Results for ScanNet
Submission data
| Full name | ScanNet semantic segmentation network |
| Publication title | ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes |
| Publication authors | Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner |
| Publication venue | CVPR'17 |
| Publication URL | http://www.scan-net.org/ |
| Input Data Types | Uses Geometry Uses 3D |
| Programming language(s) | pytorch |
| Hardware | GTX 1080 |
| Website | http://www.scan-net.org/ |
| Source code or download URL | https://github.com/scannet/scannet |
| Submission creation date | 4 Jul, 2018 |
| Last edited | 14 Jul, 2018 |
| Last uploaded | 13 Jul, 2018 |
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
 | 0.306 | 0.203 | 0.366 | 0.501 | 0.311 | 0.524 | 0.211 | 0.002 | 0.342 | 0.189 | 0.786 | 0.145 | 0.102 | 0.245 | 0.152 | 0.318 | 0.348 | 0.300 | 0.460 | 0.437 | 0.182 |