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 …

In this paper, we propose a transformer-based procedure for the efficient registration of non-
rigid 3D point clouds. The proposed approach is data-driven and adopts for the first time the …

In design for forming, it is becoming increasingly significant to develop surrogate models of
high-fidelity finite element analysis (FEA) simulations of forming processes to achieve …

We introduce a novel learning-based method to recover shapes from their Laplacian
spectra, based on establishing and exploring connections in a learned latent space. The …

Abstract We present SpecTrHuMS, a Spectral Transformer for 3D triangular Human Mesh
Sequence learning which combines known deep learning models with spectral mesh …

Abstract Machine learning models are known to be vulnerable to adversarial attacks, namely
perturbations of the data that lead to wrong predictions despite being imperceptible …

We consider the problem of human deformation transfer, where the goal is to retarget poses
between different characters. Traditional methods that tackle this problem assume a human …

A complete representation of 3D objects requires characterizing the space of deformations
in an interpretable manner, from articulations of a single instance to changes in shape …

A triangular mesh is one of the most popular 3D data representations. As such, the
deployment of deep neural networks for mesh processing is widely spread and is …

Estimating the similarity of non-rigid shapes and parts thereof plays an important role in
numerous geometry analysis applications. We propose a method for evaluating the similarity …