Chengde Wan, Thomas Probst, Luc Van Gool, Angela Yao
TL;DR本文提出了一种通过从单个深度图中回归网格模型顶点坐标来恢复手部密集 3D 表面的方法,使用两阶段 2D 完全卷积网络架构和可微分算子来实现,能够通过自我监督实现更好的效果,表现优异。
Abstract
We present a method for recovering the dense 3D surface of the hand by
regressing the vertex coordinates of a mesh model from a single depth map. To
this end, we use a two-stage 2D fully convolutional network arc