# DEMEA: Deep Mesh Autoencoders for Non-Rigidly Deforming Objects

arXiv: https://arxiv.org/abs/1905.10290 · HTML: https://mlsanity.com/paper/1905.10290/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 May 2019.

## Built on by (most cited first, 20 of 20)

- [ARAPReg: An As-Rigid-As Possible Regularization Loss for Learning Deformable Shape Generators](https://mlsanity.com/paper/2108.09432/) (2021)
- [State of the Art in Dense Monocular Non-Rigid 3D Reconstruction](https://mlsanity.com/paper/2210.15664/) (2022)
- [Learning Feature Aggregation for Deep 3D Morphable Models](https://mlsanity.com/paper/2105.02173/) (2021)
- [HandVoxNet++: 3D Hand Shape and Pose Estimation using Voxel-Based Neural Networks](https://mlsanity.com/paper/2107.01205/) (2021)
- [Deep Structural Causal Shape Models](https://mlsanity.com/paper/2208.10950/) (2022)
- [GenCorres: Consistent Shape Matching via Coupled Implicit-Explicit Shape Generative Models](https://mlsanity.com/paper/2304.10523/) (2023)
- [Diffusion Shape Prior for Wrinkle-Accurate Cloth Registration](https://mlsanity.com/paper/2311.05828/) (2023)
- [Neural Human Deformation Transfer](https://mlsanity.com/paper/2109.01588/) (2021)
- [LatentHuman: Shape-and-Pose Disentangled Latent Representation for Human Bodies](https://mlsanity.com/paper/2111.15113/) (2021)
- [Leveraging Intrinsic Properties for Non-Rigid Garment Alignment](https://mlsanity.com/paper/2308.09519/) (2023)
- [Neural Modes: Self-supervised Learning of Nonlinear Modal Subspaces](https://mlsanity.com/paper/2404.17620/) (2024)
- [3D-QAE: Fully Quantum Auto-Encoding of 3D Point Clouds](https://mlsanity.com/paper/2311.05604/) (2023)
- [Unsupervised Dense Deformation Embedding Network for Template-Free Shape Correspondence](https://mlsanity.com/paper/2108.11609/) (2021)
- [Animatable Virtual Humans: Learning pose-dependent human representations in UV space for interactive performance synthesis](https://mlsanity.com/paper/2310.03615/) (2023)
- [JADE: Joint-aware Latent Diffusion for 3D Human Generative Modeling](https://mlsanity.com/paper/2412.20470/) (2024)
- [Pop-Out Motion: 3D-Aware Image Deformation via Learning the Shape Laplacian](https://mlsanity.com/paper/2203.15235/) (2022)
- [Self-supervised learning of object pose estimation using keypoint prediction](https://mlsanity.com/paper/2302.07360/) (2023)
- [WrappingNet: Mesh Autoencoder via Deep Sphere Deformation](https://mlsanity.com/paper/2308.15413/) (2023)
- [Localized Shape Modelling with Global Coherence: An Inverse Spectral Approach](https://mlsanity.com/paper/2108.02161/) (2021)
- [Efficient 3D Reconstruction, Streaming and Visualization of Static and Dynamic Scene Parts for Multi-client Live-telepresence in Large-scale Environments](https://mlsanity.com/paper/2211.14310/) (2022)

## Abstract (arXiv)

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.