# MetaPix: Few-Shot Video Retargeting

arXiv: https://arxiv.org/abs/1910.04742 · HTML: https://mlsanity.com/paper/1910.04742/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Oct 2019.

## Built on by (most cited first, 13 of 13)

- [DisCo: Disentangled Control for Realistic Human Dance Generation](https://mlsanity.com/paper/2307.00040/) (2023)
- [Few-Shot Human Motion Transfer by Personalized Geometry and Texture Modeling](https://mlsanity.com/paper/2103.14338/) (2021)
- [Action2video: Generating Videos of Human 3D Actions](https://mlsanity.com/paper/2111.06925/) (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)
- [DiffBody: Diffusion-based Pose and Shape Editing of Human Images](https://mlsanity.com/paper/2401.02804/) (2024)
- [Harnessing Meta-Learning for Improving Full-Frame Video Stabilization](https://mlsanity.com/paper/2403.03662/) (2024)
- [Differential Motion Evolution for Fine-Grained Motion Deformation in Unsupervised Image Animation](https://mlsanity.com/paper/2110.04658/) (2021)
- [Harnessing Meta-Learning for Controllable Full-Frame Video Stabilization](https://mlsanity.com/paper/2508.18859/) (2025)
- [DF-Captcha: A Deepfake Captcha for Preventing Fake Calls](https://mlsanity.com/paper/2208.08524/) (2022)
- [Solutions to Deepfakes: Can Camera Hardware, Cryptography, and Deep Learning Verify Real Images?](https://mlsanity.com/paper/2407.04169/) (2024)
- [MetaDance: Few-shot Dancing Video Retargeting via Temporal-aware Meta-learning](https://mlsanity.com/paper/2201.04851/) (2022)
- [Diverse Video Generation from a Single Video](https://mlsanity.com/paper/2205.05725/) (2022)

## Abstract (arXiv)

We address the task of unsupervised retargeting of human actions from one video to another. We consider the challenging setting where only a few frames of the target is available. The core of our approach is a conditional generative model that can transcode input skeletal poses (automatically extracted with an off-the-shelf pose estimator) to output target frames. However, it is challenging to build a universal transcoder because humans can appear wildly different due to clothing and background scene geometry. Instead, we learn to adapt - or personalize - a universal generator to the particular human and background in the target. To do so, we make use of meta-learning to discover effective strategies for on-the-fly personalization. One significant benefit of meta-learning is that the personalized transcoder naturally enforces temporal coherence across its generated frames; all frames contain consistent clothing and background geometry of the target. We experiment on in-the-wild internet videos and images and show our approach improves over widely-used baselines for the task.