Table 5 Comparison with state-of-the-art methods on the LINEMOD dataset.
From: MagicCubePose, A more comprehensive 6D pose estimation network
Method | BB8 | PoseCNN+DeepIM35 | Tekin | Faster R-CNN+DeepIM | Our (\(\varphi\)=0) |
|---|---|---|---|---|---|
5cm5degree | 69 | 85.2 | – | 83.4 | 86.64 |
ADD | 62.7 | 88.6 | 55.95 | 86.9 | 97.5 |
2D Projection | 89.3 | 97.5 | 90.37 | 95.7 | 97.36 |
