# Fully Convolutional Mesh Autoencoder using Efficient Spatially Varying Kernels

arXiv: https://arxiv.org/abs/2006.04325 · HTML: https://mlsanity.com/paper/2006.04325/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jun 2020.

## Built on by (most cited first, 30 of 53)

- [Driving-Signal Aware Full-Body Avatars](https://mlsanity.com/paper/2105.10441/) (2021)
- [A graph convolutional autoencoder approach to model order reduction for parametrized PDEs](https://mlsanity.com/paper/2305.08573/) (2023)
- [ARAPReg: An As-Rigid-As Possible Regularization Loss for Learning Deformable Shape Generators](https://mlsanity.com/paper/2108.09432/) (2021)
- [Accurate Point Cloud Registration with Robust Optimal Transport](https://mlsanity.com/paper/2111.00648/) (2021)
- [Absolute Coordinates Make Motion Generation Easy](https://mlsanity.com/paper/2505.19377/) (2025)
- [Generalised Latent Assimilation in Heterogeneous Reduced Spaces with Machine Learning Surrogate Models](https://mlsanity.com/paper/2204.03497/) (2022)
- [Neural Face Rigging for Animating and Retargeting Facial Meshes in the Wild](https://mlsanity.com/paper/2305.08296/) (2023)
- [Deep 3D-to-2D Watermarking: Embedding Messages in 3D Meshes and Extracting Them from 2D Renderings](https://mlsanity.com/paper/2104.13450/) (2021)
- [RaBit: Parametric Modeling of 3D Biped Cartoon Characters with a Topological-consistent Dataset](https://mlsanity.com/paper/2303.12564/) (2023)
- [3D Shape Variational Autoencoder Latent Disentanglement via Mini-Batch Feature Swapping for Bodies and Faces](https://mlsanity.com/paper/2111.12448/) (2021)
- [Efficient deep data assimilation with sparse observations and time-varying sensors](https://mlsanity.com/paper/2310.16187/) (2023)
- [MEGA: Masked Generative Autoencoder for Human Mesh Recovery](https://mlsanity.com/paper/2405.18839/) (2024)
- [Learning Feature Aggregation for Deep 3D Morphable Models](https://mlsanity.com/paper/2105.02173/) (2021)
- [VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Space](https://mlsanity.com/paper/2312.08291/) (2023)
- [Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation](https://mlsanity.com/paper/2509.12815/) (2025)
- [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)
- [DMesh++: An Efficient Differentiable Mesh for Complex Shapes](https://mlsanity.com/paper/2412.16776/) (2024)
- [3D Shapes Local Geometry Codes Learning with SDF](https://mlsanity.com/paper/2108.08593/) (2021)
- [Geometry-Contrastive Transformer for Generalized 3D Pose Transfer](https://mlsanity.com/paper/2112.07374/) (2021)
- [SNAKE: Shape-aware Neural 3D Keypoint Field](https://mlsanity.com/paper/2206.01724/) (2022)
- [What's the Situation with Intelligent Mesh Generation: A Survey and Perspectives](https://mlsanity.com/paper/2211.06009/) (2022)
- [DMesh: A Differentiable Mesh Representation](https://mlsanity.com/paper/2404.13445/) (2024)
- [A Survey on Computational Solutions for Reconstructing Complete Objects by Reassembling Their Fractured Parts](https://mlsanity.com/paper/2410.14770/) (2024)
- [Diffusion Shape Prior for Wrinkle-Accurate Cloth Registration](https://mlsanity.com/paper/2311.05828/) (2023)
- [Auto-Regressive Surface Cutting](https://mlsanity.com/paper/2506.18017/) (2025)
- [A Repulsive Force Unit for Garment Collision Handling in Neural Networks](https://mlsanity.com/paper/2207.13871/) (2022)
- [Primitive-based 3D Human-Object Interaction Modelling and Programming](https://mlsanity.com/paper/2312.10714/) (2023)
- [Garment Avatars: Realistic Cloth Driving using Pattern Registration](https://mlsanity.com/paper/2206.03373/) (2022)
- [3D Generative Model Latent Disentanglement via Local Eigenprojection](https://mlsanity.com/paper/2302.12798/) (2023)

## Abstract (arXiv)

Learning latent representations of registered meshes is useful for many 3D tasks. Techniques have recently shifted to neural mesh autoencoders. Although they demonstrate higher precision than traditional methods, they remain unable to capture fine-grained deformations. Furthermore, these methods can only be applied to a template-specific surface mesh, and is not applicable to more general meshes, like tetrahedrons and non-manifold meshes. While more general graph convolution methods can be employed, they lack performance in reconstruction precision and require higher memory usage. In this paper, we propose a non-template-specific fully convolutional mesh autoencoder for arbitrary registered mesh data. It is enabled by our novel convolution and (un)pooling operators learned with globally shared weights and locally varying coefficients which can efficiently capture the spatially varying contents presented by irregular mesh connections. Our model outperforms state-of-the-art methods on reconstruction accuracy. In addition, the latent codes of our network are fully localized thanks to the fully convolutional structure, and thus have much higher interpolation capability than many traditional 3D mesh generation models.