Results for TWIST+CSC
Submission data
| Full name | Two-Way Inter-label Self-Training for Semi-supervised 3D Instance Segmentation |
| Publication title | TWIST: Two-Way Inter-label Self-Training for Semi-supervised 3D Instance Segmentation |
| Publication authors | Ruihang Chu |
| Publication venue | CVPR 2022 |
| Publication URL | https://openaccess.thecvf.com/content/CVPR2022/papers/Chu_TWIST_Two-Way_Inter-Label_Self-Training_for_Semi-Supervised_3D_Instance_Segmentation_CVPR_2022_paper.pdf |
| Input Data Types | Uses Color Uses 3D |
| Programming language(s) | python, CUDA |
| Hardware | 2080Ti |
| Submission creation date | 25 Oct, 2021 |
| Last edited | 19 Dec, 2023 |
3D semantic instance results with limited reconstructions
| Info | avg ap 50% | bathtub | bed | bookshelf | cabinet | chair | counter | curtain | desk | door | otherfurniture | picture | refrigerator | shower curtain | sink | sofa | table | toilet | window |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.481 | 0.667 | 0.760 | 0.468 | 0.313 | 0.802 | 0.008 | 0.529 | 0.098 | 0.364 | 0.411 | 0.348 | 0.500 | 0.571 | 0.504 | 0.646 | 0.530 | 0.944 | 0.201 |