Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
yehua 76eb4b1a3e | 1 year ago | |
---|---|---|
VoxelDNN_v2_tensorlayer | 2 years ago | |
LICENSE | 1 year ago | |
Lossless Coding of Point Cloud Geometry using a Deep Generative Model.pdf | 2 years ago | |
OpenPointCloud-logo.png | 1 year ago | |
README.md | 1 year ago | |
Voxeldnn explanation.docx | 2 years ago | |
ablation.png | 2 years ago | |
flowchart.vsdx | 2 years ago | |
requirements.txt | 2 years ago | |
result.csv | 2 years ago | |
test_result.xlsx | 2 years ago |
Voxeldnn, point cloud compression in deeplearning, migrated to tensorlayer
Voxeldnn, is a kind of PC lossless compression method. The source code uses TensorFlow as deeplearning framework, here we transplant to TensorLayer.
1.transplant from TensorFlow to tensorlayer
2.benchmark tests on many PCs, including those not tested by author.
3.ablation tests on downsample depth of 3 and 1, as well as restricted box size of 64 and 32.
4.performance comparasion between TensorLayer and TensorFlow.
root
└── TensorFlow open source code
└── VoxelDNN_v2_tensorlayer/: Tensorlayer source code
└── Voxeldnn explanation.docx: introduction for paper, migration, performance, instructions
└── Lossless Coding of Point Cloud Geometry using a Deep Generative Model.pdf: paper
└── flowchart.vsdx: flow chart about encoding process
└── trainingset: follow the instructions to prepare datasets
Tensorlayer:
cd VoxelDNN_v2_tensorlayer
Training:
python -m training.voxel_dnn_training_tensorlayer-2 -inputmodel Model/voxeldnn64_tl/model_27.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/ -outputmodel Model/voxeldnn64_tl_2/
Encode:
python -m voxel_dnn_coder.voxel_dnn_abac_multi_res_sepa_model-tensorlayer_MP -ply 28_airplane_0270.ply -output Output_tl/ -model64 Model/voxeldnn64_tl/model_48.npz -signaling baseline
Decode:
python -m voxel_dnn_coder.voxel_dnn_abac_multi_res_sepa_model_dec-tensorlayer_MP -level 10 -ply 28_airplane_0270.ply -depth 3 -output Output_tl/ -model64 Model/voxeldnn64_tl/model_48.npz -signaling baseline
For more instructions, please refer to VoxelDNN_v2-main/readme.md
As the paper says, VoxelDNN costs too much time in coding. And we think the reason is that for one thing, voxel-based methods would inevitably take more time than other method, as they encodes voxel by voxel. And for another, VoxelDNN needs to traverse all encoding paths to search the best one with lowest bpp, and the traversing also takes much time. Here we make an ablation test to speed up the compression.
Test 1: we restrict the downsample depth to 1 instead of 3, which means the final encoded box size will either be 64 or 32.
Test 2: we set the final encoded box size to be 64.
Test 3: we set the final encoded box size to be 32.
And the results show as below. We can see that compared to the origional result of VoxelDNN_depth3, test 1 gets a little smaller bpov(for less flags) and less time(-7% for most files). Test 2 gets bigger bpov and much less time(-20% for most files). Test 3 gets a little bigger bpov(3%) and the least time(-60%). So test 3 can be seen as the optimized version of VoxelDNN.
We tested on files of different bitwidth on testsets. The results are listed below. Compared with TensorFlow, the bpov of TensorLayer is slighterly better.
Encodedfile | TL_bpov | TF_bpov |
---|---|---|
sarah_vox10_0023.ply | 0.833 | 0.869 |
sarah_vox9_0023.ply | 0.855 | 0.879 |
phil_vox9_0139.ply | 0.897 | 0.919 |
phil_vox10_0139.ply | 0.875 | 0.909 |
redandblack_vox10_1550.ply | 0.786 | 0.804 |
queen_vox10_0200.ply | 0.702 | 0.698 |
longdress_vox10_1300.ply | 0.72 | 0.738 |
basketball_player_vox11_00000200.ply | 0.667 | 0.674 |
loot_vox10_1200.ply | 0.699 | 0.718 |
dancer_vox11_00000001.ply | 0.653 | 0.661 |
soldier_vox10_0690.ply | 0.718 | 0.739 |
@article{nguyen2021lossless,
title={Lossless Coding of Point Cloud Geometry using a Deep Generative Model},
author={Nguyen, Dat Thanh and Quach, Maurice and Valenzise, Giuseppe and Duhamel, Pierre},
journal={arXiv preprint arXiv:2107.00400},
year={2021}
}
name: Ye Hua
email: yeh@pcl.ac.cn
Voxeldnn, point cloud compression in deeplearning, migrated to tensorlayer
Python CSV
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》