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
Posted Content
Self-Supervised Few-Shot Learning on Point Clouds
Charu Sharma,Manohar Kaul +1 more
TL;DR: A comprehensive empirical evaluation of the self-supervised learning method is presented and it is shown that supervised methods pre-trained with the method significantly improve the accuracy of state-of-the-art methods and also outperforms previous unsupervised methods in downstream classification tasks.
Proceedings ArticleDOI
Supervised Fitting of Geometric Primitives to 3D Point Clouds
TL;DR: Supervised primitive fitting network (SPFN) as mentioned in this paper is an end-to-end neural network that can robustly detect a varying number of primitives at different scales without any user control.
Posted Content
Scan2Cap: Context-aware Dense Captioning in RGB-D Scans
TL;DR: This work proposes Scan2Cap, an end-to-end trained method to detect objects in the input scene and describe them in natural language, which can effectively localize and describe 3D objects in scenes from the ScanRefer dataset, outperforming 2D baseline methods by a significant margin.
Posted Content
SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters
TL;DR: SpiderCNN as mentioned in this paper extends convolutional operations from regular grids to irregular point set that can be embedded in R^n, by parametrizing a family of CNN filters, and designs the filter as a product of simple step function that captures local geodesic information and a Taylor polynomial that ensures the expressiveness.
Posted Content
3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection
TL;DR: It is proposed to use the estimated 3D IoU as a localization metric and set category-aware self-adjusted thresholds to filter poorly localized proposals and set confidence thresholds based upon the predicted objectness and class probability to filter low-quality pseudo-labels.