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
Journal ArticleDOI
Multi-directional geodesic neural networks via equivariant convolution
Adrien Poulenard,Maks Ovsjanikov +1 more
TL;DR: This work defines directional convolution in the continuous setting, proves its key properties and shows how it can be implemented in practice, for shapes represented as triangle meshes, where it shows a significant improvement over several baselines.
Proceedings ArticleDOI
ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection
TL;DR: ST3D as discussed by the authors proposed a domain adaptive self-training pipeline, named ST3D, for unsupervised domain adaptation on 3D object detection from point clouds by pre-training the 3D detector on the source domain with a proposed random object scaling strategy for mitigating the negative effects of source domain bias.
Journal ArticleDOI
A Comprehensive Survey on Geometric Deep Learning
TL;DR: This work aims to provide a comprehensive survey of geometric deep learning and related methods, introducing the relevant knowledge and history of geometricDeep learning field as well as the theoretical background and reviewing different graph network models for graphs and manifold data.
Proceedings ArticleDOI
PointCloud Saliency Maps
TL;DR: A novel way of characterizing critical points and segments to build point-cloud saliency maps is proposed, and each saliency score can be efficiently measured by the corresponding gradient of the loss w.r.t the point under the spherical coordinates.
Posted Content
A Graph-CNN for 3D Point Cloud Classification
Yingxue Zhang,Michael G. Rabbat +1 more
TL;DR: PointGCN as mentioned in this paper combines localized graph convolutions with two types of graph downsampling operations (also known as pooling) and achieves competitive performance on the 3D object classification benchmark ModelNet.