Results for PPT-SpUNet-Joint
Submission data
| Full name | Point Prompt Training |
| Publication title | Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training |
| Publication authors | Xiaoyang Wu, Zhuotao Tian, Xin Wen, Bohao Peng, Xihui Liu, Kaicheng Yu, Hengshuang Zhao |
| Publication venue | CVPR 2024 |
| Publication URL | https://arxiv.org/abs/2308.09718 |
| Input Data Types | Uses Color Uses 3D |
| Programming language(s) | Python, C++ with CUDA |
| Hardware | NVIDIA A100 |
| Website | https://github.com/Pointcept/Pointcept |
| Source code or download URL | https://github.com/Pointcept/Pointcept |
| Submission creation date | 28 Feb, 2023 |
| Last edited | 2 Mar, 2024 |
3D semantic label results
| Info | avg iou | bathtub | bed | bookshelf | cabinet | chair | counter | curtain | desk | door | floor | otherfurniture | picture | refrigerator | shower curtain | sink | sofa | table | toilet | wall | window |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.766 | 0.932 | 0.794 | 0.829 | 0.751 | 0.854 | 0.540 | 0.903 | 0.630 | 0.672 | 0.963 | 0.565 | 0.357 | 0.788 | 0.900 | 0.737 | 0.802 | 0.685 | 0.950 | 0.887 | 0.780 |