Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
yehua b30d877b6a | 1 year ago | |
---|---|---|
MSVoxelDNN-master | 1 year ago | |
LICENSE | 1 year ago | |
MSVoxelDNN explanation.docx | 1 year ago | |
MSVoxelDNN performance.xlsx | 1 year ago | |
Multiscale deep context modeling for lossless point cloud geometry compression-MSVoxelDNN.pdf | 1 year ago | |
OpenPointCloud-logo.png | 1 year ago | |
README - old-2.md | 1 year ago | |
README - old.md | 1 year ago | |
README.md | 1 year ago | |
ablation_test.xlsx | 1 year ago | |
ablation_test1.png | 1 year ago | |
requirements.txt | 1 year ago | |
result.xlsx | 1 year ago |
Point Cloud Compression, context model, Deep Generative Models, G-PCC, base on VoxelDNN
MSVoxelDNN, is a kind of point cloud lossless compression method, optimized on the basis of VoxelDNN.
1.transplant from pytorch to tensorlayer
2.model is not provided by author, so we train MSVoxelDNN's 24 model and VoxelDNN's 2 models
3.test with testsets, on pytorch and tensorlayer
4.benchmark and ablation test on downsample depth of 3 and 1
root
└── MSVoxelDNN-master: tensorlayer code
└── MSVoxelDNN pytorch source code
└── MSVoxelDNN-master/Model: model files on pytorch and tensorlayer
└── MSVoxelDNN explanation.docx: introduction for paper, migration, performance, instructions
└── Multiscale deep context modeling for lossless point cloud geometry compression.pdf: origional paper
└── datasets: follow the instructions to prepare datasets
└── MSVoxelDNN performance.xlsx: detailed performance list
Tensorlayer:
VoxelDNN training:
python -m training.voxel_dnn_training_tensorlayer -inputmodel /userhome/MSVoxelDNN/MSVoxelDNN-master/Model/voxeldnn32_tl_test/model_1.npz -dataset /userhome/VoxelDNN/datasets/8iVFBv2/10bitdepth_2_oct4/ -dataset /userhome/VoxelDNN/datasets/CAT1/10bitdepth_2_oct4/ -dataset /userhome/VoxelDNN/datasets/MVUB/10bitdepth_2_oct4/ -dataset /userhome/VoxelDNN/datasets/ModelNet40_200_pc512_oct3/
encode:
python3 -m ms_voxel_dnn_coder.ms_voxel_dnn_encoder_tensorlayer -ply /userhome/PCGCv1/pytorch_eval/28_airplane_0270.ply
As the paper shows in table II, the bpov of VoxelDNN is smaller than that of MSVoxelDNN, so in order to improve the performance, we should reduce the downsample depth to 1, and rely more on VoxelDNN coding. We make an ablation test on pytorch version to compare the encoding time and bpov between downsample depth 1 and 3.
The results shows below. We can see from the results that compared with depth=3, depth=1 achieves less encoding time (avg: 2568.8s VS 6777.1s) and smaller bpov (avg: 3.039 VS 4.037)!
Encodedfile | TL_EncTime | TL_bpov | PT_EncTime | PT_bpov |
---|---|---|---|---|
sarah_vox10_0023.ply | 625.301 | 0.871 | 646.468 | 0.871 |
sarah_vox9_0023.ply | 156.309 | 0.854 | 173.102 | 0.855 |
phil_vox9_0139.ply | 176.158 | 0.923 | 161.953 | 0.923 |
phil_vox10_0139.ply | 728.739 | 0.935 | 710.697 | 0.935 |
redandblack_vox10_1550.ply | 411.62 | 0.784 | 369.163 | 0.786 |
queen_vox10_0200.ply | 460.982 | 0.714 | 359.852 | 0.713 |
longdress_vox10_1300.ply | 466.588 | 0.701 | 382.268 | 0.703 |
basketball_player_vox11_00000200.ply | 1676.731 | 0.607 | 1385.684 | 0.609 |
loot_vox10_1200.ply | 456.226 | 0.674 | 389.951 | 0.676 |
dancer_vox11_00000001.ply | 1479.507 | 0.605 | 1188.119 | 0.607 |
soldier_vox10_0690.ply | 589.835 | 0.703 | 472.866 | 0.704 |
@article{nguyen2021multiscale,
title={Multiscale deep context modeling for lossless point cloud geometry compression},
author={Nguyen, Dat Thanh and Quach, Maurice and Valenzise, Giuseppe and Duhamel, Pierre},
journal={arXiv preprint arXiv:2104.09859},
year={2021}
}
name: Ye Hua
email: yeh@pcl.ac.cn
Point Cloud Compression, context model, Deep Generative Models, G-PCC, base on VoxelDNN
Text Python Markdown
MIT
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》