Skip to content

Latest commit

 

History

History
63 lines (44 loc) · 3.43 KB

README.md

File metadata and controls

63 lines (44 loc) · 3.43 KB

Open In Colab

PointNet

PyTorch implementation of "PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation" https://arxiv.org/abs/1612.00593

pointnet

Key points of the implementation are explained in details in this Medium article.

Classification dataset

This code implements object classification on ModelNet10 dataset.

As in the original paper, we sample 1024 points on objects surfaces depending on the area of the current face. Then we normalize the object to a unit sphere and add Gaussian noise. This is an example of input to the neural network that represents a chair:

matching points

You can download the dataset by following this link

Classification performance

Class (Accuracy) Overall Bathtub Bed Chair Desk Dresser Monitor Night stand Sofa Table Toilet
ModelNet10 82.0% 93.4% 92.0% 97.2% 81.5% 71.0% 89.4% 56.0% 86.9% 93.4% 95.9%

Pretrained model is available here

Usage

  • The first and the best option is to run the notebook with comments and visualizations /nbs/PointNetClass.ipynb in Google Colab.

  • The second option is to clone the repository on a local machine and run a model with default parameters:

    git clone https://github.com/nikitakaraevv/pointnet
    wget http://3dvision.princeton.edu/projects/2014/3DShapeNets/ModelNet10.zip
    unzip -q ModelNet10.zip
    cd pointnet/
    python train.py 

    If for some reason it doesn't work, you can install the requirements before running python train.py:

    conda create -n env python=3.7
    conda activate env
    pip install -r requirements.txt

    Another example of running a model is:

    python train.py --root_dir ../ModelNet10/ --batch_size 16 --lr 0.0001 --epochs 30 --save_model_path ./ckpts

Part segmentation dataset

The dataset includes 2609 point clouds representing different airplanes, where every point has its coordinates in 3D space and a label of an airplane’s part the point belongs to. As all images have different number of points and PyTorch library functions require images of the same size to form a PyTorch tensor, we sample uniformly 2000 points from every point cloud.

You can download the dataset by following this link

Part segmentation performance

The resulting accuracy on the validation dataset is 88%. In the original paper part segmentation results corresponding to category of objects (airplanes) is 83.4%.

Usage

This part of the project is still in development. However, you already can run the notebook /nbs/PointNetSeg.ipynb in Colab.

matching points

Authors