# Neural Human Deformation Transfer

arXiv: https://arxiv.org/abs/2109.01588 · HTML: https://mlsanity.com/paper/2109.01588/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 41 references that are in the map.
- First posted on arXiv 3 Sep 2021.

## Builds on (most cited first, 22 of 22)

- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Everybody Dance Now](https://mlsanity.com/paper/1808.07371/) (2018)
- [Few-Shot Adversarial Learning of Realistic Neural Talking Head Models](https://mlsanity.com/paper/1905.08233/) (2019)
- [Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis](https://mlsanity.com/paper/1806.04558/) (2018)
- [Generating 3D faces using Convolutional Mesh Autoencoders](https://mlsanity.com/paper/1807.10267/) (2018)
- [Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis](https://mlsanity.com/paper/1909.12224/) (2019)
- [A Variational U-Net for Conditional Appearance and Shape Generation](https://mlsanity.com/paper/1804.04694/) (2018)
- [Neural Voice Cloning with a Few Samples](https://mlsanity.com/paper/1802.06006/) (2018)
- [Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and Generation](https://mlsanity.com/paper/1905.02876/) (2019)
- [Neural Kinematic Networks for Unsupervised Motion Retargetting](https://mlsanity.com/paper/1804.05653/) (2018)
- [Variational Autoencoders for Deforming 3D Mesh Models](https://mlsanity.com/paper/1709.04307/) (2017)
- [Unsupervised Shape and Pose Disentanglement for 3D Meshes](https://mlsanity.com/paper/2007.11341/) (2020)
- [3DN: 3D Deformation Network](https://mlsanity.com/paper/1903.03322/) (2019)
- [LIMP: Learning Latent Shape Representations with Metric Preservation Priors](https://mlsanity.com/paper/2003.12283/) (2020)
- [Neural Pose Transfer by Spatially Adaptive Instance Normalization](https://mlsanity.com/paper/2003.07254/) (2020)
- [High-Fidelity Neural Human Motion Transfer from Monocular Video](https://mlsanity.com/paper/2012.10974/) (2020)
- [Geometric Disentanglement for Generative Latent Shape Models](https://mlsanity.com/paper/1908.06386/) (2019)
- [Disentangled Human Body Embedding Based on Deep Hierarchical Neural Network](https://mlsanity.com/paper/1905.05622/) (2019)
- [DEMEA: Deep Mesh Autoencoders for Non-Rigidly Deforming Objects](https://mlsanity.com/paper/1905.10290/) (2019)
- [Isospectralization, or how to hear shape, style, and correspondence](https://mlsanity.com/paper/1811.11465/) (2018)
- [Instant recovery of shape from spectrum via latent space connections](https://mlsanity.com/paper/2003.06523/) (2020)
- [Disentangling Geometric Deformation Spaces in Generative Latent Shape Models](https://mlsanity.com/paper/2103.00142/) (2021)

## Built on by (most cited first, 6 of 6)

- [BaRe-ESA: A Riemannian Framework for Unregistered Human Body Shapes](https://mlsanity.com/paper/2211.13185/) (2022)
- [Correspondence-free online human motion retargeting](https://mlsanity.com/paper/2302.00556/) (2023)
- [Deformation-Guided Unsupervised Non-Rigid Shape Matching](https://mlsanity.com/paper/2311.15668/) (2023)
- [MAPConNet: Self-supervised 3D Pose Transfer with Mesh and Point Contrastive Learning](https://mlsanity.com/paper/2304.13819/) (2023)
- [Matching Shapes Under Different Topologies: A Topology-Adaptive Deformation Guided Approach](https://mlsanity.com/paper/2509.06862/) (2025)
- [LatentReRig: An SDF-Based VAE with Dual Decoders for Latent-Space Deformation Conditioning](https://mlsanity.com/paper/2609.31720/) (2026)

## Abstract (arXiv)

We consider the problem of human deformation transfer, where the goal is to retarget poses between different characters. Traditional methods that tackle this problem require a clear definition of the pose, and use this definition to transfer poses between characters. In this work, we take a different approach and transform the identity of a character into a new identity without modifying the character's pose. This offers the advantage of not having to define equivalences between 3D human poses, which is not straightforward as poses tend to change depending on the identity of the character performing them, and as their meaning is highly contextual. To achieve the deformation transfer, we propose a neural encoder-decoder architecture where only identity information is encoded and where the decoder is conditioned on the pose. We use pose independent representations, such as isometry-invariant shape characteristics, to represent identity features. Our model uses these features to supervise the prediction of offsets from the deformed pose to the result of the transfer. We show experimentally that our method outperforms state-of-the-art methods both quantitatively and qualitatively, and generalises better to poses not seen during training. We also introduce a fine-tuning step that allows to obtain competitive results for extreme identities, and allows to transfer simple clothing.