Results for MS-SFA-net
Submission data
| Full name | Multi-Scale Supervoxel Feature Aggregation Module |
| Description | 3D point cloud semantic segmentation is a critical component of scene understanding, yet existing deep learning architectures, particularly Point Transformers, struggle with "boundary blindness" and topological disruption. |
| Input Data Types | Uses Color Uses 3D |
| Programming language(s) | python |
| Hardware | RTX3060 |
| Submission creation date | 6 Dec, 2025 |
| Last edited | 7 Dec, 2025 |
| Last uploaded | 6 Dec, 2025 |
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.730 | 0.910 | 0.819 | 0.837 | 0.698 | 0.838 | 0.532 | 0.872 | 0.605 | 0.676 | 0.959 | 0.535 | 0.341 | 0.649 | 0.598 | 0.708 | 0.810 | 0.664 | 0.895 | 0.879 | 0.771 |