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
An integrated algorithm for ego-vehicle and obstacles state estimation for autonomous driving
Mattia Bersani,Simone Mentasti,Pragyan Dahal,Stefano Arrigoni,Michele Vignati,Federico Cheli,Matteo Matteucci +6 more
TL;DR: This paper presents an integrated algorithm for the estimation of ego-vehicle and obstacles’ positioning and motion along a given road, modeled in curvilinear coordinates, validated through experimental tests carried on a prototype of an autonomous vehicle.
Posted Content
CAE-LO: LiDAR Odometry Leveraging Fully Unsupervised Convolutional Auto-Encoder for Interest Point Detection and Feature Description.
Deyu Yin,Qian Zhang,Jingbin Liu,Xinlian Liang,Yunsheng Wang,Jyri Maanpää,Hao Ma,Juha Hyyppä,Ruizhi Chen +8 more
TL;DR: A fully unsupervised Convolutional Auto-Encoder based LiDAR Odometry (CAE-LO) that detects interest points from spherical ring data using 2DCAE and extracts features from multi-resolution voxel model using 3D CAE and a backward pose update method.
Posted Content
Deep Generative Modeling for Scene Synthesis via Hybrid Representations
Zaiwei Zhang,Zhenpei Yang,Chongyang Ma,Linjie Luo,Alexander G. Huth,Etienne Vouga,Qixing Huang +6 more
TL;DR: In this paper, a deep generative scene modeling technique for indoor environments is presented, which uses a feed-forward neural network that maps a prior distribution (e.g., a normal distribution) to the distribution of primary objects in indoor scenes.
Journal ArticleDOI
Data Processing Approaches on SPAD-Based d-TOF LiDAR Systems: A Review
TL;DR: A breakthrough is sought to improve the performance of single-photon-avalanche-diode-based direct time-of-flight LiDAR systems by reviewing the data processing stages and corresponding processing approaches for LiDar measurements, starting from photon incidence and ending with high-level feature recognition.
Proceedings ArticleDOI
3D Neighborhood Convolution: Learning Depth-Aware Features for RGB-D and RGB Semantic Segmentation
TL;DR: Wang et al. as discussed by the authors proposed 3D Neighborhood Convolution (3DN-Conv), a convolutional operator around 3D neighborhoods, where the depth channel is used to adapt the receptive field of the convolution, which yields the resulting filters invariant to scale and focusing on a certain range of depth.