Results for TTT-KD
Submission data
| Full name | Test-Time Training for Indoor 3D Semantic Segmentation |
| Publication title | TTT-KD: Test-Time Training for 3D Semantic Segmentation through Knowledge Distillation from Foundation Models |
| Publication authors | Lisa Weijler, Muhammad Jehanzeb Mirza, Leon Sick, Can Ekkazan, Pedro Hermosilla |
| Publication URL | https://arxiv.org/abs/2403.11691 |
| Input Data Types | Uses Color Uses 2D,Uses 3D |
| Programming language(s) | Python, Cuda |
| Hardware | A6000 |
| Submission creation date | 15 Nov, 2023 |
| Last edited | 11 Apr, 2024 |
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.773 | 0.646 | 0.818 | 0.809 | 0.774 | 0.878 | 0.581 | 0.943 | 0.687 | 0.704 | 0.978 | 0.607 | 0.336 | 0.775 | 0.912 | 0.838 | 0.823 | 0.694 | 0.967 | 0.899 | 0.794 |