DA Wand: Distortion-Aware Selection using Neural Mesh Parameterization

TL;DR

This paper introduces DA Wand, a neural method that learns to select low-distortion mesh regions for parameterization, enhancing interactive surface editing workflows.

Contribution

It presents a novel differentiable parameterization layer that incorporates segmentation probabilities to produce distortion-aware mesh regions.

Findings

Effective in selecting meaningful low-distortion regions

Improves interactive mesh editing workflows

Code and system are publicly available

Abstract

We present a neural technique for learning to select a local sub-region around a point which can be used for mesh parameterization. The motivation for our framework is driven by interactive workflows used for decaling, texturing, or painting on surfaces. Our key idea is to incorporate segmentation probabilities as weights of a classical parameterization method, implemented as a novel differentiable parameterization layer within a neural network framework. We train a segmentation network to select 3D regions that are parameterized into 2D and penalized by the resulting distortion, giving rise to segmentations which are distortion-aware. Following training, a user can use our system to interactively select a point on the mesh and obtain a large, meaningful region around the selection which induces a low-distortion parameterization. Our code and project page are currently available.