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
What You See is What You Get: Exploiting Visibility for 3D Object Detection
TL;DR: In this paper, a voxelized visibility map is added as an additional input stream for 3D detector, which can significantly improve the overall detection accuracy of a state-of-the-art detector.
Proceedings ArticleDOI
RIO: 3D Object Instance Re-Localization in Changing Indoor Environments
TL;DR: A new data-driven approach that efficiently finds matching features using a fully-convolutional 3D correspondence network operating on multiple spatial scales is introduced, which outperforms state-of-the-art baselines on the authors' newly-established benchmark, achieving an accuracy of 30.58%.
Proceedings ArticleDOI
Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks
TL;DR: In this article, the authors address the trade-off between reconstruction quality and number of parts with Neural Parts, a novel 3D primitive representation that defines primitives using an Invertible Neural Network (INN) which implements homeomorphic mappings between a sphere and the target object.
Book ChapterDOI
PUGeo-Net: A Geometry-Centric Network for 3D Point Cloud Upsampling
TL;DR: Zhang et al. as mentioned in this paper proposed a novel deep neural network based method, called PUGeo-Net, which learns a linear transformation matrix for each input point and projects the samples to the curved surface by computing a displacement along the normal of the tangent plane.
Posted Content
MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation
Chen Liu,Yasutaka Furukawa +1 more
TL;DR: A new approach for 3D instance segmentation based on sparse convolution and point affinity prediction, which indicates the likelihood of two points belonging to the same instance, is proposed.