Results for Supervoxel-CNN
Submission data
| Full name | Supervoxel Based Networks |
| Description | A 2D-3D joint learning method |
| Input Data Types | Uses Color,Uses Geometry Uses 2D |
| Programming language(s) | C++ with CUDA |
| Hardware | TITAN RTX |
| Submission creation date | 24 Apr, 2020 |
| Last edited | 29 Oct, 2020 |
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.635 | 0.656 | 0.711 | 0.719 | 0.613 | 0.757 | 0.444 | 0.765 | 0.534 | 0.566 | 0.928 | 0.478 | 0.272 | 0.636 | 0.531 | 0.664 | 0.645 | 0.508 | 0.864 | 0.792 | 0.611 |