# SMamDiff: Spatial Mamba for Stochastic Human Motion Prediction

arXiv: https://arxiv.org/abs/2512.00355 · HTML: https://mlsanity.com/paper/2512.00355/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 18 of its 25 references that are in the map.
- First posted on arXiv 29 Nov 2025.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)
- State-space sequence models (S4, Mamba) / [Video, motion and generative Mamba models](https://mlsanity.com/ssm/video-motion-and-generative-mamba-models/)

## Builds on (most cited first, 18 of 18)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [On human motion prediction using recurrent neural networks](https://mlsanity.com/paper/1705.02445/) (2017)
- [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)
- [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)
- [DeLiGAN : Generative Adversarial Networks for Diverse and Limited Data](https://mlsanity.com/paper/1706.02071/) (2017)
- [Generating Smooth Pose Sequences for Diverse Human Motion Prediction](https://mlsanity.com/paper/2108.08422/) (2021)
- [A generic diffusion-based approach for 3D human pose prediction in the wild](https://mlsanity.com/paper/2210.05669/) (2022)
- [Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Space](https://mlsanity.com/paper/2207.07351/) (2022)
- [Motron: Multimodal Probabilistic Human Motion Forecasting](https://mlsanity.com/paper/2203.04132/) (2022)
- [Skeleton-Parted Graph Scattering Networks for 3D Human Motion Prediction](https://mlsanity.com/paper/2208.00368/) (2022)
- [Human Joint Kinematics Diffusion-Refinement for Stochastic Motion Prediction](https://mlsanity.com/paper/2210.05976/) (2022)
- [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)
- [Can We Use Diffusion Probabilistic Models for 3D Motion Prediction?](https://mlsanity.com/paper/2302.14503/) (2023)

## Abstract (arXiv)

With intelligent room-side sensing and service robots widely deployed, human motion prediction (HMP) is essential for safe, proactive assistance. However, many existing HMP methods either produce a single, deterministic forecast that ignores uncertainty or rely on probabilistic models that sacrifice kinematic plausibility. Diffusion models improve the accuracy-diversity trade-off but often depend on multi-stage pipelines that are costly for edge deployment. This work focuses on how to ensure spatial-temporal coherence within a single-stage diffusion model for HMP. We introduce SMamDiff, a Spatial Mamba-based Diffusion model with two novel designs: (i) a residual-DCT motion encoding that subtracts the last observed pose before a temporal DCT, reducing the first DC component (f=0) dominance and highlighting informative higher-frequency cues so the model learns how joints move rather than where they are; and (ii) a stickman-drawing spatial-mamba module that processes joints in an ordered, joint-by-joint manner, making later joints condition on earlier ones to induce long-range, cross-joint dependencies. On Human3.6M and HumanEva, these coherence mechanisms deliver state-of-the-art results among single-stage probabilistic HMP methods while using less latency and memory than multi-stage diffusion baselines.