Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Zhangrn 03b4ed9e7b | 2 years ago | |
---|---|---|
data | 2 years ago | |
log | 2 years ago | |
models | 2 years ago | |
scripts | 2 years ago | |
utils | 2 years ago | |
README.md | 2 years ago | |
classify.py | 2 years ago | |
drop_modelNet.py | 2 years ago | |
drop_shapeNet.py | 2 years ago | |
provider.py | 2 years ago |
onion peeling mask for point cloud completion
W. Yan, R. Zhang et al., “Vaccine-style-net: Point cloud completion in implicit continuous function space,” ACM International Conference on Multimedia, pp. 2067–2075, 2020
OPM (Onion-peeling-Mask) Generation Part:
The code is based on Saliency map by PointCLoud Saliency Map(https://github.com/tianzheng4/PointCloud-Saliency-Maps) of DGCNN model
Please refer these code to install the dependencies.
We test on cuda 9.0, tensorflow 1.12, and python 3.6.
if test on meshes, you should add trimesh lib.
pip install trimesh
./log/: pretrained model of DGCNN for evaluation recognition score of point clouds.
./data/: datasets and output masks
./data/modelnet40: modelNet40 datasets
./data/shapenetAll: Shapenet core datasets and files for classification
./data/modelnet40_ply_hdf5_2048/ :Point clouds of ModelNet40 models in HDF5 files will be automatically downloaded(MB) to the data folder.
./data/random4: random seed sampling masks of four-classes datasets of Shapenet
./data/random4/mask_ratio_0_4: random seed sampling masks of four-classes datasets of Shapenet in case of 40% drop ratio
./data/random4/mask_ratio_0_4\input: refers to the generated mask here. others files in this path refers to the generated point cloud of different methods.
./data/salient4: OPM masks of four-classes datasets of Shapenet
./data/salient4/saliency_mask_820: OPM masks of four-classes datasets of Shapenet in case of 40% drop ratio
./dump/: wrongly classified will be saved here.
Each point contains 2048 points uniformaly sampled from a shape surface.
Each cloud is zeor-mean and normalized into an unit spheer.
If you'd like to prepare your own data, you can refer to some helper functions in
./utils/data_prep_util.py for saving and loading HDF5 files.
ShapeNet core datasets can be download from:https://shapenet.org/
cd ./scripts/
bash drop_modelNet.sh
cd ./scripts/
bash drop_shapeNet.sh
cd ./scripts/
bash classify.sh
onion peeling mask for point cloud completion
Text Unity3D Asset Python
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》