Table 2.
Quantitative comparison with prediction results of other models on KITTI dataset.
| Method | δ1↑ | δ2↑ | δ3↑ | REL↓ | Sq. Rel↓ | RMS↓ | RMS log↓ |
|---|---|---|---|---|---|---|---|
| Eigen et al.1 | 0.702 | 0.898 | 0.967 | 0.203 | 1.548 | 6.307 | 0.282 |
| Fu et al.13 | 0.932 | 0.984 | 0.994 | 0.072 | 0.307 | 2.727 | 0.120 |
| Alhashim et al.8 | 0.886 | 0.965 | 0.986 | 0.093 | 0.589 | 4.170 | – |
| Yin et al.11 | 0.938 | 0.990 | 0.998 | 0.072 | – | 3.258 | 0.117 |
| Lee et al.9 | 0.956 | 0.993 | 0.998 | 0.059 | 0.245 | 2.756 | 0.096 |
| Bhat et al.14 | 0.964 | 0.995 | 0.999 | 0.058 | 0.190 | 2.360 | 0.088 |
| Ranftl et al.3 | 0.959 | 0.995 | 0.999 | 0.062 | 0.222 | 2.575 | 0.092 |
| Proposed | 0.965 | 0.995 | 0.999 | 0.057 | 0.197 | 2.368 | 0.088 |
The best results are shown in bold, and the second best results are italics.