Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation

Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation

6D object pose estimation is a fundamental yet challenging problem in computer vision. Convolutional Neural Networks (CNNs) have recently proven to be capable of predicting reliable 6D pose estimates even under monocular settings. Nonetheless, CNNs are identified as being extremely data-driven, and...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 46(2024), 3 vom: 15. Feb., Seite 1788-1803
1. Verfasser: Wang, Gu (VerfasserIn)
Weitere Verfasser: Manhardt, Fabian, Liu, Xingyu, Ji, Xiangyang, Tombari, Federico
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2024
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000caa a22002652 4500
001 NLM334556724
003 DE-627
005 20240207231940.0
007 cr uuu---uuuuu
008 231225s2024 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2021.3136301  |2 doi 
028 5 2 |a pubmed24n1283.xml 
035 |a (DE-627)NLM334556724 
035 |a (NLM)34919518 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Wang, Gu  |e verfasserin  |4 aut 
245 1 0 |a Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation 
264 1 |c 2024 
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 07.02.2024 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a 6D object pose estimation is a fundamental yet challenging problem in computer vision. Convolutional Neural Networks (CNNs) have recently proven to be capable of predicting reliable 6D pose estimates even under monocular settings. Nonetheless, CNNs are identified as being extremely data-driven, and acquiring adequate annotations is oftentimes very time-consuming and labor intensive. To overcome this limitation, we propose a novel monocular 6D pose estimation approach by means of self-supervised learning, removing the need for real annotations. After training our proposed network fully supervised with synthetic RGB data, we leverage current trends in noisy student training and differentiable rendering to further self-supervise the model on these unsupervised real RGB(-D) samples, seeking for a visually and geometrically optimal alignment. Moreover, employing both visible and amodal mask information, our self-supervision becomes very robust towards challenging scenarios such as occlusion. Extensive evaluations demonstrate that our proposed self-supervision outperforms all other methods relying on synthetic data or employing elaborate techniques from the domain adaptation realm. Noteworthy, our self-supervised approach consistently improves over its synthetically trained baseline and often almost closes the gap towards its fully supervised counterpart 
650 4 |a Journal Article 
700 1 |a Manhardt, Fabian  |e verfasserin  |4 aut 
700 1 |a Liu, Xingyu  |e verfasserin  |4 aut 
700 1 |a Ji, Xiangyang  |e verfasserin  |4 aut 
700 1 |a Tombari, Federico  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 46(2024), 3 vom: 15. Feb., Seite 1788-1803  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:46  |g year:2024  |g number:3  |g day:15  |g month:02  |g pages:1788-1803 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2021.3136301  |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 46  |j 2024  |e 3  |b 15  |c 02  |h 1788-1803