Saved in:
Bibliographic Details
Main Authors: Fayolle, Pierre-Alain, Maltsev, Evgenii
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.14216
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909585631084544
author Fayolle, Pierre-Alain
Maltsev, Evgenii
author_facet Fayolle, Pierre-Alain
Maltsev, Evgenii
contents We propose a framework for performing differentiable geometric modeling based on the Function Representation (FRep). The framework is built on top of modern libraries for performing automatic differentiation allowing us to obtain derivatives w.r.t. space or shape parameters. We demonstrate possible applications of this framework: Curvature estimation for shape interrogation, signed distance function computation and approximation and fitting shape parameters of a parametric model to data. Our framework is released as open-source.
format Preprint
id arxiv_https___arxiv_org_abs_2504_14216
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PyFRep: Shape Modeling with Differentiable Function Representation
Fayolle, Pierre-Alain
Maltsev, Evgenii
Graphics
We propose a framework for performing differentiable geometric modeling based on the Function Representation (FRep). The framework is built on top of modern libraries for performing automatic differentiation allowing us to obtain derivatives w.r.t. space or shape parameters. We demonstrate possible applications of this framework: Curvature estimation for shape interrogation, signed distance function computation and approximation and fitting shape parameters of a parametric model to data. Our framework is released as open-source.
title PyFRep: Shape Modeling with Differentiable Function Representation
topic Graphics
url https://arxiv.org/abs/2504.14216