DEMEA: Deep Mesh Autoencoders for Non-Rigidly Deforming Objects
This work addresses the challenge of non-rigid deformation modeling in computer vision and graphics, offering a novel method for applications like 3D reconstruction and surface tracking.
The paper tackles the problem of modeling non-rigidly deforming objects in 3D by proposing DEMEA, a deep mesh autoencoder with an embedded deformation layer, which achieves higher-quality results for highly deformable objects compared to direct vertex regression.
Mesh autoencoders are commonly used for dimensionality reduction, sampling and mesh modeling. We propose a general-purpose DEep MEsh Autoencoder (DEMEA) which adds a novel embedded deformation layer to a graph-convolutional mesh autoencoder. The embedded deformation layer (EDL) is a differentiable deformable geometric proxy which explicitly models point displacements of non-rigid deformations in a lower dimensional space and serves as a local rigidity regularizer. DEMEA decouples the parameterization of the deformation from the final mesh resolution since the deformation is defined over a lower dimensional embedded deformation graph. We perform a large-scale study on four different datasets of deformable objects. Reasoning about the local rigidity of meshes using EDL allows us to achieve higher-quality results for highly deformable objects, compared to directly regressing vertex positions. We demonstrate multiple applications of DEMEA, including non-rigid 3D reconstruction from depth and shading cues, non-rigid surface tracking, as well as the transfer of deformations over different meshes.