Deep learning for 3d point clouds: A survey

Y Guo, H Wang, Q Hu, H Liu, L Liu… - IEEE transactions on …, 2020 - ieeexplore.ieee.org
Point cloud learning has lately attracted increasing attention due to its wide applications in
many areas, such as computer vision, autonomous driving, and robotics. As a dominating …

Deep learning on point clouds and its application: A survey

W Liu, J Sun, W Li, T Hu, P Wang - Sensors, 2019 - mdpi.com
Point cloud is a widely used 3D data form, which can be produced by depth sensors, such
as Light Detection and Ranging (LIDAR) and RGB-D cameras. Being unordered and …

Spherical cnns

TS Cohen, M Geiger, J Köhler, M Welling - arXiv preprint arXiv …, 2018 - arxiv.org
Convolutional Neural Networks (CNNs) have become the method of choice for learning
problems involving 2D planar images. However, a number of problems of recent interest …

3d steerable cnns: Learning rotationally equivariant features in volumetric data

M Weiler, M Geiger, M Welling… - Advances in …, 2018 - proceedings.neurips.cc
We present a convolutional network that is equivariant to rigid body motions. The model
uses scalar-, vector-, and tensor fields over 3D Euclidean space to represent data, and …

Escape from cells: Deep kd-networks for the recognition of 3d point cloud models

R Klokov, V Lempitsky - Proceedings of the IEEE …, 2017 - openaccess.thecvf.com
We present a new deep learning architecture (called Kd-network) that is designed for 3D
model recognition tasks and works with unstructured point clouds. The new architecture …

Pix3d: Dataset and methods for single-image 3d shape modeling

X Sun, J Wu, X Zhang, Z Zhang… - Proceedings of the …, 2018 - openaccess.thecvf.com
We study 3D shape modeling from a single image and make contributions to it in three
aspects. First, we present Pix3D, a large-scale benchmark of diverse image-shape pairs with …

Learning so (3) equivariant representations with spherical cnns

C Esteves, C Allen-Blanchette… - Proceedings of the …, 2018 - openaccess.thecvf.com
We address the problem of 3D rotation equivariance in convolutional neural networks. 3D
rotations have been a challenging nuisance in 3D classification tasks requiring higher …

Point2sequence: Learning the shape representation of 3d point clouds with an attention-based sequence to sequence network

X Liu, Z Han, YS Liu, M Zwicker - … of the AAAI conference on artificial …, 2019 - ojs.aaai.org
Exploring contextual information in the local region is important for shape understanding
and analysis. Existing studies often employ hand-crafted or explicit ways to encode …

Triplet-center loss for multi-view 3d object retrieval

X He, Y Zhou, Z Zhou, S Bai… - Proceedings of the IEEE …, 2018 - openaccess.thecvf.com
Most existing 3D object recognition algorithms focus on leveraging the strong discriminative
power of deep learning models with softmax loss for the classification of 3D data, while …

Attentional shapecontextnet for point cloud recognition

S Xie, S Liu, Z Chen, Z Tu - Proceedings of the IEEE …, 2018 - openaccess.thecvf.com
We tackle the problem of point cloud recognition. Unlike previous approaches where a point
cloud is either converted into a volume/image or represented independently in a …