DA Wand: Distortion-Aware Selection using Neural Mesh Parameterization
This addresses the need for efficient and low-distortion mesh parameterization in interactive graphics applications, representing an incremental improvement over classical methods.
The paper tackles the problem of selecting low-distortion local regions on 3D meshes for parameterization in interactive workflows like texturing, by introducing a neural method that trains a segmentation network to minimize distortion, resulting in meaningful regions with reduced distortion.
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.