Results for 3D-SIS
Submission data
| Full name | 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans |
| Publication title | 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans |
| Publication authors | Ji Hou, Angela Dai, Matthias Niessner |
| Publication venue | CVPR 2019 |
| Publication URL | https://arxiv.org/abs/1812.07003 |
| Input Data Types | Uses Color,Uses Geometry Uses 2D,Uses 3D |
| Programming language(s) | PyTorch |
| Hardware | GTX1080Ti |
| Source code or download URL | https://github.com/Sekunde/3D-SIS |
| Submission creation date | 23 Nov, 2018 |
| Last edited | 27 Apr, 2019 |
3D semantic instance results
| Info | avg ap 25% | bathtub | bed | bookshelf | cabinet | chair | counter | curtain | desk | door | otherfurniture | picture | refrigerator | shower curtain | sink | sofa | table | toilet | window |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
 | 0.558 | 1.000 | 0.773 | 0.614 | 0.503 | 0.691 | 0.200 | 0.412 | 0.498 | 0.546 | 0.311 | 0.103 | 0.600 | 0.857 | 0.382 | 0.799 | 0.445 | 0.938 | 0.371 |