3D Semantic Segmentation On Scannet200
Métriques
test mIoU
val mIoU
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | test mIoU | val mIoU |
|---|---|---|
| dino-in-the-room-leveraging-2d-foundation | 44.9 | 41.2 |
| towards-large-scale-3d-representation | 33.2 | 31.9 |
| mamba24-8d-enhancing-global-interaction-in | 37.1 | 36.3 |
| octformer-octree-based-transformers-for-3d | 32.5 | 32.6 |
| ponderv2-pave-the-way-for-3d-foundataion | 34.6 | 32.3 |
| oneformer3d-one-transformer-for-unified-point | - | 30.1 |
| oa-cnns-omni-adaptive-sparse-cnns-for-3d | 32.3 | 33.3 |
| lsk3dnet-towards-effective-and-efficient-3d | - | 33.1 |
| exploring-data-efficient-3d-scene | 24.9 | 26.4 |
| 4d-spatio-temporal-convnets-minkowski | 25.3 | 25.0 |
| odin-a-single-model-for-2d-and-3d-perception | 36.8 | 40.5 |
| sonata-self-supervised-learning-of-reliable | - | 36.8 |
| bfanet-revisiting-3d-semantic-segmentation | 36.0 | 37.3 |
| point-transformer-v3-simpler-faster-stronger | 39.3 | 36.0 |
| language-grounded-indoor-3d-semantic | 27.2 | 28.8 |
| arkit-labelmaker-a-new-scale-for-indoor-3d | 41.4 | 40.3 |