Primitive Fitting on Primitive Fitting (Out-of-distribution)
80.4mIoUAutoGPart (HPNet)
Evaluation results
| Method | Links | |
|---|---|---|
| AutoGPart (HPNet)Segmentation Module Type=Clustering-based2022.03 | 80.4 | |
| HPNetSegmentation Module Type=Clustering-based2022.03 | 79.5 | |
| AutoGPart (PN++)Backbone=PointNet++, Segmentation Module Type=Classification-based2022.03 | 76.5 | |
| AutoGPart (DGCNN)Backbone=DGCNN, Segmentation Module Type=Classification-based2022.03 | 73.4 | |
| SPFNSegmentation Module Type=Classification-based2022.03 | 72.3 | |
| PointNet++Backbone=PointNet++, Segmentation Module Type=Classification-based2022.03 | 71.6 | |
| Gradient Surgery (DGCNN)Backbone=DGCNN, Training Strategy=Gradient Surgery, Segmentation Module Type=Classification-based2022.03 | 71.6 | |
| MixStyle (DGCNN)Backbone=DGCNN, Training Strategy=MixStyle, Segmentation Module Type=Classification-based2022.03 | 71.4 | |
| MixStyle (PN++)Backbone=PointNet++, Training Strategy=MixStyle, Segmentation Module Type=Classification-based2022.03 | 70.9 | |
| Gradient Surgery (PN++)Backbone=PointNet++, Training Strategy=Gradient Surgery, Segmentation Module Type=Classification-based2022.03 | 70.3 | |
| HPNet*Segmentation Module Type=Clustering-based2022.03 | 69.6 | |
| Meta-learning (DGCNN)Backbone=DGCNN, Training Strategy=Meta-learning, Segmentation Module Type=Classification-based2022.03 | 69.3 | |
| Meta Learning (PN++)Backbone=PointNet++, Training Strategy=Meta-learning, Segmentation Module Type=Classification-based2022.03 | 68.5 | |
| DGCNNBackbone=DGCNN, Segmentation Module Type=Classification-based2022.03 | 68 |