# Residual Flow Matching with Dynamic Cross-Interaction for 3D Multi-Person Motion Prediction

arXiv: https://arxiv.org/abs/2608.03379 · HTML: https://mlsanity.com/paper/2608.03379/

## 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 23 of its 32 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 23 of 23)

- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [Action-Conditioned 3D Human Motion Synthesis with Transformer VAE](https://mlsanity.com/paper/2104.05670/) (2021)
- [TEMOS: Generating diverse human motions from textual descriptions](https://mlsanity.com/paper/2204.14109/) (2022)
- [PhysDiff: Physics-Guided Human Motion Diffusion Model](https://mlsanity.com/paper/2212.02500/) (2022)
- [Learning Trajectory Dependencies for Human Motion Prediction](https://mlsanity.com/paper/1908.05436/) (2019)
- [Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB](https://mlsanity.com/paper/1712.03453/) (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)
- [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)
- [Generating Smooth Pose Sequences for Diverse Human Motion Prediction](https://mlsanity.com/paper/2108.08422/) (2021)
- [Multi-Person 3D Motion Prediction with Multi-Range Transformers](https://mlsanity.com/paper/2111.12073/) (2021)
- [A generic diffusion-based approach for 3D human pose prediction in the wild](https://mlsanity.com/paper/2210.05669/) (2022)
- [Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning](https://mlsanity.com/paper/2404.05218/) (2024)
- [Stochastic Multi-Person 3D Motion Forecasting](https://mlsanity.com/paper/2306.05421/) (2023)
- [Trajectory-Aware Body Interaction Transformer for Multi-Person Pose Forecasting](https://mlsanity.com/paper/2303.05095/) (2023)
- [CoMusion: Towards Consistent Stochastic Human Motion Prediction via Motion Diffusion](https://mlsanity.com/paper/2305.12554/) (2023)
- [Joint-Relation Transformer for Multi-Person Motion Prediction](https://mlsanity.com/paper/2308.04808/) (2023)
- [Deep Compositional Phase Diffusion for Long Motion Sequence Generation](https://mlsanity.com/paper/2510.14427/) (2025)
- [Expressive Forecasting of 3D Whole-body Human Motions](https://mlsanity.com/paper/2312.11972/) (2023)
- [Efficient Multi-Person Motion Prediction by Lightweight Spatial and Temporal Interactions](https://mlsanity.com/paper/2507.09446/) (2025)

## Abstract (arXiv)

3D multi-person motion prediction requires modeling both individual kinematics and inter-person interactions. While Flow Matching is effective for multi-hypothesis generation to improve prediction accuracy, directly predicting skeletal sequences from pure noise often compromises structural consistency and introduces unreliable cross-agent interactions during early noise-dominated integration steps. To address this, we propose a Prior-Guided Residual Flow Matching framework. First, a Deterministic Coarse Prior (DCP) establishes a kinematic anchor, formulating the generative process as a conditional flow over motion residuals to simplify the generative objective and preserve structural stability. Second, a Dynamic Cross-Interaction (DCI) mechanism temporally synchronizes inter-agent message-passing with the integration progress, ensuring the extraction of reliable social contexts and improving multi-person motion fidelity. Finally, a decoupled joint-motion architecture with bidirectional fusion effectively preserves fine-grained kinematic coherence. Extensive experiments demonstrate that our approach achieves state-of-the-art prediction accuracy across multiple datasets. Code is available at https://github.com/Wei-Wei-a/Residual-Flow-Matching-with-Dynamic-Cross-Interaction-for-3D-Multi-Person-Motion-Prediction.