Results for OneFormer3D
Submission data
| Full name | One Transformer for Unified Point Cloud Segmentation |
| Publication title | OneFormer3D: One Transformer for Unified Point Cloud Segmentation |
| Publication authors | Maxim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich |
| Publication URL | https://arxiv.org/abs/2311.14405 |
| Input Data Types | Uses Color Uses 3D |
| Programming language(s) | Python, CUDA |
| Hardware | RTX 3090 TI |
| Source code or download URL | https://github.com/oneformer3d/oneformer3d |
| Submission creation date | 31 Jul, 2022 |
| Last edited | 5 Mar, 2024 |
3D semantic instance results
| Info | avg ap 50% | bathtub | bed | bookshelf | cabinet | chair | counter | curtain | desk | door | otherfurniture | picture | refrigerator | shower curtain | sink | sofa | table | toilet | window |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
 | 0.801 | 1.000 | 0.973 | 0.909 | 0.698 | 0.928 | 0.582 | 0.668 | 0.685 | 0.780 | 0.687 | 0.698 | 0.702 | 1.000 | 0.794 | 0.900 | 0.784 | 0.986 | 0.635 |