PointNet.pytorch and FoldingNet decoder, add quantization, change latent code size from 512 to 1024
This repo is implementation for PointNet(https://arxiv.org/abs/1612.00593) in pytorch. The model is in pointnet.py.
Download data and running
bash build.sh #build C++ code for visualization
bash download.sh #download dataset
python train_classification.py #train 3D model classification
python python train_segmentation.py # train 3D model segmentaion
python show_seg.py --model seg/seg_model_20.pth # show segmentation results
Performance
Without heavy tuning, PointNet can achieve 80-90% performance in classification and segmentaion on this dataset.
Sample segmentation result:
