3D Object Classification

32 papers with code • 3 benchmarks • 5 datasets

3D Object Classification is the task of predicting the class of a 3D object point cloud. It is a voxel level prediction where each voxel is classified into a category. The popular benchmark for this task is the ModelNet dataset. The models for this task are usually evaluated with the Classification Accuracy metric.

Image: Sedaghat et al

Most implemented papers

Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds

hlei-ziyan/SPH3D-GCN 20 Sep 2019

We propose a spherical kernel for efficient graph convolution of 3D point clouds.

3D Point Capsule Networks

yongheng1991/3D-point-capsule-networks CVPR 2019

In this paper, we propose 3D point-capsule networks, an auto-encoder designed to process sparse 3D point clouds while preserving spatial arrangements of the input data.

Point Transformer

engelnico/point-transformer 2 Nov 2020

In this work, we present Point Transformer, a deep neural network that operates directly on unordered and unstructured point sets.

SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences

ShunChengWu/SceneGraphFusion CVPR 2021

Scene graphs are a compact and explicit representation successfully used in a variety of 2D scene understanding tasks.

PointMixer: MLP-Mixer for Point Cloud Understanding

lifebeyondexpectations/eccv22-pointmixer 22 Nov 2021

MLP-Mixer has newly appeared as a new challenger against the realm of CNNs and transformer.

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

kanezaki/rotationnet CVPR 2018

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.

OctNet: Learning Deep 3D Representations at High Resolutions

griegler/octnet CVPR 2017

We present OctNet, a representation for deep learning with sparse 3D data.

ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes

suryanshkumar/online-joint-depthfusion-and-semantic CVPR 2017

A key requirement for leveraging supervised deep learning methods is the availability of large, labeled datasets.

Learning a Hierarchical Latent-Variable Model of 3D Shapes

lorenmt/vsl 17 May 2017

We propose the Variational Shape Learner (VSL), a generative model that learns the underlying structure of voxelized 3D shapes in an unsupervised fashion.

O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis

Microsoft/O-CNN 5 Dec 2017

We present O-CNN, an Octree-based Convolutional Neural Network (CNN) for 3D shape analysis.