Results for SQN_0.1%
Submission data
| Full name | SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds |
| Description | Semantic Query Network trained with only 0.1% randomly selected labels |
| Input Data Types | Uses Color,Uses Geometry Uses 3D |
| Programming language(s) | Tensorflow |
| Hardware | Intel Core™ i9-10900X CPU, NVIDIARTX Titan GPU |
| Submission creation date | 24 Mar, 2021 |
| Last edited | 25 Jan, 2022 |
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.569 | 0.676 | 0.696 | 0.657 | 0.497 | 0.779 | 0.424 | 0.548 | 0.515 | 0.376 | 0.902 | 0.422 | 0.357 | 0.379 | 0.456 | 0.596 | 0.659 | 0.544 | 0.685 | 0.665 | 0.556 |