Pointnet2.ScanNet

PointNet++ Semantic Segmentation on ScanNet in PyTorch with CUDA acceleration based on the original PointNet++ repo and the PyTorch implementation with CUDA

Performance

The semantic segmentation results in percentage on the ScanNet train/val split in data/.

Avg	Floor	Wall	Cabinet	Bed	Chair	Sofa	Table	Door	Window	Bookshelf	Picture	Counter	Desk	Curtain	Refrigerator	Bathtub	Shower	Toilet	Sink	Others
50.62	90.96	63.87	35.21	56.75	62.43	68.46	47.15	36.12	34.12	25.62	23.58	41.46	42.73	32.38	44.12	64.93	63.90	74.04	58.13	46.40

The pretrained models: SSG MSG

Installation

Requirements

Linux (tested on Ubuntu 14.04/16.04)
Python 3.6+
PyTorch 1.0
TensorBoardX

Install

Install this library by running the following command:

cd pointnet2
python setup.py install

Configure

Change the path configurations for the ScanNet data in lib/config.py

Usage

preprocess ScanNet scenes

Parse the ScanNet data into *.npy files and save them in preprocessing/scannet_scenes/

python preprocessing/collect_scannet_scenes.py

sanity check

Don't forget to visualize the preprocessed scenes to check the consistency

python preprocessing/visualize_prep_scene.py --scene_id <scene_id>

The visualized <scene_id>.ply is stored in preprocessing/label_point_clouds/

train

Train the PointNet++ semantic segmentation model on ScanNet scenes

python train.py --batch_size 32 --epoch 500 --lr 1e-3 --verbose 10 --weighting

The trained models and logs will be saved in outputs/<time_stamp>/

Note: please refer to train.py for more training settings

eval

Evaluate the trained models and report the segmentation performance in point accuracy, voxel accuracy and calibrated voxel accuracy

python eval.py --batch_size 32 --folder <time_stamp>

vis

Visualize the semantic segmentation results on points in a given scene

python visualize.py --batch_size 32 --folder <time_stamp> --scene_id <scene_id>

The generated <scene_id>.ply is stored in outputs/<time_stamp>/preds. See the class palette here

Acknowledgement

charlesq34/pointnet2: Paper author and official code repo.
sshaoshuai/Pointnet2.PyTorch: Initial work of PyTorch implementation of PointNet++ with CUDA acceleration.

triple-tam / pointnet2.scannet Goto Github PK