This repo contains code to train a volumetric deep neural network to complete partially scanned 3D shapes. More information can be found in our paper.
Train/test data is available for download on our project website.
Training tasks use Torch7, with torch packages cudnn
, cunn
, torch-hdf5
, xlua
.
The shape synthesis code was developed under VS2013, and uses flann
(included in external).
th train_class.lua -model epn-unet-class -save logs-epn-unet-class -train_data data/h5_shapenet_dim32_sdf/train_shape_voxel_data_list.txt -test_data data/h5_shapenet_dim32_sdf/test_shape_voxel_data_list.txt -gpu_index 0
- Trained models: trained_models.zip (700mb)
@inproceedings{dai2017complete,
title={Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis},
author={Dai, Angela and Qi, Charles Ruizhongtai and Nie{\ss}ner, Matthias},
booktitle = {Proc. Computer Vision and Pattern Recognition (CVPR), IEEE},
year = {2017}
}
If you have any questions, please email Angela Dai at [email protected].