https://github.com/charlesq34/pointnet-autoencoder

Autoencoder for Point Clouds
https://github.com/charlesq34/pointnet-autoencoder

autoencoder deep-learning point-cloud pointnet

Last synced: 13 days ago
JSON representation

Autoencoder for Point Clouds

• Host: GitHub
• URL: https://github.com/charlesq34/pointnet-autoencoder
• Owner: charlesq34
• License: other
• Created: 2018-05-14T23:02:04.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2023-10-08T13:42:28.000Z (about 1 year ago)
• Last Synced: 2024-08-01T03:45:50.331Z (3 months ago)
• Topics: autoencoder, deep-learning, point-cloud, pointnet
• Language: Python
• Size: 472 KB
• Stars: 409
• Watchers: 11
• Forks: 85
• Open Issues: 16
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# pointnet-autoencoder

![prediction example](https://github.com/charlesq34/pointnet-autoencoder/blob/master/doc/teaser.jpg)

Here we present code to build an autoencoder for point clouds, with PointNet encoder and various kinds of decoders. We train and test our autoencoder on the ShapeNetPart dataset. This is a side project I played with recently -- you are welcomed to modify it for your own projects or research. Let me know if you discover something interesting!

## LICENSE

This repository is under the MIT license. See the LICENSE file for detail.

## Installation

We need TensorFlow (version>=1.4).

For point cloud reconstruction loss function, we need to compile two custum TF operators under `tf_ops/nn_distance` (Chamfer's distance) and `tf_ops/approxmatch` (earth mover's distance). Check the `tf_compile_*.sh` script under these two folders, modify the TensorFlow and CUDA path accordingly before you run the shell script to compile the operators. Check this PAPER for an introduction for these two point cloud losses.

For a visualization helper, go to `utils/` and run `sh compile_render_balls_so.sh` -- run `python show3d_balls.py` to test if you have successfully compiled it.

## Download Data

ShapeNetPart dataset is available HERE (635MB). Simply download the zip file and move the `shapenetcore_partanno_segmentation_benchmark_v0` folder to `data`.

To visualize the dataset, run (type `q` to go to the next shape, see `show3d_balls.py` for more detailed hot keys):

    python part_dataset.py

## Train an Autoencoder

To train the most basic autoencoder (fully connected layer decoder with Chamfer's distance loss) on chair models with aligned poses, simply run the following command:

    python train.py --model model --log_dir log_chair_norotation --num_point 2048 --category Chair --no_rotation

You can check more options for training by:

    python train.py -h

## Visualize Reconstruction on Test Set

To test and visualize results of the trained autoencoder above, simply run:

    python test.py --model model --model_path log_chair_norotation/model.ckpt --category Chair

You can check more options for testing by:

    

    python test.py -h