Open AccessProceedings Article
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
Charles R. Qi,Li Yi,Hao Su,Leonidas J. Guibas +3 more
- Vol. 30, pp 5099-5108
Reads0
Chats0
TLDR
PointNet++ as discussed by the authors applies PointNet recursively on a nested partitioning of the input point set to learn local features with increasing contextual scales, and proposes novel set learning layers to adaptively combine features from multiple scales.Abstract:
Few prior works study deep learning on point sets. PointNet is a pioneer in this direction. However, by design PointNet does not capture local structures induced by the metric space points live in, limiting its ability to recognize fine-grained patterns and generalizability to complex scenes. In this work, we introduce a hierarchical neural network that applies PointNet recursively on a nested partitioning of the input point set. By exploiting metric space distances, our network is able to learn local features with increasing contextual scales. With further observation that point sets are usually sampled with varying densities, which results in greatly decreased performance for networks trained on uniform densities, we propose novel set learning layers to adaptively combine features from multiple scales. Experiments show that our network called PointNet++ is able to learn deep point set features efficiently and robustly. In particular, results significantly better than state-of-the-art have been obtained on challenging benchmarks of 3D point clouds.read more
Citations
More filters
Proceedings ArticleDOI
SO-HandNet: Self-Organizing Network for 3D Hand Pose Estimation With Semi-Supervised Learning
TL;DR: Inspired by the point cloud autoencoder presented in self-organizing network (SO-Net), the proposed SO-HandNet aims at making use of the unannotated data to obtain accurate 3D hand pose estimation in a semi-supervised manner.
Posted Content
Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN
TL;DR: The proposed Geo-CNN applies a generic convolution-like operation dubbed as GeoConv to each point and its local neighborhood, which encourages the network to preserve the geometric structure in Euclidean space throughout the feature extraction hierarchy.
Proceedings ArticleDOI
RPM-Net: Robust Point Matching Using Learned Features
Zi Jian Yew,Gim Hee Lee +1 more
TL;DR: RPMNet as mentioned in this paper uses the differentiable Sinkhorn layer and annealing to get soft assignments of point correspondences from hybrid features learned from both spatial coordinates and local geometry.
Proceedings ArticleDOI
ACNe: Attentive Context Normalization for Robust Permutation-Equivariant Learning
TL;DR: In this article, the authors propose an attention-based normalization of the feature maps of a permutation-equivariant network to find the essential data points in high-dimensional space to solve a given task.
Journal ArticleDOI
SHPR-Net: Deep Semantic Hand Pose Regression From Point Clouds
TL;DR: A deep semantic hand pose regression network (SHPR-Net) for hand pose estimation from point sets, which consists of two subnetworks: a semantic segmentation subnetwork and a hand poses regression subnetwork, which is more robust to geometric transformations.