3D Object Classification
43 papers with code • 3 benchmarks • 6 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
Latest papers
Regularization Strategy for Point Cloud via Rigidly Mixed Sample
dogyoonlee/RSMix-official
•
•
CVPR 2021
Data augmentation is an effective regularization strategy to alleviate the overfitting, which is an inherent drawback of the deep neural networks.
Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud
mutianxu/GDANet
•
•
GDANet introduces Geometry-Disentangle Module to dynamically disentangle point clouds into the contour and flat part of 3D objects, respectively denoted by sharp and gentle variation components.
A Fast Hybrid Cascade Network for Voxel-based 3D Object Classification
CorleoneJW/3D-Retrieval-System
•
•
Voxel-based 3D object classification has been thoroughly studied in recent years.
Point Transformer
qq456cvb/Point-Transformers
•
•
In this work, we present Point Transformer, a deep neural network that operates directly on unordered and unstructured point sets.
Cascaded Refinement Network for Point Cloud Completion with Self-supervision
xiaogangw/cascaded-point-completion
•
•
This is to mitigate the dependence of existing approaches on large amounts of ground truth training data that are often difficult to obtain in real-world applications.
Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds
raoyongming/PointGLR
•
•
CVPR 2020
Based on this hypothesis, we propose to learn point cloud representation by bidirectional reasoning between the local structures at different abstraction hierarchies and the global shape without human supervision.
FPConv: Learning Local Flattening for Point Convolution
We introduce FPConv, a novel surface-style convolution operator designed for 3D point cloud analysis.
InSphereNet: a Concise Representation and Classification Method for 3D Object
Unlike previous methods that use points, voxels, or multi-view images as inputs of deep neural network (DNN), the proposed method constructs a class of more representative features named infilling spheres from signed distance field (SDF).
Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds
We propose a spherical kernel for efficient graph convolution of 3D point clouds.
Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data
hkust-vgd/scanobjectnn
•
•
ICCV 2019
From our comprehensive benchmark, we show that our dataset poses great challenges to existing point cloud classification techniques as objects from real-world scans are often cluttered with background and/or are partial due to occlusions.
