# TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting

arXiv: https://arxiv.org/abs/2003.14401 · HTML: https://mlsanity.com/paper/2003.14401/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Mar 2020.

## Built on by (most cited first, 30 of 36)

- [MotionBERT: A Unified Perspective on Learning Human Motion Representations](https://mlsanity.com/paper/2210.06551/) (2022)
- [Latent Image Animator: Learning to Animate Images via Latent Space Navigation](https://mlsanity.com/paper/2203.09043/) (2022)
- [Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes](https://mlsanity.com/paper/2303.02760/) (2023)
- [Structure-Aware Motion Transfer with Deformable Anchor Model](https://mlsanity.com/paper/2204.05018/) (2022)
- [MegActor: Harness the Power of Raw Video for Vivid Portrait Animation](https://mlsanity.com/paper/2405.20851/) (2024)
- [LoCoNet: Long-Short Context Network for Active Speaker Detection](https://mlsanity.com/paper/2301.08237/) (2023)
- [Vision-Based Human Pose Estimation via Deep Learning: A Survey](https://mlsanity.com/paper/2308.13872/) (2023)
- [3DHumanGAN: 3D-Aware Human Image Generation with 3D Pose Mapping](https://mlsanity.com/paper/2212.07378/) (2022)
- [Aligning Human Motion Generation with Human Perceptions](https://mlsanity.com/paper/2407.02272/) (2024)
- [AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movements](https://mlsanity.com/paper/2503.07499/) (2025)
- [Diverse Generation from a Single Video Made Possible](https://mlsanity.com/paper/2109.08591/) (2021)
- [MoCaNet: Motion Retargeting in-the-wild via Canonicalization Networks](https://mlsanity.com/paper/2112.10082/) (2021)
- [Copy Motion From One to Another: Fake Motion Video Generation](https://mlsanity.com/paper/2205.01373/) (2022)
- [Flow Guided Transformable Bottleneck Networks for Motion Retargeting](https://mlsanity.com/paper/2106.07771/) (2021)
- [Cross-identity Video Motion Retargeting with Joint Transformation and Synthesis](https://mlsanity.com/paper/2210.01559/) (2022)
- [Conditional Temporal Variational AutoEncoder for Action Video Prediction](https://mlsanity.com/paper/2108.05658/) (2021)
- [Do As I Do: Pose Guided Human Motion Copy](https://mlsanity.com/paper/2406.16601/) (2024)
- [DisUnknown: Distilling Unknown Factors for Disentanglement Learning](https://mlsanity.com/paper/2109.08090/) (2021)
- [Reenact Anything: Semantic Video Motion Transfer Using Motion-Textual Inversion](https://mlsanity.com/paper/2408.00458/) (2024)
- [Two-Person Interaction Augmentation with Skeleton Priors](https://mlsanity.com/paper/2404.05490/) (2024)
- [A Survey on Applications of Digital Human Avatars toward Virtual Co-presence](https://mlsanity.com/paper/2201.04168/) (2022)
- [REMOT: A Region-to-Whole Framework for Realistic Human Motion Transfer](https://mlsanity.com/paper/2209.00475/) (2022)
- [Versatile Face Animator: Driving Arbitrary 3D Facial Avatar in RGBD Space](https://mlsanity.com/paper/2308.06076/) (2023)
- [LIA-X: Interpretable Latent Portrait Animator](https://mlsanity.com/paper/2508.09959/) (2025)
- [Video Reenactment as Inductive Bias for Content-Motion Disentanglement](https://mlsanity.com/paper/2102.00324/) (2021)
- [Render In-between: Motion Guided Video Synthesis for Action Interpolation](https://mlsanity.com/paper/2111.01029/) (2021)
- [Neural Marionette: Unsupervised Learning of Motion Skeleton and Latent Dynamics from Volumetric Video](https://mlsanity.com/paper/2202.08418/) (2022)
- [An Identity-Preserved Framework for Human Motion Transfer](https://mlsanity.com/paper/2204.06862/) (2022)
- [Neural Sign Reenactor: Deep Photorealistic Sign Language Retargeting](https://mlsanity.com/paper/2209.01470/) (2022)
- [Recovering Complete Actions for Cross-dataset Skeleton Action Recognition](https://mlsanity.com/paper/2410.23641/) (2024)

## Abstract (arXiv)

We present a lightweight video motion retargeting approach TransMoMo that is capable of transferring motion of a person in a source video realistically to another video of a target person. Without using any paired data for supervision, the proposed method can be trained in an unsupervised manner by exploiting invariance properties of three orthogonal factors of variation including motion, structure, and view-angle. Specifically, with loss functions carefully derived based on invariance, we train an auto-encoder to disentangle the latent representations of such factors given the source and target video clips. This allows us to selectively transfer motion extracted from the source video seamlessly to the target video in spite of structural and view-angle disparities between the source and the target. The relaxed assumption of paired data allows our method to be trained on a vast amount of videos needless of manual annotation of source-target pairing, leading to improved robustness against large structural variations and extreme motion in videos. We demonstrate the effectiveness of our method over the state-of-the-art methods. Code, model and data are publicly available on our project page (https://yzhq97.github.io/transmomo).