Learning and Meshing from Deep Implicit Surface Networks Using an Efficient Implementation of Analytic Marching

06/18/2021
by   Jiabao Lei, et al.
11

Reconstruction of object or scene surfaces has tremendous applications in computer vision, computer graphics, and robotics. In this paper, we study a fundamental problem in this context about recovering a surface mesh from an implicit field function whose zero-level set captures the underlying surface. To achieve the goal, existing methods rely on traditional meshing algorithms; while promising, they suffer from loss of precision learned in the implicit surface networks, due to the use of discrete space sampling in marching cubes. Given that an MLP with activations of Rectified Linear Unit (ReLU) partitions its input space into a number of linear regions, we are motivated to connect this local linearity with a same property owned by the desired result of polygon mesh. More specifically, we identify from the linear regions, partitioned by an MLP based implicit function, the analytic cells and analytic faces that are associated with the function's zero-level isosurface. We prove that under mild conditions, the identified analytic faces are guaranteed to connect and form a closed, piecewise planar surface. Based on the theorem, we propose an algorithm of analytic marching, which marches among analytic cells to exactly recover the mesh captured by an implicit surface network. We also show that our theory and algorithm are equally applicable to advanced MLPs with shortcut connections and max pooling. Given the parallel nature of analytic marching, we contribute AnalyticMesh, a software package that supports efficient meshing of implicit surface networks via CUDA parallel computing, and mesh simplification for efficient downstream processing. We apply our method to different settings of generative shape modeling using implicit surface networks. Extensive experiments demonstrate our advantages over existing methods in terms of both meshing accuracy and efficiency.

READ FULL TEXT

page 4

page 9

page 14

page 15

page 17

page 19

page 20

research
02/16/2020

Analytic Marching: An Analytic Meshing Solution from Deep Implicit Surface Networks

This paper studies a problem of learning surface mesh via implicit funct...
research
10/05/2022

NeuralMeshing: Differentiable Meshing of Implicit Neural Representations

The generation of triangle meshes from point clouds, i.e. meshing, is a ...
research
04/16/2021

Signed Distance Function Computation from an Implicit Surface

We describe in this short note a technique to convert an implicit surfac...
research
04/14/2022

A Level Set Theory for Neural Implicit Evolution under Explicit Flows

Coordinate-based neural networks parameterizing implicit surfaces have e...
research
05/08/2021

Sign-Agnostic CONet: Learning Implicit Surface Reconstructions by Sign-Agnostic Optimization of Convolutional Occupancy Networks

Surface reconstruction from point clouds is a fundamental problem in the...
research
09/16/2023

Surface Extraction from Neural Unsigned Distance Fields

We propose a method, named DualMesh-UDF, to extract a surface from unsig...
research
06/09/2016

Implicit Tubular Surface Generation Guided by Centerline

Most machine learning-based coronary artery segmentation methods represe...

Please sign up or login with your details

Forgot password? Click here to reset