# Human Joint Kinematics Diffusion-Refinement for Stochastic Motion Prediction

arXiv: https://arxiv.org/abs/2210.05976 · HTML: https://mlsanity.com/paper/2210.05976/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 51 references that are in the map.
- First posted on arXiv 12 Oct 2022.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [WaveGrad: Estimating Gradients for Waveform Generation](https://mlsanity.com/paper/2009.00713/) (2020)
- [On human motion prediction using recurrent neural networks](https://mlsanity.com/paper/1705.02445/) (2017)
- [3D Human Pose Estimation with Spatial and Temporal Transformers](https://mlsanity.com/paper/2103.10455/) (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)
- [Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders](https://mlsanity.com/paper/1611.02648/) (2016)
- [DLow: Diversifying Latent Flows for Diverse Human Motion Prediction](https://mlsanity.com/paper/2003.08386/) (2020)
- [Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion](https://mlsanity.com/paper/2203.13777/) (2022)
- [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)
- [We are More than Our Joints: Predicting how 3D Bodies Move](https://mlsanity.com/paper/2012.00619/) (2020)
- [MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction](https://mlsanity.com/paper/2108.07152/) (2021)
- [A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion](https://mlsanity.com/paper/2112.03530/) (2021)
- [Back to MLP: A Simple Baseline for Human Motion Prediction](https://mlsanity.com/paper/2207.01567/) (2022)
- [Structured Prediction Helps 3D Human Motion Modelling](https://mlsanity.com/paper/1910.09070/) (2019)
- [The Pose Knows: Video Forecasting by Generating Pose Futures](https://mlsanity.com/paper/1705.00053/) (2017)
- [MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics](https://mlsanity.com/paper/1808.04545/) (2018)
- [Space-Time-Separable Graph Convolutional Network for Pose Forecasting](https://mlsanity.com/paper/2110.04573/) (2021)
- [Diverse Trajectory Forecasting with Determinantal Point Processes](https://mlsanity.com/paper/1907.04967/) (2019)
- [DeLiGAN : Generative Adversarial Networks for Diverse and Limited Data](https://mlsanity.com/paper/1706.02071/) (2017)

## Built on by (most cited first, 28 of 28)

- [InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion](https://mlsanity.com/paper/2308.16905/) (2023)
- [CG-HOI: Contact-Guided 3D Human-Object Interaction Generation](https://mlsanity.com/paper/2311.16097/) (2023)
- [Recent Advancements in End-to-End Autonomous Driving using Deep Learning: A Survey](https://mlsanity.com/paper/2307.04370/) (2023)
- [BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction](https://mlsanity.com/paper/2211.14304/) (2022)
- [HumanMAC: Masked Motion Completion for Human Motion Prediction](https://mlsanity.com/paper/2302.03665/) (2023)
- [CoMusion: Towards Consistent Stochastic Human Motion Prediction via Motion Diffusion](https://mlsanity.com/paper/2305.12554/) (2023)
- [TransFusion: A Practical and Effective Transformer-based Diffusion Model for 3D Human Motion Prediction](https://mlsanity.com/paper/2307.16106/) (2023)
- [Realistic Human Motion Generation with Cross-Diffusion Models](https://mlsanity.com/paper/2312.10993/) (2023)
- [Learning Semantic Latent Directions for Accurate and Controllable Human Motion Prediction](https://mlsanity.com/paper/2407.11494/) (2024)
- [Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction](https://mlsanity.com/paper/2501.06035/) (2025)
- [Enhanced Fine-grained Motion Diffusion for Text-driven Human Motion Synthesis](https://mlsanity.com/paper/2305.13773/) (2023)
- [MotionWavelet: Human Motion Prediction via Wavelet Manifold Learning](https://mlsanity.com/paper/2411.16964/) (2024)
- [EgoReAct: Egocentric Video-Driven 3D Human Reaction Generation](https://mlsanity.com/paper/2512.22808/) (2025)
- [DivDiff: A Conditional Diffusion Model for Diverse Human Motion Prediction](https://mlsanity.com/paper/2409.00014/) (2024)
- [DeFeeNet: Consecutive 3D Human Motion Prediction with Deviation Feedback](https://mlsanity.com/paper/2304.04496/) (2023)
- [CacheFlow: Fast Human Motion Prediction by Cached Normalizing Flow](https://mlsanity.com/paper/2505.13140/) (2025)
- [R2-Diff: Denoising by diffusion as a refinement of retrieved motion for image-based motion prediction](https://mlsanity.com/paper/2306.09483/) (2023)
- [Physics-constrained Attack against Convolution-based Human Motion Prediction](https://mlsanity.com/paper/2306.11990/) (2023)
- [Bayesian-Optimized One-Step Diffusion Model with Knowledge Distillation for Real-Time 3D Human Motion Prediction](https://mlsanity.com/paper/2409.12456/) (2024)
- [Uncertainty-aware Probabilistic 3D Human Motion Forecasting via Invertible Networks](https://mlsanity.com/paper/2507.14694/) (2025)
- [A Spatio-temporal Continuous Network for Stochastic 3D Human Motion Prediction](https://mlsanity.com/paper/2508.01585/) (2025)
- [HumanCM: One Step Human Motion Prediction](https://mlsanity.com/paper/2510.16709/) (2025)
- [MMCM: Multimodality-aware Metric using Clustering-based Modes for Probabilistic Human Motion Prediction](https://mlsanity.com/paper/2511.15179/) (2025)
- [SMamDiff: Spatial Mamba for Stochastic Human Motion Prediction](https://mlsanity.com/paper/2512.00355/) (2025)
- [KHMP: Frequency-Domain Kalman Refinement for High-Fidelity Human Motion Prediction](https://mlsanity.com/paper/2603.21327/) (2026)
- [Gaussian-Mixture Latent Flow for Stochastic 3D Human Motion Prediction](https://mlsanity.com/paper/2608.21093/) (2026)
- [From Where to How: Continuous 4D Interaction Forecasting from Egocentric Video](https://mlsanity.com/paper/2609.08636/) (2026)
- [Skeletons in Flow: Graph Structured Flow Matching for Human Motion Prediction](https://mlsanity.com/paper/2609.32231/) (2026)

## Abstract (arXiv)

Stochastic human motion prediction aims to forecast multiple plausible future motions given a single pose sequence from the past. Most previous works focus on designing elaborate losses to improve the accuracy, while the diversity is typically characterized by randomly sampling a set of latent variables from the latent prior, which is then decoded into possible motions. This joint training of sampling and decoding, however, suffers from posterior collapse as the learned latent variables tend to be ignored by a strong decoder, leading to limited diversity. Alternatively, inspired by the diffusion process in nonequilibrium thermodynamics, we propose MotionDiff, a diffusion probabilistic model to treat the kinematics of human joints as heated particles, which will diffuse from original states to a noise distribution. This process offers a natural way to obtain the "whitened" latents without any trainable parameters, and human motion prediction can be regarded as the reverse diffusion process that converts the noise distribution into realistic future motions conditioned on the observed sequence. Specifically, MotionDiff consists of two parts: a spatial-temporal transformer-based diffusion network to generate diverse yet plausible motions, and a graph convolutional network to further refine the outputs. Experimental results on two datasets demonstrate that our model yields the competitive performance in terms of both accuracy and diversity.