Submission details
| Method name | D2-Net - multi-scale (210 poses) & InLoc (146 poses) |
| Dataset | inloc |
| Submission date | Aug. 28, 2019, 11:16 a.m. |
| Last modified | Nov. 1, 2019, 9:50 a.m. |
| Publication url | http://openaccess.thecvf.com/content_CVPR_2019/papers/Dusmanu_D2-Net_A_Trainable_CNN_for_Joint_Description_and_Detection_of_CVPR_2019_paper.pdf |
| Code url | https://github.com/mihaidusmanu/d2-net |
| Other info | Geometric Verification Reordering + Pose Estimation with GV Inliers for Top 10 + Dense Pose Verification Reordering + Pose Selection based on View Synthesis Score |
Detailed results for all conditions
| Method | duc1 | duc2 |
|---|---|---|
| D2-Net - multi-scale (210 poses) & InLoc (146 poses) | 42.9 / 63.1 / 75.3 | 40.5 / 61.8 / 77.9 |