|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM360812848 |
| 003 |
DE-627 |
| 005 |
20231226083820.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2023 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2023.3305399
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1202.xml
|
| 035 |
|
|
|a (DE-627)NLM360812848
|
| 035 |
|
|
|a (NLM)37581967
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Chen, Rui
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a ActiveZero++
|b Mixed Domain Learning Stereo and Confidence-Based Depth Completion With Zero Annotation
|
| 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 Learning-based stereo methods usually require a large scale dataset with depth, however obtaining accurate depth in the real domain is difficult, but groundtruth depth is readily available in the simulation domain. In this article we propose a new framework, ActiveZero++, which is a mixed domain learning solution for active stereovision systems that requires no real world depth annotation. In the simulation domain, we use a combination of supervised disparity loss and self-supervised loss on a shape primitives dataset. By contrast, in the real domain, we only use self-supervised loss on a dataset that is out-of-distribution from either training simulation data or test real data. To improve the robustness and accuracy of our reprojection loss in hard-to-perceive regions, our method introduces a novel self-supervised loss called temporal IR reprojection. Further, we propose the confidence-based depth completion module, which uses the confidence from the stereo network to identify and improve erroneous areas in depth prediction through depth-normal consistency. Extensive qualitative and quantitative evaluations on real-world data demonstrate state-of-the-art results that can even outperform a commercial depth sensor. Furthermore, our method can significantly narrow the Sim2Real domain gap of depth maps for state-of-the-art learning based 6D pose estimation algorithms
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Liu, Isabella
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yang, Edward
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Tao, Jianyu
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhang, Xiaoshuai
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Ran, Qing
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Liu, Zhu
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Xu, Jing
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Su, Hao
|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: 15. Dez., Seite 14098-14113
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:45
|g year:2023
|g number:12
|g day:15
|g month:12
|g pages:14098-14113
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2023.3305399
|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 15
|c 12
|h 14098-14113
|