PointCNN: Convolution On X-Transformed Points (NeurIPS 2018)

View on GitHub

PointCNN: Convolution On X-Transformed Points

Created by Yangyan Li, Rui Bu, Mingchao Sun, Wei Wu, Xinhan Di, and Baoquan Chen.


PointCNN is a simple and general framework for feature learning from point cloud, which refreshed five benchmark records in point cloud processing (as of Jan. 23, 2018), including:

See our preprint on arXiv (accepted to NeurIPS 2018) for more details.

Pretrained models can be downloaded from here.

Performance on Recent Benchmarks

Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data

PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding

ABC: A Big CAD Model Dataset For Geometric Deep Learning

Practical Applications

3D cities: Deep Learning in three-dimensional space (from Esri)

PointCNN: replacing 50,000 man hours with AI (from Esri)

Point Cloud Segmentation using PointCNN in ArcGIS API for Python (from Esri)

More Implementations

We highly welcome issues, rather than emails, for PointCNN related questions.


Our code is released under MIT License (see LICENSE file for details).

Code Organization

The core X-Conv and PointCNN architecture are defined in pointcnn.py.

The network/training/data augmentation hyper parameters for classification tasks are defined in pointcnn_cls, for segmentation tasks are defined in pointcnn_seg.

Explanation of X-Conv and X-DeConv Parameters

Take the xconv_params and xdconv_params from shapenet_x8_2048_fps.py for example:

xconv_param_name = ('K', 'D', 'P', 'C', 'links')
xconv_params = [dict(zip(xconv_param_name, xconv_param)) for xconv_param in
                [(8, 1, -1, 32 * x, []),
                 (12, 2, 768, 32 * x, []),
                 (16, 2, 384, 64 * x, []),
                 (16, 6, 128, 128 * x, [])]]

xdconv_param_name = ('K', 'D', 'pts_layer_idx', 'qrs_layer_idx')
xdconv_params = [dict(zip(xdconv_param_name, xdconv_param)) for xdconv_param in
                 [(16, 6, 3, 2),
                  (12, 6, 2, 1),
                  (8, 6, 1, 0),
                  (8, 4, 0, 0)]]

Each element in xconv_params is a tuple of (K, D, P, C, links), where K is the neighborhood size, D is the dilation rate, P is the representative point number in the output (-1 means all input points are output representative points), and C is the output channel number. The links are used for adding DenseNet style links, e.g., [-1, -2] will tell the current layer to receive inputs from the previous two layers. Each element specifies the parameters of one X-Conv layer, and they are stacked to create a deep network.

Each element in xdconv_params is a tuple of (K, D, pts_layer_idx, qrs_layer_idx), where K and D have the same meaning as that in xconv_params, pts_layer_idx specifies the output of which X-Conv layer (from the xconv_params) will be the input of this X-DeConv layer, and qrs_layer_idx specifies the output of which X-Conv layer (from the xconv_params) will be forwarded and fused with the output of this X-DeConv layer. The P and C parameters of this X-DeConv layer is also determined by qrs_layer_idx. Similarly, each element specifies the parameters of one X-DeConv layer, and they are stacked to create a deep network.

PointCNN Usage

PointCNN is implemented and tested with Tensorflow 1.6 in python3 scripts. Tensorflow before 1.5 version is not recommended, because of API. It has dependencies on some python packages such as transforms3d, h5py, plyfile, and maybe more if it complains. Install these packages before the use of PointCNN.

If you can only use Tensorflow 1.5 because of OS factor(UBUNTU 14.04),please modify “isnan()” to “std::nan()” in “/usr/local/lib/python3.5/dist-packages/tensorflow/include/tensorflow/core/framework/numeric_types.h” line 49

Here we list the commands for training/evaluating PointCNN on classification and segmentation tasks on multiple datasets.

Please notice that these command just for Area 1 (specified by -a 1 option) validation. Results on other Areas can be computed by iterating -a option.

Please check the free disk space before start, about 900 GB will be required.

  cd data_conversions
  bash download_semantic3d.sh
  bash un7z_semantic3d.sh
  python3 prepare_semantic3d_data.py
  mkdir ../../data/semantic3d/filelists
  python3 prepare_semantic3d_filelists.py
  cd ../pointcnn_seg
  ./train_val_semantic3d.sh -g 0 -x semantic3d_x4_2048_fps
  ./test_semantic3d.sh -g 0 -x semantic3d_x4_2048_fps -l <path to ckpt>
  cd ../evaluation
  python3 semantic3d_merge.py -d <path to *_pred.h5> -v <reduced or full>