Results for ROSMRF3D
Submission data
| Full name | ROSMRF: Real-time Online 3D Semantic segmentation for mobile scene |
| Description | A novel multi-modal fusion framework, named ROSMRF, to online achieve semantic segmentation of 3D scenes. |
| Input Data Types | Uses Color,Uses Geometry Uses 2D |
| Programming language(s) | python with cuda |
| Hardware | TITAN RTX |
| Submission creation date | 28 Dec, 2020 |
| Last edited | 10 Mar, 2021 |
| Last uploaded | 9 Mar, 2021 |
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.673 | 0.789 | 0.748 | 0.763 | 0.635 | 0.814 | 0.407 | 0.747 | 0.581 | 0.573 | 0.950 | 0.484 | 0.271 | 0.607 | 0.754 | 0.649 | 0.774 | 0.596 | 0.883 | 0.823 | 0.606 |