Results for TST3D
Submission data
Full name | Two-scale Superpoint with 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 Mar, 2024 |
3D semantic instance results
Info | avg ap | bathtub | bed | bookshelf | cabinet | chair | counter | curtain | desk | door | otherfurniture | picture | refrigerator | shower curtain | sink | sofa | table | toilet | window |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0.569 | 0.778 | 0.675 | 0.598 | 0.451 | 0.727 | 0.280 | 0.476 | 0.395 | 0.472 | 0.457 | 0.583 | 0.580 | 0.777 | 0.462 | 0.735 | 0.547 | 0.919 | 0.333 |