Results for Sparse R-CNN
Submission data
| Full name | Sparse Convolutions for Semantic 3D Instance Segmentation |
| Description | Semantic Instance Segmentation based on Mask R-CNN, 3D-SIS and Submanifold Sparse Convolutional Networks |
| Input Data Types | Uses Color,Uses Geometry Uses 3D |
| Programming language(s) | Python 3.8, PyTorch 1.4 |
| Hardware | GeForce GTX 1080 Ti |
| Submission creation date | 16 Mar, 2020 |
| Last edited | 20 May, 2020 |
3D semantic instance results
| Info | avg ap 50% | bathtub | bed | bookshelf | cabinet | chair | counter | curtain | desk | door | otherfurniture | picture | refrigerator | shower curtain | sink | sofa | table | toilet | window |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.515 | 1.000 | 0.538 | 0.282 | 0.468 | 0.790 | 0.173 | 0.345 | 0.429 | 0.413 | 0.484 | 0.176 | 0.595 | 0.591 | 0.522 | 0.668 | 0.476 | 0.986 | 0.327 |