|
|
|
|
| LEADER |
01000caa a22002652c 4500 |
| 001 |
NLM340651350 |
| 003 |
DE-627 |
| 005 |
20250303081958.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2023 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2022.3174130
|2 doi
|
| 028 |
5 |
2 |
|a pubmed25n1135.xml
|
| 035 |
|
|
|a (DE-627)NLM340651350
|
| 035 |
|
|
|a (NLM)35536823
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Liu, Shuaicheng
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Content-Aware Unsupervised Deep Homography Estimation and its Extensions
|
| 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 Completed 07.04.2023
|
| 500 |
|
|
|a Date Revised 07.04.2023
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Homography estimation is a basic image alignment method in many applications. It is usually done by extracting and matching sparse feature points, which are error-prone in low-light and low-texture images. On the other hand, previous deep homography approaches use either synthetic images for supervised learning or aerial images for unsupervised learning, both ignoring the importance of handling depth disparities and moving objects in real-world applications. To overcome these problems, in this work, we propose an unsupervised deep homography method with a new architecture design. In the spirit of the RANSAC procedure in traditional methods, we specifically learn an outlier mask to only select reliable regions for homography estimation. We calculate loss with respect to our learned deep features instead of directly comparing image content as did previously. To achieve the unsupervised training, we also formulate a novel triplet loss customized for our network. We verify our method by conducting comprehensive comparisons on a new dataset that covers a wide range of scenes with varying degrees of difficulties for the task. Experimental results reveal that our method outperforms the state-of-the-art, including deep solutions and feature-based solutions
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Ye, Nianjin
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Wang, Chuan
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhang, Jirong
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Jia, Lanpeng
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Luo, Kunming
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Wang, Jue
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Sun, Jian
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 45(2023), 3 vom: 01. März, Seite 2849-2863
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnas
|
| 773 |
1 |
8 |
|g volume:45
|g year:2023
|g number:3
|g day:01
|g month:03
|g pages:2849-2863
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2022.3174130
|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 3
|b 01
|c 03
|h 2849-2863
|