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
PPR-Net:Point-wise Pose Regression Network for Instance Segmentation and 6D Pose Estimation in Bin-picking Scenarios
TL;DR: A simple but novel Point-wise Pose Regression Network (PPR-Net), where for each point in the point cloud, the network regresses a 6D pose of the object instance that the point belongs to, which works well in real world robot bin-picking tasks.
Posted Content
Dense 3D Point Cloud Reconstruction Using a Deep Pyramid Network
TL;DR: DensePCR as mentioned in this paper is a deep pyramidal network for point cloud reconstruction that hierarchically predicts point clouds of increasing resolution by aggregating local and global point features to deform a grid.
Posted Content
Point Cloud Super Resolution with Adversarial Residual Graph Networks
TL;DR: A data-driven method for point cloud super-resolution based on graph networks and adversarial losses that achieves the state-of-the-art performance and have a good generalization ability to unseen data is presented.
Proceedings ArticleDOI
3d Object Detection For Autonomous Driving Using Temporal Lidar Data
Scott McCrae,Avideh Zakhor +1 more
TL;DR: This work modify PointPillars to become a recurrent network, using fewer LiDAR frames per forward pass, and when given 3 frames of data as input to both models, the recurrent architecture outperforms PointPilars by 21% and 1% in pedestrian and vehicle detection, respectively.
Journal ArticleDOI
GraNet: Global relation-aware attentional network for semantic segmentation of ALS point clouds
Rong Huang,Yusheng Xu,Uwe Stilla +2 more
TL;DR: A novel neural network focusing on semantic labeling of ALS point clouds is proposed, which investigates the importance of long-range spatial and channel-wise relations and is termed as global relation-aware attentional network (GraNet).