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

TL;DR

This paper introduces a handle-guided neural field deformation method using local patch meshing, improving quality, robustness, and efficiency in 3D shape manipulation by bridging classical geometry and neural representations.

Contribution

It proposes a novel local patch mesh representation for neural field deformation, enhancing control and scalability over existing neural deformation techniques.

Findings

Outperforms baselines in deformation quality and robustness

Achieves higher computational efficiency in neural field manipulation

Demonstrates effective discretization over marching cubes

Abstract

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.