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
VERAM: View-Enhanced Recurrent Attention Model for 3D Shape Classification
TL;DR: In this article, a view-enhanced recurrent attention model is proposed to select a sequence of views for highly accurate 3D shape classification, achieving state-of-the-art performance.
Posted Content
PU-Net: Point Cloud Upsampling Network.
TL;DR: In this article, a multi-branch convolutional unit implicitly in feature space is used to learn multi-level features per point and expand the point set via a multilayer CNN, which is then reconstructed to an upsampled point set.
Proceedings ArticleDOI
Self-Supervised Learning on 3D Point Clouds by Learning Discrete Generative Models
TL;DR: In this paper, a self-supervised loss is formed under the interpretation that these soft partitions implicitly parameterize a latent Gaussian Mixture Model (GMM), and that this generative model establishes a data likelihood function.
Posted Content
JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds
TL;DR: This paper tackles the 3D semantic edge detection task for the first time and presents a new two-stream fully-convolutional network that jointly performs the two tasks and proposes a novel loss function that encourages the network to produce semantic segmentation results with better boundaries.
Posted Content
A Survey on Deep Geometry Learning: From a Representation Perspective
TL;DR: Recent developments in deep learning for 3D geometry from a representation perspective are reviewed, summarizing the advantages and disadvantages of different representations for different applications and present existing datasets in these representations.