Submission details
Method name | NetVLAD (top-20) & D2-Net - single-scale |
Dataset | silda |
Submission date | Sept. 25, 2019, 3:05 p.m. |
Last modified | Sept. 25, 2019, 3:05 p.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 | Uses NetVLAD (sum_edges = 1400) to identify the top-20 closest database images, then uses single-scale D2-Net features matching and COLMAP's image_registrator for localization. |
Detailed results for all conditions
Method | evening | snow | night |
---|---|---|---|
NetVLAD (top-20) & D2-Net - single-scale | 28.1 / 66.8 / 93.5 | 1.7 / 11.1 / 67.3 | 24.4 / 49.0 / 75.7 |