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
Benchmarks
These leaderboards are used to track progress in 3D Object Classification
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
Datasets
ModelNet
3RScan
Cyclone Data
UR5 Tool Dataset
Most implemented papers
Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds
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
•
•
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
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
•
•
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
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
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
•
•
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
•
•
We present O-CNN, an Octree-based Convolutional Neural Network (CNN) for 3D shape analysis.
