Results for VACNN++
Submission data
| Full name | Voxel-Attention Convolutional Neural Network |
| Description | efficient point clouds convolution using voxel edge features and attentional weight function |
| Input Data Types | Uses Color Uses 3D |
| Programming language(s) | PyTorch 1.6.0 & Python3.6 |
| Hardware | GTX 1080 Ti |
| Submission creation date | 13 Sep, 2020 |
| Last edited | 16 Nov, 2020 |
| Last uploaded | 14 Jun, 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.684 | 0.728 | 0.757 | 0.776 | 0.690 | 0.804 | 0.464 | 0.816 | 0.577 | 0.587 | 0.945 | 0.508 | 0.276 | 0.671 | 0.710 | 0.663 | 0.750 | 0.589 | 0.881 | 0.832 | 0.653 |