TY - CONF AU - Shanxin Yuan AU - Guillermo Garcia-Hernando AU - Bjorn Stenger AU - Gyeongsik Moon AU - Ju Yong Chang AU - Kyoung Mu Lee AU - Pavlo Molchanov AU - Jan Kautz AU - Sina Honari AU - Liuhao Ge AU - Junsong Yuan AU - Xinghao Chen AU - Guijin Wang AU - Fan Yang AU - Kai Akiyama AU - Yang Wu AU - Qingfu Wan AU - Meysam Madadi AU - Sergio Escalera AU - Shile Li AU - Dongheui Lee AU - Iason Oikonomidis AU - Antonis Argyros AU - Tae-Kyun Kim A2 - CVPR PY - 2018// TI - Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals BT - 31st IEEE Conference on Computer Vision and Pattern Recognition SP - 2636 EP - 2645 KW - Three-dimensional displays KW - Task analysis KW - Pose estimation KW - Two dimensional displays KW - Joints KW - Training KW - Solid modeling N2 - In this paper, we strive to answer two questions: What is the current state of 3D hand pose estimation from depth images? And, what are the next challenges that need to be tackled? Following the successful Hands In the Million Challenge (HIM2017), we investigate the top 10 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 [70, 120] 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. L1 - http://refbase.cvc.uab.es/files/YGS2018.pdf UR - http://dx.doi.org/10.1109/CVPR.2018.00279 N1 - HUPBA; no proj ID - Shanxin Yuan2018 ER -