# Human Motion Transfer from Poses in the Wild

arXiv: https://arxiv.org/abs/2004.03142 · HTML: https://mlsanity.com/paper/2004.03142/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2020.

## Built on by (most cited first, 17 of 17)

- [Motion Representations for Articulated Animation](https://mlsanity.com/paper/2104.11280/) (2021)
- [A Good Image Generator Is What You Need for High-Resolution Video Synthesis](https://mlsanity.com/paper/2104.15069/) (2021)
- [Teachers Do More Than Teach: Compressing Image-to-Image Models](https://mlsanity.com/paper/2103.03467/) (2021)
- [Diverse Generation from a Single Video Made Possible](https://mlsanity.com/paper/2109.08591/) (2021)
- [Flow Guided Transformable Bottleneck Networks for Motion Retargeting](https://mlsanity.com/paper/2106.07771/) (2021)
- [Towards Smooth Video Composition](https://mlsanity.com/paper/2212.07413/) (2022)
- [Motion Transformer for Unsupervised Image Animation](https://mlsanity.com/paper/2209.14024/) (2022)
- [Continuous Piecewise-Affine Based Motion Model for Image Animation](https://mlsanity.com/paper/2401.09146/) (2024)
- [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)
- [Programmatic Concept Learning for Human Motion Description and Synthesis](https://mlsanity.com/paper/2206.13502/) (2022)
- [One-shot Human Motion Transfer via Occlusion-Robust Flow Prediction and Neural Texturing](https://mlsanity.com/paper/2412.06174/) (2024)
- [Do as we do: Multiple Person Video-To-Video Transfer](https://mlsanity.com/paper/2104.04721/) (2021)
- [CTrGAN: Cycle Transformers GAN for Gait Transfer](https://mlsanity.com/paper/2206.15248/) (2022)
- [Can Pose Transfer Models Generate Realistic Human Motion?](https://mlsanity.com/paper/2501.15648/) (2025)
- [Diverse Video Generation from a Single Video](https://mlsanity.com/paper/2205.05725/) (2022)
- [Face Animation with Multiple Source Images](https://mlsanity.com/paper/2212.00256/) (2022)

## Abstract (arXiv)

In this paper, we tackle the problem of human motion transfer, where we synthesize novel motion video for a target person that imitates the movement from a reference video. It is a video-to-video translation task in which the estimated poses are used to bridge two domains. Despite substantial progress on the topic, there exist several problems with the previous methods. First, there is a domain gap between training and testing pose sequences--the model is tested on poses it has not seen during training, such as difficult dancing moves. Furthermore, pose detection errors are inevitable, making the job of the generator harder. Finally, generating realistic pixels from sparse poses is challenging in a single step. To address these challenges, we introduce a novel pose-to-video translation framework for generating high-quality videos that are temporally coherent even for in-the-wild pose sequences unseen during training. We propose a pose augmentation method to minimize the training-test gap, a unified paired and unpaired learning strategy to improve the robustness to detection errors, and two-stage network architecture to achieve superior texture quality. To further boost research on the topic, we build two human motion datasets. Finally, we show the superiority of our approach over the state-of-the-art studies through extensive experiments and evaluations on different datasets.