# Multiscale Mesh Deformation Component Analysis with Attention-based Autoencoders

arXiv: https://arxiv.org/abs/2012.02459 · HTML: https://mlsanity.com/paper/2012.02459/

## Key facts

- Cited by 7 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 4 Dec 2020.

## Built on by (most cited first, 7 of 7)

- [NeRF-Editing: Geometry Editing of Neural Radiance Fields](https://mlsanity.com/paper/2205.04978/) (2022)
- [Skeleton-free Pose Transfer for Stylized 3D Characters](https://mlsanity.com/paper/2208.00790/) (2022)
- [TapMo: Shape-aware Motion Generation of Skeleton-free Characters](https://mlsanity.com/paper/2310.12678/) (2023)
- [AttWalk: Attentive Cross-Walks for Deep Mesh Analysis](https://mlsanity.com/paper/2104.11571/) (2021)
- [Active Learning of Neural Collision Handler for Complex 3D Mesh Deformations](https://mlsanity.com/paper/2110.07727/) (2021)
- [HMC: Hierarchical Mesh Coarsening for Skeleton-free Motion Retargeting](https://mlsanity.com/paper/2303.10941/) (2023)
- [Unsupervised Representation Learning for Diverse Deformable Shape Collections](https://mlsanity.com/paper/2310.18141/) (2023)

## Abstract (arXiv)

Deformation component analysis is a fundamental problem in geometry processing and shape understanding. Existing approaches mainly extract deformation components in local regions at a similar scale while deformations of real-world objects are usually distributed in a multi-scale manner. In this paper, we propose a novel method to exact multiscale deformation components automatically with a stacked attention-based autoencoder. The attention mechanism is designed to learn to softly weight multi-scale deformation components in active deformation regions, and the stacked attention-based autoencoder is learned to represent the deformation components at different scales. Quantitative and qualitative evaluations show that our method outperforms state-of-the-art methods. Furthermore, with the multiscale deformation components extracted by our method, the user can edit shapes in a coarse-to-fine fashion which facilitates effective modeling of new shapes.