Implicit-ARAP: Efficient Handle-Guided Neural Field Deformation via Local Patch Meshing

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Baieri, Daniele, Maggioli, Filippo, Rodolà, Emanuele, Melzi, Simone, Lähner, Zorah
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914062977204224
author Baieri, Daniele
Maggioli, Filippo
Rodolà, Emanuele
Melzi, Simone
Lähner, Zorah
author_facet Baieri, Daniele
Maggioli, Filippo
Rodolà, Emanuele
Melzi, Simone
Lähner, Zorah
contents Neural fields have emerged as a powerful representation for 3D geometry, enabling compact and continuous modeling of complex shapes. Despite their expressive power, manipulating neural fields in a controlled and accurate manner -- particularly under spatial constraints -- remains an open challenge, as existing approaches struggle to balance surface quality, robustness, and efficiency. We address this by introducing a novel method for handle-guided neural field deformation, which leverages discrete local surface representations to optimize the As-Rigid-As-Possible deformation energy. To this end, we propose the local patch mesh representation, which discretizes level sets of a neural signed distance field by projecting and deforming flat mesh patches guided solely by the SDF and its gradient. We conduct a comprehensive evaluation showing that our method consistently outperforms baselines in deformation quality, robustness, and computational efficiency. We also present experiments that motivate our choice of discretization over marching cubes. By bridging classical geometry processing and neural representations through local patch meshing, our work enables scalable, high-quality deformation of neural fields and paves the way for extending other geometric tasks to neural domains.
format Preprint
id arxiv_https___arxiv_org_abs_2405_12895
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Implicit-ARAP: Efficient Handle-Guided Neural Field Deformation via Local Patch Meshing
Baieri, Daniele
Maggioli, Filippo
Rodolà, Emanuele
Melzi, Simone
Lähner, Zorah
Graphics
Computer Vision and Pattern Recognition
68U05
I.3.5; I.2.6
Neural fields have emerged as a powerful representation for 3D geometry, enabling compact and continuous modeling of complex shapes. Despite their expressive power, manipulating neural fields in a controlled and accurate manner -- particularly under spatial constraints -- remains an open challenge, as existing approaches struggle to balance surface quality, robustness, and efficiency. We address this by introducing a novel method for handle-guided neural field deformation, which leverages discrete local surface representations to optimize the As-Rigid-As-Possible deformation energy. To this end, we propose the local patch mesh representation, which discretizes level sets of a neural signed distance field by projecting and deforming flat mesh patches guided solely by the SDF and its gradient. We conduct a comprehensive evaluation showing that our method consistently outperforms baselines in deformation quality, robustness, and computational efficiency. We also present experiments that motivate our choice of discretization over marching cubes. By bridging classical geometry processing and neural representations through local patch meshing, our work enables scalable, high-quality deformation of neural fields and paves the way for extending other geometric tasks to neural domains.
title Implicit-ARAP: Efficient Handle-Guided Neural Field Deformation via Local Patch Meshing
topic Graphics
Computer Vision and Pattern Recognition
68U05
I.3.5; I.2.6
url https://arxiv.org/abs/2405.12895