Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
yehua d8b4b1a56f | 1 year ago | |
---|---|---|
MindSpore | 1 year ago | |
PyTorch | 1 year ago | |
TensorFlow | 1 year ago | |
config | 1 year ago | |
projection_splicing | 1 year ago | |
2022_No-Reference Point Cloud Quality Assessment via Domain Adaptation.pdf | 1 year ago | |
LICENSE | 1 year ago | |
README.md | 1 year ago |
key words: point cloud quality assessment, no-reference, domain adaptation
IT-PCQA is a novel point cloud quality assessment method of no reference. Leveraging the rich subjective scores of the natural images, IT-PCQA quests the evaluation criteria of human perception via DNN and transfers the capability of prediction to 3D point clouds. The method suggests the feasibility of assessing the quality of specific media content without the expensive and cumbersome subjective evaluations.
1.transplant from pytorch to tensorflow and mindspore.
2.benchmark test on mindspore, tensorflow and pytorch, and compare the performance.
root
└── config: dataset config files, updated from original version to fit our environment
└── MindSpore: mindspore code, results and models are included
└── TensorFlow: tensorflow code, results and models are included
└── PyTorch: results and models in pytorch version, for pytorch source code, please go to: https://github.com/Qi-Yangsjtu/IT-PCQA
└── 2022_No-Reference Point Cloud Quality Assessment via Domain Adaptation.pdf: origional paper
cd MindSpore
cd TensorFlow
training:
python train.py
Table 1. Test on SJTU dataset
Source | PLCC | SROCC | GPU memory(MB) |
---|---|---|---|
Paper | 0.58 | 0.63 | - |
Pytorch | 0.686 | 0.6285 | 3750 |
Mindspore | 0.7228 | 0.5198 | 5200 |
TensorFlow | 0.7221 | 0.6348 | 4750 |
"Qi Yang, Yipeng Liu, Siheng Chen, Yiling Xu, Jun Sun, "No-Reference Point Cloud Quality Assessment via Domain Adaptation," in CVPR, 2022."
@InProceedings{yang2022ITPCQA,
author = {Qi Yang and Yipeng Liu and Siheng Chen and Yiling Xu and Jun Sun},
title = {No-Reference Point Cloud Quality Assessment via Domain Adaptation},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2022}
}
name: Ye Hua
email: yeh@pcl.ac.cn
point cloud quality assessment, no-reference, Domain Adaptation
CSV Text Python
Apache-2.0
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》