Neural Cages for Detail-Preserving 3D Deformations

TL;DR

This paper introduces a neural network-based method that uses a learnable cage representation to achieve detail-preserving 3D shape deformations, enabling structure matching while maintaining surface details.

Contribution

It presents a novel neural architecture that predicts cage deformations for shape matching, extending traditional cage-based methods with end-to-end training and unsupervised learning.

Findings

Effective preservation of surface details during deformation

Able to synthesize shape variations and transfer deformations

Operates without cage-specific annotations

Abstract

We propose a novel learnable representation for detail-preserving shape deformation. The goal of our method is to warp a source shape to match the general structure of a target shape, while preserving the surface details of the source. Our method extends a traditional cage-based deformation technique, where the source shape is enclosed by a coarse control mesh termed \emph{cage}, and translations prescribed on the cage vertices are interpolated to any point on the source mesh via special weight functions. The use of this sparse cage scaffolding enables preserving surface details regardless of the shape's intricacy and topology. Our key contribution is a novel neural network architecture for predicting deformations by controlling the cage. We incorporate a differentiable cage-based deformation module in our architecture, and train our network end-to-end. Our method can be trained with common collections of 3D models in an unsupervised fashion, without any cage-specific annotations. We demonstrate the utility of our method for synthesizing shape variations and deformation transfer.