Results for DCRedNet
Submission data
| Full name | Fusing self-supervised depth completion with residual encoder-decoder network |
| Description | This is a unified framework incorporating self-supervised depth completion with the residual encoder-decoder segmentation, proposed by AI department, CloudMinds Inc (CM-CV&AR). |
| Input Data Types | Uses Color,Uses Geometry Uses 2D |
| Programming language(s) | PyTorch |
| Hardware | GeForce 1080Ti 12GB,i7-8700k |
| Submission creation date | 5 Mar, 2019 |
| Last edited | 6 Jun, 2019 |
2D 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.583 | 0.682 | 0.723 | 0.542 | 0.510 | 0.310 | 0.451 | 0.668 | 0.549 | 0.520 | 0.920 | 0.375 | 0.446 | 0.528 | 0.417 | 0.670 | 0.577 | 0.478 | 0.862 | 0.806 | 0.628 |