Model Zoo
1. Indoor semantic segmentation
Model | Benchmark | Additional Data | Num GPUs | Val mIoU | Config | Tensorboard | Exp Record |
---|---|---|---|---|---|---|---|
PTv3 | ScanNet | β | 4 | 77.6% | link | link | link |
PTv3 + PPT | ScanNet | β | 8 | 78.5% | link | link | link |
PTv3 | ScanNet200 | β | 4 | 35.3% | link | link | link |
PTv3 + PPT | ScanNet200 | β (f.t.) | 4 | ||||
PTv3 | S3DIS (Area5) | β | 4 | 73.6% | link | link | link |
PTv3 + PPT | S3DIS (Area5) | β | 8 | 75.4% | link | link | link |
2. Outdoor semantic segmentation
Model | Benchmark | Additional Data | Num GPUs | Val mIoU | Config | Tensorboard | Exp Record |
---|---|---|---|---|---|---|---|
PTv3 | nuScenes | β | 4 | 80.3 | link | link | link |
PTv3 + PPT | nuScenes | β | 8 | ||||
PTv3 | SemanticKITTI | β | 4 | ||||
PTv3 + PPT | SemanticKITTI | β | 8 | ||||
PTv3 | Waymo | β | 4 | 71.2 | link | link | link (log only) |
PTv3 + PPT | Waymo | β | 8 |
- Model weights trained with Waymo Open Dataset cannot be released due to the regulations.