Efficient Virtual View Selection for 3D Hand Pose Estimation
This addresses view variation and occlusion issues in hand pose estimation for applications in computer vision, representing an incremental improvement over existing methods.
The paper tackles the problem of 3D hand pose estimation from single depth images by proposing a virtual view selection and fusion module, which improves accuracy and robustness, outperforming state-of-the-art methods on NYU and ICVL datasets and achieving competitive performance on Hands2019-Task1.
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.