3D Point Cloud Classification
126 papers with code • 5 benchmarks • 6 datasets
Image: Qi et al
Benchmarks
These leaderboards are used to track progress in 3D Point Cloud Classification
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find 3D Point Cloud Classification models and implementations
ModelNet
ScanObjectNN
ModelNet40-C
IntrA
Sydney Urban Objects
Teeth3DS
Subtasks
Most implemented papers
DeepGCNs: Making GCNs Go as Deep as CNNs
This work transfers concepts such as residual/dense connections and dilated convolutions from CNNs to GCNs in order to successfully train very deep GCNs.
3D Point Cloud Classification and Segmentation using 3D Modified Fisher Vector Representation for Convolutional Neural Networks
The point cloud is gaining prominence as a method for representing 3D shapes, but its irregular format poses a challenge for deep learning methods.
SO-Net: Self-Organizing Network for Point Cloud Analysis
This paper presents SO-Net, a permutation invariant architecture for deep learning with orderless point clouds.
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.
Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline
It also outperforms state-of-the-art methods on ScanObjectNN, a real-world point cloud benchmark, and demonstrates better cross-dataset generalization.
Masked Autoencoders for Point Cloud Self-supervised Learning
Then, a standard Transformer based autoencoder, with an asymmetric design and a shifting mask tokens operation, learns high-level latent features from unmasked point patches, aiming to reconstruct the masked point patches.
Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training
By fine-tuning on downstream tasks, Point-M2AE achieves 86. 43% accuracy on ScanObjectNN, +3. 36% to the second-best, and largely benefits the few-shot classification, part segmentation and 3D object detection with the hierarchical pre-training scheme.
PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies
In this work, we revisit the classical PointNet++ through a systematic study of model training and scaling strategies, and offer two major contributions.
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?
runpeidong/act
•
•
The success of deep learning heavily relies on large-scale data with comprehensive labels, which is more expensive and time-consuming to fetch in 3D compared to 2D images or natural languages.
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining
qizekun/ReCon
•
•
This motivates us to learn 3D representations by sharing the merits of both paradigms, which is non-trivial due to the pattern difference between the two paradigms.
