3D Hand Pose Estimation: From Current Achievements to Future Goals
Shanxin Yuan, Guillermo Garcia-Hernando, Björn Stenger, Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee, Pavlo A. Molchanov, Jan Kautz, Sina Honari, Liuhao Ge, Junsong Yuan, Xinghao Chen, Guijin Wang, Fan Yang, Kai Akiyama, Yang Sheng Wu, Qingfu Wan, Meysam Madadi, Sérgio Escalera, Shile Li · arXiv (Cornell University) · 2017
In this paper, we strive to answer two questions: What is the current state of 3D hand pose estimation? And, what are the next challenges that need to be tackled? Following the successful Hands In the Million Challenge (HIM2017), we investigate 11 state-of-the-art methods on three tasks: single frame 3D pose estimation, 3D hand tracking, and hand pose estimation during object interaction. We analyze the performance of different CNN structures with regard to hand shape, joint visibility, view point and articulation distributions. Our findings include: (1) isolated 3D hand pose estimation achieves low mean errors (10 mm) in the view point range of [40, 150] degrees, but it is far from being solved for extreme view points; (2)3D volumetric representations outperform 2D CNNs, better capturing the spatial structure of the depth data; (3)~Discriminative methods still generalize poorly to unseen hand shapes; (4)~While joint occlusions pose a challenge for most methods, explicit modeling of structure constraints can significantly narrow the gap between errors on visible and occluded joints.