# Motion Diffusion Autoencoders: Enabling Attribute Manipulation in Human Motion Demonstrated on Karate Techniques

arXiv: https://arxiv.org/abs/2501.18729 · HTML: https://mlsanity.com/paper/2501.18729/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 39 references that are in the map.
- First posted on arXiv 30 Jan 2025.

## Builds on (most cited first, 20 of 20)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Diffusion Autoencoders: Toward a Meaningful and Decodable Representation](https://mlsanity.com/paper/2111.15640/) (2021)
- [Action2Motion: Conditioned Generation of 3D Human Motions](https://mlsanity.com/paper/2007.15240/) (2020)
- [The KIT Motion-Language Dataset](https://mlsanity.com/paper/1607.03827/) (2016)
- [Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset](https://mlsanity.com/paper/2307.00818/) (2023)
- [Learning to Estimate 3D Human Pose and Shape from a Single Color Image](https://mlsanity.com/paper/1805.04092/) (2018)
- [StableVideo: Text-driven Consistency-aware Diffusion Video Editing](https://mlsanity.com/paper/2308.09592/) (2023)
- [CCEdit: Creative and Controllable Video Editing via Diffusion Models](https://mlsanity.com/paper/2309.16496/) (2023)
- [Learning Residual Images for Face Attribute Manipulation](https://mlsanity.com/paper/1612.05363/) (2016)
- [Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding](https://mlsanity.com/paper/2212.02802/) (2022)
- [MotioNet: 3D Human Motion Reconstruction from Monocular Video with Skeleton Consistency](https://mlsanity.com/paper/2006.12075/) (2020)
- [Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction](https://mlsanity.com/paper/2112.15012/) (2021)
- [Space-Time Representation of People Based on 3D Skeletal Data: A Review](https://mlsanity.com/paper/1601.01006/) (2016)
- [Direct Inversion: Optimization-Free Text-Driven Real Image Editing with Diffusion Models](https://mlsanity.com/paper/2211.07825/) (2022)
- [A Large-scale Varying-view RGB-D Action Dataset for Arbitrary-view Human Action Recognition](https://mlsanity.com/paper/1904.10681/) (2019)

## Built on by (most cited first, 2 of 2)

- [ExpertEdit: Learning Skill-Aware Motion Editing from Expert Videos](https://mlsanity.com/paper/2604.10466/) (2026)
- [Schr"odinger's Cat: Probabilistic Representation and Prediction of Potential Scene Kinematics](https://mlsanity.com/paper/2607.25984/) (2026)

## Abstract (arXiv)

Attribute manipulation deals with the problem of changing individual attributes of a data point or a time series, while leaving all other aspects unaffected. This work focuses on the domain of human motion, more precisely karate movement patterns. To the best of our knowledge, it presents the first success at manipulating attributes of human motion data. One of the key requirements for achieving attribute manipulation on human motion is a suitable pose representation. Therefore, we design a novel continuous, rotation-based pose representation that enables the disentanglement of the human skeleton and the motion trajectory, while still allowing an accurate reconstruction of the original anatomy. The core idea of the manipulation approach is to use a transformer encoder for discovering high-level semantics, and a diffusion probabilistic model for modeling the remaining stochastic variations. We show that the embedding space obtained from the transformer encoder is semantically meaningful and linear. This enables the manipulation of high-level attributes, by discovering their linear direction of change in the semantic embedding space and moving the embedding along said direction. All code and data is made publicly available.