Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Chunyang Fu 37ffd05b57 | 2 years ago | |
---|---|---|
OctreeCPP | 2 years ago | |
Preparedata | 2 years ago | |
file | 2 years ago | |
modelsave/obj | 2 years ago | |
numpyAc | 2 years ago | |
.gitignore | 2 years ago | |
Octree.py | 2 years ago | |
README.md | 2 years ago | |
attentionModel.py | 2 years ago | |
dataPrepare.py | 2 years ago | |
dataset.py | 2 years ago | |
decoder.py | 2 years ago | |
encoder.py | 2 years ago | |
encoderTool.py | 2 years ago | |
networkTool.py | 2 years ago | |
octAttention.py | 2 years ago | |
pt.py | 2 years ago | |
testTMC.py | 2 years ago |
There are two branches named obj
and lidar
that implement Object and LiDAR point cloud coding respectively. They share the same network. Paper.
file/environment.sh
to help you build this environmentSemanticKITTI (80G)
23201/20351 frames in 00-10/11-21 folders for training/testing.
MPEG 8iVFBv2 (5.5GB)
300/300 frames in soldier10 and longdress10 for training
300/300 frames in loot10 and redandblack10 for testing
MPEG 8iVFB (100M)
1/1/1/1 frame in Boxer9/10 and Thaidancer9/10 (quantized from 12bit data) for testing
JPEG MVUB (8GB)
318/216/207 frames in andrew10, david10 and sarah10 for training
245/245/216/216 frames in Phil9/10 and Ricardo9/10 for testing
(Note: We rotated the MVUB data to make it consistent with MPEG 8i. Please set rotation=True
in the dataPrepare
function when processing MVUB data in training and testing.)
Please set oriDir
in dataPrepare.py
before.
python dataPrepare.py
To prepare train and test data. It will generate *.mat
data in the directory Data
.
python octAttention.py
You should set the Network parameters expName,DataRoot
etc. in networkTool.py
.
This will output checkpoint in expName
folder, e.g. Exp/Kitti
. (Note: You should run DataFolder.calcdataLenPerFile()
in dataset.py
for a new dataset, and you can comment it after you get the parameter dataLenPerFile
)
You may need to run the following command to provide pc_error
and tmc13v14
execute permission.
chmod +x file/pc_error file/tmc13v14
python encoder.py
This will output binary codes saved in .bin
format in Exp(expName)/data
, and will generate *.mat
data in the directory Data/testPly
.
python decoder.py
This will load *.mat
data for check and calculate PSNR by pc_error
.
We provide the test code for TMC13 v14 (G-PCC) for Object and LiDAR point cloud compression.
python testTMC.py
If this work is useful for your research, please consider citing :
@inproceedings{OctAttention,
title={OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compression},
author={Fu, Chunyang and Li, Ge and Song, Rui and Gao, Wei and Liu, Shan},
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)},
year={2022}
}
No Description
Python C++ HAProxy Shell
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》