# MoReFlow: Motion Retargeting Learning through Unsupervised Flow Matching

arXiv: https://arxiv.org/abs/2509.25600 · HTML: https://mlsanity.com/paper/2509.25600/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 25 of its 37 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations](https://mlsanity.com/paper/2301.06052/) (2023)
- [Flow Matching Guide and Code](https://mlsanity.com/paper/2412.06264/) (2024)
- [Skeleton-Aware Networks for Deep Motion Retargeting](https://mlsanity.com/paper/2005.05732/) (2020)
- [Guided Flows for Generative Modeling and Decision Making](https://mlsanity.com/paper/2311.13443/) (2023)
- [Learning to Generate Long-term Future via Hierarchical Prediction](https://mlsanity.com/paper/1704.05831/) (2017)
- [Hierarchical Quantized Autoencoders](https://mlsanity.com/paper/2002.08111/) (2020)
- [Motion Flow Matching for Human Motion Synthesis and Editing](https://mlsanity.com/paper/2312.08895/) (2023)
- [Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometry](https://mlsanity.com/paper/2303.08658/) (2023)
- [WalkTheDog: Cross-Morphology Motion Alignment via Phase Manifolds](https://mlsanity.com/paper/2407.18946/) (2024)
- [ACE: Adversarial Correspondence Embedding for Cross Morphology Motion Retargeting from Human to Nonhuman Characters](https://mlsanity.com/paper/2305.14792/) (2023)
- [ImitationNet: Unsupervised Human-to-Robot Motion Retargeting via Shared Latent Space](https://mlsanity.com/paper/2309.05310/) (2023)
- [Physics-based Motion Retargeting from Sparse Inputs](https://mlsanity.com/paper/2307.01938/) (2023)
- [CrossLoco: Human Motion Driven Control of Legged Robots via Guided Unsupervised Reinforcement Learning](https://mlsanity.com/paper/2309.17046/) (2023)
- [Spatio-Temporal Motion Retargeting for Quadruped Robots](https://mlsanity.com/paper/2404.11557/) (2024)
- [Correspondence-free online human motion retargeting](https://mlsanity.com/paper/2302.00556/) (2023)
- [Human Motion Control of Quadrupedal Robots using Deep Reinforcement Learning](https://mlsanity.com/paper/2204.13336/) (2022)
- [FlowMotion: Target-Predictive Conditional Flow Matching for Jitter-Reduced Text-Driven Human Motion Generation](https://mlsanity.com/paper/2504.01338/) (2025)
- [Multi-Embodiment Robotic Retargeting via Guided Diffusion Model](https://mlsanity.com/paper/2505.20857/) (2025)
- [Learning Physical Interaction Skills from Human Demonstrations](https://mlsanity.com/paper/2507.20445/) (2025)

## Built on by (most cited first, 2 of 2)

- [EquiFusion: Kinematics-Agnostic Human Motion Prediction via Equivariant Latent Diffusion](https://mlsanity.com/paper/2607.10984/) (2026)
- [Why Cross-Skeleton Retargeting Is Non-Identifiable: Structural Limits of Generative Motion Models](https://mlsanity.com/paper/2609.37297/) (2026)

## Abstract (arXiv)

Motion retargeting holds a premise of offering a larger set of motion data for characters and robots with different morphologies. Many prior works have approached this problem via either handcrafted constraints or paired motion datasets, limiting their applicability to humanoid characters or narrow behaviors such as locomotion. Moreover, they often assume a fixed notion of retargeting, overlooking domain-specific objectives like style preservation in animation or task-space alignment in robotics. In this work, we propose MoReFlow, Motion Retargeting via Flow Matching, an unsupervised framework that learns correspondences between characters' motion embedding spaces. Our method consists of two stages. First, we train tokenized motion embeddings for each character using a VQ-VAE, yielding compact latent representations. Then, we employ flow matching with conditional coupling to align the latent spaces across characters, which simultaneously learns conditioned and unconditioned matching to achieve robust but flexible retargeting. Once trained, MoReFlow enables flexible and reversible retargeting without requiring paired data. Experiments demonstrate that MoReFlow produces high-quality motions across diverse characters and tasks, offering improved controllability, generalization, and motion realism compared to the baselines.