VariGrad: A Novel Feature Vector Architecture for Geometric Deep Learning on Unregistered Data

2023/07/07 by Emmanuel Hartman, Hartman, Emmanuel, Emery Pierson +1 · 1 citation
Computer Science · Engineering · #3D Shape Modeling and Analysis #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #I.4.0 #I.4.5 #I.5.1 #Image Processing and 3D Reconstruction #Optical measurement and interference techniques

paper · pdf · doi:10.48550/arxiv.2307.03553

openalex publication_date 2023/07/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We present a novel geometric deep learning layer that leverages the varifold gradient (VariGrad) to compute feature vector representations of 3D geometric data. These feature vectors can be used in a variety of downstream learning tasks such as classification, registration, and shape reconstruction. Our model's use of parameterization independent varifold representations of geometric data allows our model to be both trained and tested on data independent of the given sampling or parameterization. We demonstrate the efficiency, generalizability, and robustness to resampling demonstrated by the proposed VariGrad layer.

Cited by

• SVarM: Linear Support Varifold Machines for Classification and Regression on Geometric Data

Related

• SVarM: Linear Support Varifold Machines for Classification and Regression on Geometric Data
• Neural varifolds: an aggregate representation for quantifying the geometry of point clouds
• Toward Mesh-Invariant 3D Generative Deep Learning with Geometric Measures
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• Geometric Deep Learning: Going beyond Euclidean data