Submission details
Method name | DenseVLAD (top-50) & D2-Net - multi-scale |
Dataset | aachen |
Submission date | Sept. 20, 2019, 5:08 p.m. |
Last modified | Nov. 1, 2019, 9:49 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 | Uses DenseVLAD (single-scale) to identify the top-50 closest database images, then uses multi-scale D2-Net features for feature matching and COLMAP's image_registrator for localization. |
Detailed results for all conditions
Method | day | night |
---|---|---|
DenseVLAD (top-50) & D2-Net - multi-scale | 83.1 / 90.9 / 95.5 | 74.5 / 85.7 / 90.8 |