Browse > Computer Vision > 3D > 3D Object Classification

3D Object Classification Edit

7 papers with code · Computer Vision

Trend Dataset Best Method Paper title Paper Code Compare

Spherical Fractal Convolutional Neural Networks for Point Cloud Recognition

We present a generic, flexible and 3D rotation invariant framework based on spherical symmetry for point cloud recognition.

ClusterNet: Deep Hierarchical Cluster Network With Rigorously Rotation-Invariant Representation for Point Cloud Analysis

Current neural networks for 3D object recognition are vulnerable to 3D rotation.

Octree Guided CNN With Spherical Kernels for 3D Point Clouds

We propose an octree guided neural network architecture and spherical convolutional kernel for machine learning from arbitrary 3D point clouds.

Octree guided CNN with Spherical Kernels for 3D Point Clouds

We propose an octree guided neural network architecture and spherical convolutional kernel for machine learning from arbitrary 3D point clouds.

3DTI-Net: Learn Inner Transform Invariant 3D Geometry Features using Dynamic GCN

15 Dec 2018

Deep learning on point clouds has made a lot of progress recently.

A Graph-CNN for 3D Point Cloud Classification

28 Nov 2018

Graph convolutional neural networks (Graph-CNNs) extend traditional CNNs to handle data that is supported on a graph.

SPNet: Deep 3D Object Classification and Retrieval using Stereographic Projection

5 Nov 2018

We propose an efficient Stereographic Projection Neural Network (SPNet) for learning representations of 3D objects.

RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews From Unsupervised Viewpoints

We propose a Convolutional Neural Network (CNN)-based model RotationNet,'' which takes multi-view images of an object as input and jointly estimates its pose and object category.

Spherical Convolutional Neural Network for 3D Point Clouds

21 May 2018

We propose a neural network for 3D point cloud processing that exploits `spherical' convolution kernels and octree partitioning of space.

Deep 2.5D Vehicle Classification with Sparse SfM Depth Prior for Automated Toll Systems

9 May 2018

Furthermore due to the design of the network, at test time only the 2D camera images are required for classification which enables the usage in portable computer vision systems.