3D hand shape and pose estimation from a single depth map is a new and challenging computer vision problem with many applications. Existing methods addressing it directly regress hand meshes via 2D convolutional neural networks, which leads to artifacts due to perspective distortions in the images. To address the limitations of the existing methods, we develop HandVoxNet++, i.e., a voxel-based deep network with 3D and graph convolutions trained in a fully supervised manner. The input to our network is a 3D voxelized-depth-map-based on the truncated signed distance function (TSDF). HandVoxNet++ relies on two hand shape representations. The first one is the 3D voxelized grid of hand shape, which does not preserve the mesh topology and which is the most accurate representation. The second representation is the hand surface that preserves the mesh topology. We combine the advantages of both representations by aligning the hand surface to the voxelized hand shape either with a new neural Graph-Convolutions-based Mesh Registration (GCN-MeshReg) or classical segment-wise Non-Rigid Gravitational Approach (NRGA++) which does not rely on training data. In extensive evaluations on three public benchmarks, i.e., SynHand5M, depth-based HANDS19 challenge and HO-3D, the proposed HandVoxNet++ achieves the state-of-the-art performance. In this journal extension of our previous approach presented at CVPR 2020, we gain 41.09% and 13.7% higher shape alignment accuracy on SynHand5M and HANDS19 datasets, respectively. Our method is ranked first on the HANDS19 challenge dataset (Task 1: Depth-Based 3D Hand Pose Estimation) at the moment of the submission of our results to the portal in August 2020.
翻译:3D 手形和从单一深度映射中作出估计是一个具有挑战性的新型计算机图像问题。 许多应用程序都存在。 通过 2D 进化神经网络直接递退手模件的现存方法, 这导致图像的视觉扭曲。 为解决现有方法的局限性, 我们开发HandVoxNet+++, 即基于 voxel 的深网络, 由 3D 和 图形的完全监控方式培训。 我们网络的输入是 3D 驱动的 计算机门户网站 。 以 快速签名远程功能( TSDF) 为基础, 3DVelel 深度的计算机图像。 HandVoxNet++ 依赖两个手形表达方式。 第一个是 3D vell化的手形网格, 它不会保存网形图示, 也就是以 3DVD为主的 。 我们的手表面与基于 Scial- 3Server 的图像转换方法( GCN-Mesh- Reeg+++) 显示两个直径直径直径直径, 的H- deal- dal- disal- destal- disal- disal- disal- disal- disal- disal- dismal- disal- disl- dismal- disl) 。 在三 Reval- disal- disal- disal- disal- disal- dismal- dismal- disfal- disfal- dismal- disgal- 上, 上, 上, 上,,,, 和O- dis- dis- dis- dis- dis- disg- dis- disl- disg- disgal- disgald- disgal- dism- disgald- disald- disald-d-d-d-d- dism- disal- disal-d- disal- disal- dism- disl- dism- dism- 和O- 和O- 上, 上,