Feasibility classification on GraspNet-1Billion 1.0 (Seen)
0.996AUROCGRASPFC-PTX
Evaluation results
| Method | Links | |
|---|---|---|
| GRASPFC-PTXEncoder (Architecture)=PTv3, Input=Pose + Cloud, Train. set=MOFEAS-200K2026.06 | 0.996 | |
| GRASPFC-NNETEncoder (Architecture)=PointNeXt-S, Input=Pose + Cloud, Train. set=MOFEAS-200K2026.06 | 0.995 | |
| GRASPFC-PTXEncoder (Architecture)=PTv3, Input=Pose + Cloud, Train. set=MOFEAS-5K-Bal2026.06 | 0.981 | |
| GRASPFC-CONV3DEncoder (Architecture)=VGN + GIGA, Input=Pose + Voxel, Train. set=MOFEAS-200K2026.06 | 0.98 | |
| GRASPFC-CONV3DEncoder (Architecture)=VGN + GIGA, Input=Pose + Voxel, Train. set=MOFEAS-5K-Bal2026.06 | 0.964 | |
| GRASPFC-CONV3D (no pose)Encoder (Architecture)=VGN, Input=Scene cloud, Train. set=MOFEAS-5K-Bal2026.06 | 0.552 |