PyTorch Code of our WACV2020 paper: Silhouette Guided Point Cloud Reconstruction beyond Occlusion
PyTorch implementation of our WACV 2020 paper: "Silhouette Guided Point Cloud Reconstruction beyond Occlusion"
Our short introduction video
Network architecture:
Point cloud reconstruction
python train.py
python test.py
This will save network predictions for the downstream FSSR post-refinement step.
Silhouette completion First train on DYCE dataset:
python train_sc.py
Then finetune on Pix3D dataset, using 5-fold cross validation ( you will need to run it 5 times by changing the fold number in L32-35 ):
python train_sc_ft.py
python test_sc_pix3d.py
Silhouette guidede point cloud reconstruction
python train_occ.py
python test_rec_pix3d.py
Then perform FSSR post-refinement step as describe below
cd matlab
./matlab
FssrPostRefine
cd ..
python fssr_batch_process.py
cd matlab
preComputeFssrParam
cd ..
This produces the refined point clouds for evaluation.cd pcn
python metrics_pix3d.py
cd ..
cd pix3d/eval/
python eval_pix3d.py
cd ../../
cd pcn
python eval_shapenet.py
cd ..
cd pcn
python metrics_shapenet.py
cd ../pix3d/eval/
python eval_shapenet_object_centered.py
cd ../../
python test_sc_DYCE.py
Please cite our paper for any purpose of usage.
@inproceedings{zou2020silhouette,
title={Silhouette Guided Point Cloud Reconstruction beyond Occlusion},
author={Zou, Chuhang and Hoiem, Derek},
booktitle={The IEEE Winter Conference on Applications of Computer Vision},
pages={41--50},
year={2020}
}