compares the wrapper approach to induction without feature subset selection and to Relief, a filter approach tofeature subset selection.
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.
Journal ArticleDOI
Dynamic Graph CNN for Learning on Point Clouds
TL;DR: This work proposes a new neural network module suitable for CNN-based high-level tasks on point clouds, including classification and segmentation called EdgeConv, which acts on graphs dynamically computed in each layer of the network.