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 …

Abstract We present Lepard, a Learning based approach for partial point cloud matching in
rigid and deformable scenes. The key characteristics are the following techniques that …

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 …

We present a novel learning-based approach for computing correspondences between non-
rigid 3D shapes. Unlike previous methods that either require extensive training data or …

Cycle consistency has long been exploited as a powerful prior for jointly optimizing maps
within a collection of shapes. In this paper, we investigate its utility in the approaches of …

Recurrent neural networks are widely used on time series data, yet such models often
ignore the underlying physical structures in such sequences. A new class of physics-based …

We consider the problem of computing dense correspondences between non-rigid shapes
with potentially significant partiality. Existing formulations tackle this problem through heavy …

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 this work, we present a novel non-rigid shape matching framework based on multi-
resolution functional maps with spectral attention. Existing functional map learning methods …

We present NeuroMorph, a new neural network architecture that takes as input two 3D
shapes and produces in one go, ie in a single feed forward pass, a smooth interpolation and …