English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We present MeshODE, a scalable and robust framework for pairwise CAD modeldeformation without prespecified correspondences. Given a pair of shapes, ourframework provides a novel shape feature-preserving mapping function thatcontinuously deforms one model to the other by minimizing fitting and rigiditylosses based on the non-rigid iterative-closest-point (ICP) algorithm. Weaddress two challenges in this problem, namely the design of a powerfuldeformation function and obtaining a feature-preserving CAD deformation. Whiletraditional deformation directly optimizes for the coordinates of the meshvertices or the vertices of a control cage, we introduce a deep bijectivemapping that utilizes a flow model parameterized as a neural network. Ourfunction has the capacity to handle complex deformations, produces deformationsthat are guaranteed free of self-intersections, and requires low rigidityconstraining for geometry preservation, which leads to a better fitting qualitycompared with existing methods. It additionally enables continuous deformationbetween two arbitrary shapes without supervision for intermediate shapes.Furthermore, we propose a robust preprocessing pipeline for raw CAD meshesusing feature-aware subdivision and a uniform graph template representation toaddress artifacts in raw CAD models including self-intersections, irregulartriangles, topologically disconnected components, non-manifold edges, andnonuniformly distributed vertices. This facilitates a fast deformationoptimization process that preserves global and local details. Our code ispublicly available.

MeshODE: A Robust and Scalable Framework for Mesh Deformation