3D Semantic Segmentation On Scannet 1
المقاييس
Top-1 IoU
Top-3 IoU
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
اسم النموذج | Top-1 IoU | Top-3 IoU | Paper Title | Repository |
|---|---|---|---|---|
| PTv2 | 0.427 | 0.665 | Point Transformer V2: Grouped Vector Attention and Partition-based Pooling | |
| PonderV2 + SparseUNet | 0.386 | 0.386 | PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm | |
| MinkowskiNet | 0.292 | 0.531 | 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks | |
| KPConv | 0.265 | 0.460 | KPConv: Flexible and Deformable Convolution for Point Clouds | |
| PointNet++ | 0.201 | 0.389 | PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space | |
| PTv3 | 0.458 | 0.697 | Point Transformer V3: Simpler, Faster, Stronger | |
| PTv3 + PPT | 0.464 | 0.710 | Point Transformer V3: Simpler, Faster, Stronger |
0 of 7 row(s) selected.