# An Identity-Preserved Framework for Human Motion Transfer

arXiv: https://arxiv.org/abs/2204.06862 · HTML: https://mlsanity.com/paper/2204.06862/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 72 references that are in the map.
- First posted on arXiv 14 Apr 2022.

## Builds on (most cited first, 30 of 37)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Video-to-Video Synthesis](https://mlsanity.com/paper/1808.06601/) (2018)
- [Everybody Dance Now](https://mlsanity.com/paper/1808.07371/) (2018)
- [Few-shot Video-to-Video Synthesis](https://mlsanity.com/paper/1910.12713/) (2019)
- [Deformable GANs for Pose-based Human Image Generation](https://mlsanity.com/paper/1801.00055/) (2017)
- [Skeleton-Aware Networks for Deep Motion Retargeting](https://mlsanity.com/paper/2005.05732/) (2020)
- [Gait Recognition via Effective Global-Local Feature Representation and Local Temporal Aggregation](https://mlsanity.com/paper/2011.01461/) (2020)
- [GaitGraph: Graph Convolutional Network for Skeleton-Based Gait Recognition](https://mlsanity.com/paper/2101.11228/) (2021)
- [Dense Intrinsic Appearance Flow for Human Pose Transfer](https://mlsanity.com/paper/1903.11326/) (2019)
- [Synthesizing Images of Humans in Unseen Poses](https://mlsanity.com/paper/1804.07739/) (2018)
- [Neural Kinematic Networks for Unsupervised Motion Retargetting](https://mlsanity.com/paper/1804.05653/) (2018)
- [World-Consistent Video-to-Video Synthesis](https://mlsanity.com/paper/2007.08509/) (2020)
- [GaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Set](https://mlsanity.com/paper/2102.03247/) (2021)
- [GaitEdge: Beyond Plain End-to-end Gait Recognition for Better Practicality](https://mlsanity.com/paper/2203.03972/) (2022)
- [Learning Character-Agnostic Motion for Motion Retargeting in 2D](https://mlsanity.com/paper/1905.01680/) (2019)
- [Deep Spatial Transformation for Pose-Guided Person Image Generation and Animation](https://mlsanity.com/paper/2008.12606/) (2020)
- [TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting](https://mlsanity.com/paper/2003.14401/) (2020)
- [Structure-Aware Motion Transfer with Deformable Anchor Model](https://mlsanity.com/paper/2204.05018/) (2022)
- [Spatial Transformer Network on Skeleton-based Gait Recognition](https://mlsanity.com/paper/2204.03873/) (2022)
- [Contact-Aware Retargeting of Skinned Motion](https://mlsanity.com/paper/2109.07431/) (2021)
- [High-Fidelity Neural Human Motion Transfer from Monocular Video](https://mlsanity.com/paper/2012.10974/) (2020)
- [Few-Shot Human Motion Transfer by Personalized Geometry and Texture Modeling](https://mlsanity.com/paper/2103.14338/) (2021)
- [Zero-shot Synthesis with Group-Supervised Learning](https://mlsanity.com/paper/2009.06586/) (2020)

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

- [Human Motion Video Generation: A Survey](https://mlsanity.com/paper/2509.03883/) (2025)
- [Pedestrian Attribute Editing for Gait Recognition and Anonymization](https://mlsanity.com/paper/2303.05076/) (2023)

## Abstract (arXiv)

Human motion transfer (HMT) aims to generate a video clip for the target subject by imitating the source subject's motion. Although previous methods have achieved good results in synthesizing good-quality videos, they lose sight of individualized motion information from the source and target motions, which is significant for the realism of the motion in the generated video. To address this problem, we propose a novel identity-preserved HMT network, termed textitIDPres. This network is a skeleton-based approach that uniquely incorporates the target's individualized motion and skeleton information to augment identity representations. This integration significantly enhances the realism of movements in the generated videos. Our method focuses on the fine-grained disentanglement and synthesis of motion. To improve the representation learning capability in latent space and facilitate the training of textitIDPres, we introduce three training schemes. These schemes enable textitIDPres to concurrently disentangle different representations and accurately control them, ensuring the synthesis of ideal motions. To evaluate the proportion of individualized motion information in the generated video, we are the first to introduce a new quantitative metric called Identity Score (textitID-Score), motivated by the success of gait recognition methods in capturing identity information. Moreover, we collect an identity-motion paired dataset, Dancer101, consisting of solo-dance videos of 101 subjects from the public domain, providing a benchmark to prompt the development of HMT methods. Extensive experiments demonstrate that the proposed textitIDPres method surpasses existing state-of-the-art techniques in terms of reconstruction accuracy, realistic motion, and identity preservation.