A Dual-Branch Self-Boosting Framework for Self-Supervised 3D Hand Pose Estimation

A Dual-Branch Self-Boosting Framework for Self-Supervised 3D Hand Pose Estimation

Although 3D hand pose estimation has made significant progress in recent years with the development of the deep neural network, most learning-based methods require a large amount of labeled data that is time-consuming to collect. In this paper, we propose a dual-branch self-boosting framework for se...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 31(2022) vom: 09., Seite 5052-5066
1. Verfasser: Ren, Pengfei (VerfasserIn)
Weitere Verfasser: Sun, Haifeng, Hao, Jiachang, Qi, Qi, Wang, Jingyu, Liao, Jianxin
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2022
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM344014436
003 DE-627
005 20231226021802.0
007 cr uuu---uuuuu
008 231226s2022 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2022.3192708  |2 doi 
028 5 2 |a pubmed24n1146.xml 
035 |a (DE-627)NLM344014436 
035 |a (NLM)35881601 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Ren, Pengfei  |e verfasserin  |4 aut 
245 1 2 |a A Dual-Branch Self-Boosting Framework for Self-Supervised 3D Hand Pose Estimation 
264 1 |c 2022 
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 04.08.2022 
500 |a Date Revised 04.08.2022 
500 |a published: Print-Electronic 
500 |a Citation Status MEDLINE 
520 |a Although 3D hand pose estimation has made significant progress in recent years with the development of the deep neural network, most learning-based methods require a large amount of labeled data that is time-consuming to collect. In this paper, we propose a dual-branch self-boosting framework for self-supervised 3D hand pose estimation from depth images. First, we adopt a simple yet effective image-to-image translation technology to generate realistic depth images from synthetic data for network pre-training. Second, we propose a dual-branch network to perform 3D hand model estimation and pixel-wise pose estimation in a decoupled way. Through a part-aware model-fitting loss, the network can be updated according to the fine-grained differences between the hand model and the unlabeled real image. Through an inter-branch loss, the two complementary branches can boost each other continuously during self-supervised learning. Furthermore, we adopt a refinement stage to better utilize the prior structure information in the estimated hand model for a more accurate and robust estimation. Our method outperforms previous self-supervised methods by a large margin without using paired multi-view images and achieves comparable results to strongly supervised methods. Besides, by adopting our regenerated pose annotations, the performance of the skeleton-based gesture recognition is significantly improved 
650 4 |a Journal Article 
700 1 |a Sun, Haifeng  |e verfasserin  |4 aut 
700 1 |a Hao, Jiachang  |e verfasserin  |4 aut 
700 1 |a Qi, Qi  |e verfasserin  |4 aut 
700 1 |a Wang, Jingyu  |e verfasserin  |4 aut 
700 1 |a Liao, Jianxin  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society  |d 1992  |g 31(2022) vom: 09., Seite 5052-5066  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnns 
773 1 8 |g volume:31  |g year:2022  |g day:09  |g pages:5052-5066 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2022.3192708  |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 31  |j 2022  |b 09  |h 5052-5066