Results for TST3D
Submission data
| Full name | Two-scale Superpoint with Twin-attention for 3D Instance Segmentation |
| Description | MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation |
| Input Data Types | Uses Color,Uses Geometry Uses 3D |
| Programming language(s) | Python |
| Hardware | NVIDIA A100 |
| Submission creation date | 27 Sep, 2023 |
| Last edited | 25 Jul, 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.795 | 1.000 | 0.929 | 0.918 | 0.709 | 0.884 | 0.596 | 0.704 | 0.769 | 0.734 | 0.644 | 0.699 | 0.751 | 1.000 | 0.794 | 0.876 | 0.757 | 0.997 | 0.550 |