MeshODE: A Robust and Scalable Framework for Mesh Deformation

by   Jingwei Huang, et al.

We present MeshODE, a scalable and robust framework for pairwise CAD model deformation without prespecified correspondences. Given a pair of shapes, our framework provides a novel shape feature-preserving mapping function that continuously deforms one model to the other by minimizing fitting and rigidity losses based on the non-rigid iterative-closest-point (ICP) algorithm. We address two challenges in this problem, namely the design of a powerful deformation function and obtaining a feature-preserving CAD deformation. While traditional deformation directly optimizes for the coordinates of the mesh vertices or the vertices of a control cage, we introduce a deep bijective mapping that utilizes a flow model parameterized as a neural network. Our function has the capacity to handle complex deformations, produces deformations that are guaranteed free of self-intersections, and requires low rigidity constraining for geometry preservation, which leads to a better fitting quality compared with existing methods. It additionally enables continuous deformation between two arbitrary shapes without supervision for intermediate shapes. Furthermore, we propose a robust preprocessing pipeline for raw CAD meshes using feature-aware subdivision and a uniform graph template representation to address artifacts in raw CAD models including self-intersections, irregular triangles, topologically disconnected components, non-manifold edges, and nonuniformly distributed vertices. This facilitates a fast deformation optimization process that preserves global and local details. Our code is publicly available.



There are no comments yet.


page 8

page 11

page 15

page 16

page 17

page 18

page 19

page 20


Quasi-structured quadrilateral meshing in Gmsh – a robust pipeline for complex CAD models

We propose an end-to-end pipeline to robustly generate high-quality quad...

Unsupervised Dense Deformation Embedding Network for Template-Free Shape Correspondence

Shape correspondence from 3D deformation learning has attracted appealin...

Neural Cages for Detail-Preserving 3D Deformations

We propose a novel learnable representation for detail-preserving shape ...

DeepMLS: Geometry-Aware Control Point Deformation

We introduce DeepMLS, a space-based deformation technique, guided by a s...

DeepMetaHandles: Learning Deformation Meta-Handles of 3D Meshes with Biharmonic Coordinates

We propose DeepMetaHandles, a 3D conditional generative model based on m...

Modeling and Optimization with Gaussian Processes in Reduced Eigenbases – Extended Version

Parametric shape optimization aims at minimizing an objective function f...

Multiscale Mesh Deformation Component Analysis with Attention-based Autoencoders

Deformation component analysis is a fundamental problem in geometry proc...
This week in AI

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