# AnyPose: Anytime 3D Human Pose Forecasting via Neural Ordinary Differential Equations

arXiv: https://arxiv.org/abs/2309.04840 · HTML: https://mlsanity.com/paper/2309.04840/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 48 references that are in the map.
- First posted on arXiv 9 Sep 2023.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Convolutional Sequence to Sequence Learning](https://mlsanity.com/paper/1705.03122/) (2017)
- [On human motion prediction using recurrent neural networks](https://mlsanity.com/paper/1705.02445/) (2017)
- [Learning Trajectory Dependencies for Human Motion Prediction](https://mlsanity.com/paper/1908.05436/) (2019)
- [How to train your neural ODE: the world of Jacobian and kinetic regularization](https://mlsanity.com/paper/2002.02798/) (2020)
- [Long-term Human Motion Prediction with Scene Context](https://mlsanity.com/paper/2007.03672/) (2020)
- [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)
- [Convolutional Sequence to Sequence Model for Human Dynamics](https://mlsanity.com/paper/1805.00655/) (2018)
- [Human Motion Prediction via Spatio-Temporal Inpainting](https://mlsanity.com/paper/1812.05478/) (2018)
- [Stochastic Latent Residual Video Prediction](https://mlsanity.com/paper/2002.09219/) (2020)
- [Deep representation learning for human motion prediction and classification](https://mlsanity.com/paper/1702.07486/) (2017)
- [The Pose Knows: Video Forecasting by Generating Pose Futures](https://mlsanity.com/paper/1705.00053/) (2017)
- [A Neural Temporal Model for Human Motion Prediction](https://mlsanity.com/paper/1809.03036/) (2018)
- [Space-Time-Separable Graph Convolutional Network for Pose Forecasting](https://mlsanity.com/paper/2110.04573/) (2021)
- [Learning to Encode Position for Transformer with Continuous Dynamical Model](https://mlsanity.com/paper/2003.09229/) (2020)
- [Pose Transformers (POTR): Human Motion Prediction with Non-Autoregressive Transformers](https://mlsanity.com/paper/2109.07531/) (2021)
- [Imitation Learning for Human Pose Prediction](https://mlsanity.com/paper/1909.03449/) (2019)
- [Vid-ODE: Continuous-Time Video Generation with Neural Ordinary Differential Equation](https://mlsanity.com/paper/2010.08188/) (2020)
- [Bio-LSTM: A Biomechanically Inspired Recurrent Neural Network for 3D Pedestrian Pose and Gait Prediction](https://mlsanity.com/paper/1809.03705/) (2018)
- [Object Handover Prediction using Gaussian Processes clustered with Trajectory Classification](https://mlsanity.com/paper/1707.02745/) (2017)

## Built on by (most cited first, 4 of 4)

- [VITA: Vision-to-Action Flow Matching Policy](https://mlsanity.com/paper/2507.13231/) (2025)
- [Wow, wo, val! A Comprehensive Embodied World Model Evaluation Turing Test](https://mlsanity.com/paper/2601.04137/) (2026)
- [Recent Advances in Deterministic Human Motion Prediction: A Review](https://mlsanity.com/paper/2312.06184/) (2023)
- [UPTor: Unified 3D Human Pose Dynamics and Trajectory Prediction for Human-Robot Interaction](https://mlsanity.com/paper/2505.14866/) (2025)

## Abstract (arXiv)

Anytime 3D human pose forecasting is crucial to synchronous real-world human-machine interaction, where the term ``anytime" corresponds to predicting human pose at any real-valued time step. However, to the best of our knowledge, all the existing methods in human pose forecasting perform predictions at preset, discrete time intervals. Therefore, we introduce AnyPose, a lightweight continuous-time neural architecture that models human behavior dynamics with neural ordinary differential equations. We validate our framework on the Human3.6M, AMASS, and 3DPW dataset and conduct a series of comprehensive analyses towards comparison with existing methods and the intersection of human pose and neural ordinary differential equations. Our results demonstrate that AnyPose exhibits high-performance accuracy in predicting future poses and takes significantly lower computational time than traditional methods in solving anytime prediction tasks.