Results for DITR ScanNet
Submission data
| Full name | DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation |
| Input Data Types | Uses Color,Uses Geometry Uses 2D,Uses 3D |
| Programming language(s) | Python with CUDA |
| Hardware | H100 |
| Submission creation date | 14 Nov, 2024 |
| Last edited | 14 Nov, 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.793 | 0.811 | 0.852 | 0.889 | 0.774 | 0.907 | 0.592 | 0.927 | 0.719 | 0.718 | 0.961 | 0.652 | 0.348 | 0.817 | 0.927 | 0.795 | 0.824 | 0.749 | 0.948 | 0.887 | 0.771 |