DeepMetaHandles: Learning Deformation Meta-Handles of 3D Meshes with Biharmonic Coordinates

TL;DR

DeepMetaHandles introduces a novel 3D mesh deformation model that learns interpretable, disentangled meta-handles representing plausible deformations, enabling controllable and smooth shape variations using biharmonic coordinates.

Contribution

The paper presents a new method for learning deformation meta-handles of 3D meshes, combining biharmonic coordinates with a generative model for interpretable and plausible shape deformations.

Findings

Meta-handles effectively factorize shape deformations.

Generated deformations are smooth and plausible.

Meta-handles are interpretable and consistent across shapes.

Abstract

We propose DeepMetaHandles, a 3D conditional generative model based on mesh deformation. Given a collection of 3D meshes of a category and their deformation handles (control points), our method learns a set of meta-handles for each shape, which are represented as combinations of the given handles. The disentangled meta-handles factorize all the plausible deformations of the shape, while each of them corresponds to an intuitive deformation. A new deformation can then be generated by sampling the coefficients of the meta-handles in a specific range. We employ biharmonic coordinates as the deformation function, which can smoothly propagate the control points' translations to the entire mesh. To avoid learning zero deformation as meta-handles, we incorporate a target-fitting module which deforms the input mesh to match a random target. To enhance deformations' plausibility, we employ a soft-rasterizer-based discriminator that projects the meshes to a 2D space. Our experiments demonstrate the superiority of the generated deformations as well as the interpretability and consistency of the learned meta-handles.