|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM361145039 |
| 003 |
DE-627 |
| 005 |
20231226084524.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2023 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2023.3307889
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1203.xml
|
| 035 |
|
|
|a (DE-627)NLM361145039
|
| 035 |
|
|
|a (NLM)37616133
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Gao, Yuan
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Dynamic Keypoint Detection Network for Image Matching
|
| 264 |
|
1 |
|c 2023
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Revised 07.11.2023
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Establishing effective correspondences between a pair of images is difficult due to real-world challenges such as illumination, viewpoint and scale variations. Modern detector-based methods typically learn fixed detectors from a given dataset, which is hard to extract repeatable and reliable keypoints for various images with extreme appearance changes and weakly textured scenes. To deal with this problem, we propose a novel Dynamic Keypoint Detection Network (DKDNet) for robust image matching via a dynamic keypoint feature learning module and a guided heatmap activator. The proposed DKDNet enjoys several merits. First, the proposed dynamic keypoint feature learning module can generate adaptive keypoint features via the attention mechanism, which is flexibly updated with the current input image and can capture keypoints with different patterns. Second, the guided heatmap activator can effectively fuse multi-group keypoint heatmaps by fully considering the importance of different feature channels, which can realize more robust keypoint detection. Extensive experimental results on four standard benchmarks demonstrate that our DKDNet outperforms state-of-the-art image-matching methods by a large margin. Specifically, our DKDNet can outperform the best image-matching method by 2.1% in AUC3px on HPatches, 3.74% in AUC@ 5° on ScanNet, 7.14% in AUC@ 5° on MegaDepth and 12.32% in AUC@ 5° on YFCC100M
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a He, Jianfeng
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhang, Tianzhu
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhang, Zhe
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhang, Yongdong
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 45(2023), 12 vom: 24. Dez., Seite 14404-14419
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:45
|g year:2023
|g number:12
|g day:24
|g month:12
|g pages:14404-14419
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2023.3307889
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 45
|j 2023
|e 12
|b 24
|c 12
|h 14404-14419
|