Non‐rigid registration computes an alignment between a source surface with a target
surface in a non‐rigid manner. In the past decade, with the advances in 3D sensing …

Point clouds provide a flexible geometric representation suitable for countless applications
in computer graphics; they also comprise the raw output of most 3D data acquisition devices …

Deep learning methods have achieved great success in analyzing traditional data such as
texts, sounds, images and videos. More and more research works are carrying out to extend …

As a fundamental and critical task in various visual applications, image matching can identify
then correspond the same or similar structure/content from two or more images. Over the …

Geometric deep learning is an umbrella term for emerging techniques attempting to
generalize (structured) deep neural models to non-Euclidean domains, such as graphs and …

We present a simple, flexible, and general framework titled Partial Registration Network
(PRNet), for partial-to-partial point cloud registration. Inspired by recently-proposed learning …

Abstract We present Spline-based Convolutional Neural Networks (SplineCNNs), a variant
of deep neural networks for irregular structured and geometric input, eg, graphs or meshes …

We introduce a new general-purpose approach to deep learning on three-dimensional
surfaces based on the insight that a simple diffusion layer is highly effective for spatial …

Graph neural networks are increasingly becoming the go-to approach in various fields such
as computer vision, computational biology and chemistry, where data are naturally …

We present a new deep learning approach for matching deformable shapes by introducing
Shape Deformation Networks which jointly encode 3D shapes and correspondences. This is …