Efficient Virtual View Selection for 3D Hand Pose Estimation

29 Mar 2022  ·  Jian Cheng, Yanguang Wan, Dexin Zuo, Cuixia Ma, Jian Gu, Ping Tan, Hongan Wang, Xiaoming Deng, yinda zhang ·

3D hand pose estimation from single depth is a fundamental problem in computer vision, and has wide applications.However, the existing methods still can not achieve satisfactory hand pose estimation results due to view variation and occlusion of human hand. In this paper, we propose a new virtual view selection and fusion module for 3D hand pose estimation from single depth.We propose to automatically select multiple virtual viewpoints for pose estimation and fuse the results of all and find this empirically delivers accurate and robust pose estimation. In order to select most effective virtual views for pose fusion, we evaluate the virtual views based on the confidence of virtual views using a light-weight network via network distillation. Experiments on three main benchmark datasets including NYU, ICVL and Hands2019 demonstrate that our method outperforms the state-of-the-arts on NYU and ICVL, and achieves very competitive performance on Hands2019-Task1, and our proposed virtual view selection and fusion module is both effective for 3D hand pose estimation.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Hand Pose Estimation HANDS 2019 Ours-15views Average 3D Error 12.51 # 1
Hand Pose Estimation ICVL Ours-15views Error (mm) 4.76 # 1
Hand Pose Estimation ICVL Hands Virtual View Selection Average 3D Error 4.79 # 1
Hand Pose Estimation NYU Hands Virtual View Selection Average 3D Error 6.4 # 1

Methods


No methods listed for this paper. Add relevant methods here