Object Rearrangement On Open6Dor V2
Metrics
6-DoF
pos-level0
pos-level1
rot-level0
rot-level1
rot-level2
Results
Performance results of various models on this benchmark
Model Name | 6-DoF | pos-level0 | pos-level1 | rot-level0 | rot-level1 | rot-level2 | Paper Title | Repository |
|---|---|---|---|---|---|---|---|---|
| GPT-4V | - | 39.1 | 46.8 | 9.1 | 6.9 | 11.7 | GPT-4 Technical Report | |
| Open6DOR | 35.6 | 60.3 | 78.6 | 45.7 | 32.5 | 49.8 | Open6DOR: Benchmarking Open-instruction 6-DoF Object Rearrangement and A VLM-based Approach | |
| SoFar | 48.7 | 96.0 | 81.5 | 68.6 | 42.2 | 70.1 | SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation | |
| Dream2Real | 13.5 | 11.0 | 17.2 | 37.3 | 27.6 | 26.2 | Dream2Real: Zero-Shot 3D Object Rearrangement with Vision-Language Models | - |
| VoxPoser | - | 21.7 | 35.6 | - | - | - | VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models |
0 of 5 row(s) selected.