Chenhao Zhang 8fd0feb50b | 2 weeks ago | |
---|---|---|
.idea | 3 months ago | |
.ipynb_checkpoints | 2 months ago | |
GPCC | 1 month ago | |
PCGCv2 | 1 month ago | |
__pycache__ | 1 month ago | |
dataset/basketball | 2 months ago | |
ddpcc_ckpts | 2 weeks ago | |
log/DDPCC_geo/I10 | 2 months ago | |
models | 2 weeks ago | |
pcgcv2_ckpts | 3 months ago | |
results | 2 weeks ago | |
results_csv | 2 months ago | |
runs | 1 month ago | |
tmp | 2 weeks ago | |
README.md | 2 months ago | |
__init__.py | 3 months ago | |
aaa.txt | 2 weeks ago | |
dataset_lossy.py | 2 months ago | |
dataset_owlii.py | 1 month ago | |
lossless_coder.pth | 3 months ago | |
requirements.txt | 3 months ago | |
test_owlii.py | 2 months ago | |
test_time.py | 2 weeks ago | |
trainer.py | 2 weeks ago | |
trainer_lossless.py | 3 months ago |
This is the code of D-DPCC: Deep Dynamic Point Cloud Compression via 3D Motion Prediction.
Link of the paper: https://www.ijcai.org/proceedings/2022/0126.pdf
If you want to cite our work, please use the following reference:
@inproceedings{ijcai2022p126,
title = {D-DPCC: Deep Dynamic Point Cloud Compression via 3D Motion Prediction},
author = {Fan, Tingyu and Gao, Linyao and Xu, Yiling and Li, Zhu and Wang, Dong},
booktitle = {Proceedings of the Thirty-First International Joint Conference on
Artificial Intelligence, {IJCAI-22}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
editor = {Lud De Raedt},
pages = {898--904},
year = {2022},
month = {7},
note = {Main Track},
doi = {10.24963/ijcai.2022/126},
url = {https://doi.org/10.24963/ijcai.2022/126},
}
(Also shown in requirements.txt
)
cuda~=11.5.50
numpy~=1.21.2
open3d~=0.14.1
pandas~=1.2.3
torch~=1.10.0
MinkowskiEngine~=0.5.4
pytorch3d~=0.6.1
tqdm~=4.62.3
tensorboardX~=2.5
matplotlib~=3.5.1
h5py~=3.6.0
torchac~=0.9.3
setuptools~=58.0.4
scipy~=1.7.3
scikit-learn~=1.0.2
python trainer.py --batch_size=4 --gpu=0 --lamb=10 --exp_name=I10 --dataset_dir='/tmp/dataset/8iVFB'
python trainer_lossless.py --dataset_dir='/home/zhaoxudong/dataset_npy'
In fact, the pretrained model is lossless_coder.pth
. You probably needn't to retrain this model.
Estimate the bitrate with factorized entropy model, without practical and separate encoding and decoding process:
# python test_owlii.py --log_name='aaa' --gpu=1 --frame_count=32 --results_dir='results' --tmp_dir='tmp' --dataset_dir='/home/zhaoxudong/Owlii_10bit'
python test_owlii.py --log_name='aaa' --gpu=0 --frame_count=32 --results_dir='results' --tmp_dir='tmp' --dataset_dir='/tmp/dataset/8iVFB'
With separate encoding and decoding process, which generates real bitstream,
and calculate encoding and decoding time.
python test_time.py --log_name='aaa' --gpu=0 --frame_count=32 --results_dir='results' --tmp_dir='tmp' --dataset_dir='/tmp/dataset/8iVFB'
./GPCC/tmc3: Permission denied
:chmod 777 ./GPCC/tmc3
./GPCC/pc_error: Permission denied
:chmod 777 ./GPCC/pc_error
PCGCv2
need to be copied and in both the parent and current directory.Shown in the folder results_csv
.
See details in the MPEG proposal: M60267 “[AI-3DGC] D-DPCC Test Results on 10 bit Owlii”, 2022/7.
No Description
Python Text CSV Markdown 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》