# Learning Disentangled Representations for Controllable Human Motion Prediction

arXiv: https://arxiv.org/abs/2207.01388 · HTML: https://mlsanity.com/paper/2207.01388/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 58 references that are in the map.
- First posted on arXiv 4 Jul 2022.

## Builds on (most cited first, 30 of 39)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [On human motion prediction using recurrent neural networks](https://mlsanity.com/paper/1705.02445/) (2017)
- [AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting](https://mlsanity.com/paper/2103.14023/) (2021)
- [A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehicles](https://mlsanity.com/paper/1604.07446/) (2016)
- [Learning Trajectory Dependencies for Human Motion Prediction](https://mlsanity.com/paper/1908.05436/) (2019)
- [Neural Autoregressive Flows](https://mlsanity.com/paper/1804.00779/) (2018)
- [Stochastic Scene-Aware Motion Prediction](https://mlsanity.com/paper/2108.08284/) (2021)
- [Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction](https://mlsanity.com/paper/2003.01460/) (2020)
- [DLow: Diversifying Latent Flows for Diverse Human Motion Prediction](https://mlsanity.com/paper/2003.08386/) (2020)
- [HP-GAN: Probabilistic 3D human motion prediction via GAN](https://mlsanity.com/paper/1711.09561/) (2017)
- [History Repeats Itself: Human Motion Prediction via Motion Attention](https://mlsanity.com/paper/2007.11755/) (2020)
- [A Spatio-temporal Transformer for 3D Human Motion Prediction](https://mlsanity.com/paper/2004.08692/) (2020)
- [Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction](https://mlsanity.com/paper/2003.08802/) (2020)
- [Convolutional Sequence to Sequence Model for Human Dynamics](https://mlsanity.com/paper/1805.00655/) (2018)
- [We are More than Our Joints: Predicting how 3D Bodies Move](https://mlsanity.com/paper/2012.00619/) (2020)
- [Unsupervised Learning of Object Landmarks through Conditional Image Generation](https://mlsanity.com/paper/1806.07823/) (2018)
- [MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction](https://mlsanity.com/paper/2108.07152/) (2021)
- [LookOut: Diverse Multi-Future Prediction and Planning for Self-Driving](https://mlsanity.com/paper/2101.06547/) (2021)
- [MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics](https://mlsanity.com/paper/1808.04545/) (2018)
- [Diverse Trajectory Forecasting with Determinantal Point Processes](https://mlsanity.com/paper/1907.04967/) (2019)
- [Generating Smooth Pose Sequences for Diverse Human Motion Prediction](https://mlsanity.com/paper/2108.08422/) (2021)
- [Accurate and Diverse Sampling of Sequences based on a "Best of Many" Sample Objective](https://mlsanity.com/paper/1806.07772/) (2018)
- [MoGlow: Probabilistic and controllable motion synthesis using normalising flows](https://mlsanity.com/paper/1905.06598/) (2019)
- [Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitions](https://mlsanity.com/paper/1912.10150/) (2019)
- [Pose Transformers (POTR): Human Motion Prediction with Non-Autoregressive Transformers](https://mlsanity.com/paper/2109.07531/) (2021)
- [Multi-level Motion Attention for Human Motion Prediction](https://mlsanity.com/paper/2106.09300/) (2021)
- [Hierarchical Style-based Networks for Motion Synthesis](https://mlsanity.com/paper/2008.10162/) (2020)

## Built on by (most cited first, 5 of 5)

- [BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction](https://mlsanity.com/paper/2211.14304/) (2022)
- [Learning Semantic Latent Directions for Accurate and Controllable Human Motion Prediction](https://mlsanity.com/paper/2407.11494/) (2024)
- [Orientation-Aware Leg Movement Learning for Action-Driven Human Motion Prediction](https://mlsanity.com/paper/2310.14907/) (2023)
- [Disentanglement with Factor Quantized Variational Autoencoders](https://mlsanity.com/paper/2409.14851/) (2024)
- [BeatDance: Generating Beat-Consistent 3D Dance with Hierarchical Spatial-Temporal Modeling](https://mlsanity.com/paper/2609.37400/) (2026)

## Abstract (arXiv)

Generative model-based motion prediction techniques have recently realized predicting controlled human motions, such as predicting multiple upper human body motions with similar lower-body motions. However, to achieve this, the state-of-the-art methods require either subsequently learning mapping functions to seek similar motions or training the model repetitively to enable control over the desired portion of body. In this paper, we propose a novel framework to learn disentangled representations for controllable human motion prediction. Our network involves a conditional variational auto-encoder (CVAE) architecture to model full-body human motion, and an extra CVAE path to learn only the corresponding partial-body (e.g., lower-body) motion. Specifically, the inductive bias imposed by the extra CVAE path encourages two latent variables in two paths to respectively govern separate representations for each partial-body motion. With a single training, our model is able to provide two types of controls for the generated human motions: (i) strictly controlling one portion of human body and (ii) adaptively controlling the other portion, by sampling from a pair of latent spaces. Additionally, we extend and adapt a sampling strategy to our trained model to diversify the controllable predictions. Our framework also potentially allows new forms of control by flexibly customizing the input for the extra CVAE path. Extensive experimental results and ablation studies demonstrate that our approach is capable of predicting state-of-the-art controllable human motions both qualitatively and quantitatively.