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-View Saliency Guided Deep Neural Network for 3-D Object Retrieval and Classification
TL;DR: The proposed MVSG-DNN can discover the discriminative structure of multi-view sequence without constraints of specific camera settings and can support flexible 3D object retrieval and classification for real applications by avoiding the required camera settings.
Book ChapterDOI
Self-supervised Single-View 3D Reconstruction via Semantic Consistency
TL;DR: In this article, a self-supervised, single-view 3D reconstruction model that predicts the 3D mesh shape, texture and camera pose of a target object with a collection of 2D images and silhouettes is proposed.
Journal ArticleDOI
Role of Deep Learning in Loop Closure Detection for Visual and Lidar SLAM: A Survey.
Saba Arshad,Gon-Woo Kim +1 more
TL;DR: Loop closure detection is of vital importance in the process of simultaneous localization and mapping (SLAM), as it helps to reduce the cumulative error of the robot's estimated pose and generate a consistent global map.
Proceedings ArticleDOI
SSRNet: Scalable 3D Surface Reconstruction Network
TL;DR: SSRNet as discussed by the authors constructs local geometry-aware features for octree vertices and designs a scalable reconstruction pipeline, which not only greatly enhances the predication accuracy of the relative position between the vertices between the implicit surface facilitating the surface reconstruction quality, but also allows dividing the point cloud and octree nodes and processing different parts in parallel for superior scalability.
Posted Content
Embodied Question Answering in Photorealistic Environments with Point Cloud Perception
Erik Wijmans,Samyak Datta,Oleksandr Maksymets,Abhishek Das,Georgia Gkioxari,Stefan Lee,Irfan Essa,Devi Parikh,Dhruv Batra +8 more
TL;DR: It is found that point clouds provide a richer signal than RGB images for learning obstacle avoidance, motivating the use (and continued study) of 3D deep learning models for embodied navigation.