MongeNet: Efficient Sampler for Geometric Deep Learning

04/29/2021
by   Leo Lebrat, et al.
10

Recent advances in geometric deep-learning introduce complex computational challenges for evaluating the distance between meshes. From a mesh model, point clouds are necessary along with a robust distance metric to assess surface quality or as part of the loss function for training models. Current methods often rely on a uniform random mesh discretization, which yields irregular sampling and noisy distance estimation. In this paper we introduce MongeNet, a fast and optimal transport based sampler that allows for an accurate discretization of a mesh with better approximation properties. We compare our method to the ubiquitous random uniform sampling and show that the approximation error is almost half with a very small computational overhead.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 2

page 7

page 8

10/11/2021

Mesh Draping: Parametrization-Free Neural Mesh Transfer

Despite recent advances in geometric modeling, 3D mesh modeling still in...
04/20/2021

Geometric Deep Learning on Anatomical Meshes for the Prediction of Alzheimer's Disease

Geometric deep learning can find representations that are optimal for a ...
03/19/2018

Low Rank Matrix Approximation for Geometry Filtering

We propose a robust, anisotropic normal estimation method for both point...
01/30/2019

DDSL: Deep Differentiable Simplex Layer for Learning Geometric Signals

We present a Deep Differentiable Simplex Layer (DDSL) for neural network...
07/09/2021

Beyond Farthest Point Sampling in Point-Wise Analysis

Sampling, grouping, and aggregation are three important components in th...
12/01/2020

DiffusionNet: Discretization Agnostic Learning on Surfaces

We introduce a new approach to deep learning on 3D surfaces, based on th...
05/15/2019

Geometric Losses for Distributional Learning

Building upon recent advances in entropy-regularized optimal transport, ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.