论文标题
元变形网络：形状对应的元功能
Meta Deformation Network: Meta Functionals for Shape Correspondence
论文作者
论文摘要
我们提出了一种通过变形的新技术，称为3D形状匹配的“元变形网络”，其中深神经网络将参考形状映射到第二个神经网络的参数上，其任务是通过变形给予学习模板和查询形状之间的对应关系。我们将第二个神经网络分为元函数或另一个函数生成的函数，因为它的参数是由第一个网络以每输入为基础的。这导致了直接的整体体系结构和更快的执行速度，而不会损失模板的变形质量。我们在实验中表明，元变形网络会改善MPI爆炸互动挑战，而不是使用具有非动力学参数的传统解码器设计。
We present a new technique named "Meta Deformation Network" for 3D shape matching via deformation, in which a deep neural network maps a reference shape onto the parameters of a second neural network whose task is to give the correspondence between a learned template and query shape via deformation. We categorize the second neural network as a meta-function, or a function generated by another function, as its parameters are dynamically given by the first network on a per-input basis. This leads to a straightforward overall architecture and faster execution speeds, without loss in the quality of the deformation of the template. We show in our experiments that Meta Deformation Network leads to improvements on the MPI-FAUST Inter Challenge over designs that utilized a conventional decoder design that has non-dynamic parameters.
