Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
zhangych02 86db543910 | 1 year ago | |
---|---|---|
ClsNetwork | 1 year ago | |
Clsutils | 1 year ago | |
PretrainModel | 1 year ago | |
arch | 1 year ago | |
auction_match | 1 year ago | |
chamfer_distance | 1 year ago | |
data | 1 year ago | |
loss | 1 year ago | |
option | 1 year ago | |
pointnet2 | 1 year ago | |
savedModel | 1 year ago | |
test | 1 year ago | |
train | 1 year ago | |
utils | 1 year ago | |
README.md | 1 year ago | |
SPU.pdf | 1 year ago | |
logo.png | 1 year ago |
This is the code project of Semantic Point Cloud Upsampling (SPU) published on IEEE Transactions on Multimedia.
Python 3.6
PyTorch 1.2.0
Torchvision 0.4.0
KNN_CUDA 0.2.0
You can get the trained upsampling model in the dir of ./savedModel.
The pre-trained classification networks are at ./PretrainModel.
You can switch DGCNN or PointNet as classification network.
cd ./train
python trainSPUDGCNN8x.py
python trainSPUPointNet8x.py
In this commond, you can revise upsampling factor to achieve paper results.
cd ./test
python TestSPU2.py
scale | CD | HD | Top1 acc | Cls ave | F-Euc |
---|---|---|---|---|---|
4X | 0.002771 | 0.021539 | 0.883712 | 0.842134 | 3.395767 |
8X | 0.003900 | 0.038486 | 0.845219 | 0.803791 | 5.123443 |
scale | CD | HD | Top1 acc | Cls ave | F-Euc |
---|---|---|---|---|---|
4X | 0.002689 | 0.023840 | 0.868314 | 0.832221 | 12.505258 |
8X | 0.003910 | 0.042285 | 0.761345 | 0.725174 | 14.432164 |
Zhuangzi Li, Ge Li, Thomas Li, Shan Liu, Wei Gao, “Semantic Point Cloud Upsampling,” IEEE Transactions on Multimedia (TMM), accepted in March 2022.
name: Zhang Yongchi
email: zhangych02@pcl.ac.cn
No Description
Python Cuda Text C++ other
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》