Meta Deformation Network: Meta Functionals for Shape Correspondence
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.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderSimilar Papers 제목 키워드 기반
DeepMetaHandles: Learning Deformation Meta-Handles of 3D Meshes with Biharmonic Coordinates
We propose DeepMetaHandles, a 3D conditional generative model based on mesh deformation. Given a collection of 3D meshes of a category and their deformation handles (control points), our method learns a set of meta-handl…
MetaRegNet: Metamorphic Image Registration Using Flow-Driven Residual Networks
Deep learning based methods provide efficient solutions to medical image registration, including the challenging problem of diffeomorphic image registration. However, most methods register normal image pairs, facing diff…
Image RegistrationMedical Image RegistrationDeep Meta Functionals for Shape Representation
We present a new method for 3D shape reconstruction from a single image, in which a deep neural network directly maps an image to a vector of network weights. The network \textcolor{black}{parametrized by} these weights …
3D Shape Reconstruction3D Meta Point Signature: Learning to Learn 3D Point Signature for 3D Dense Shape Correspondence
Point signature, a representation describing the structural neighborhood of a point in 3D shapes, can be applied to establish correspondences between points in 3D shapes. Conventional methods apply a weight-sharing netwo…
3D Dense Shape CorrespondenceMeta-LearningLearning-Based Image Registration With Meta-Regularization
We introduce a meta-regularization framework for learning-based image registration. Current learning-based image registration methods use high-resolution architectures such as U-Nets to produce spatial transformation…
Image Registration