Meta Deformation Network: Meta Functionals for Shape Correspondence
This addresses shape correspondence for 3D modeling or computer vision applications, but it appears incremental as it builds on existing deformation-based methods with a novel parameterization.
The paper tackles 3D shape matching by introducing a Meta Deformation Network, where one neural network dynamically generates parameters for another to deform a template onto query shapes, resulting in faster execution without quality loss and improvements on the MPI-FAUST Inter Challenge.
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.