# Skeleton-Aware Networks for Deep Motion Retargeting

arXiv: https://arxiv.org/abs/2005.05732 · HTML: https://mlsanity.com/paper/2005.05732/

## Key facts

- Cited by 124 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 May 2020.

## Built on by (most cited first, 30 of 124)

- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis](https://mlsanity.com/paper/2305.00976/) (2023)
- [AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism](https://mlsanity.com/paper/2309.00796/) (2023)
- [EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling](https://mlsanity.com/paper/2401.00374/) (2023)
- [HumanTOMATO: Text-aligned Whole-body Motion Generation](https://mlsanity.com/paper/2310.12978/) (2023)
- [Real-Time Style Modelling of Human Locomotion via Feature-Wise Transformations and Local Motion Phases](https://mlsanity.com/paper/2201.04439/) (2022)
- [OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction](https://mlsanity.com/paper/2509.26633/) (2025)
- [NeMF: Neural Motion Fields for Kinematic Animation](https://mlsanity.com/paper/2206.03287/) (2022)
- [Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes](https://mlsanity.com/paper/2303.02760/) (2023)
- [Single Motion Diffusion](https://mlsanity.com/paper/2302.05905/) (2023)
- [Motion Puzzle: Arbitrary Motion Style Transfer by Body Part](https://mlsanity.com/paper/2202.05274/) (2022)
- [The Wanderings of Odysseus in 3D Scenes](https://mlsanity.com/paper/2112.09251/) (2021)
- [MoDi: Unconditional Motion Synthesis from Diverse Data](https://mlsanity.com/paper/2206.08010/) (2022)
- [Learning Skeletal Articulations with Neural Blend Shapes](https://mlsanity.com/paper/2105.02451/) (2021)
- [Locomotion-Action-Manipulation: Synthesizing Human-Scene Interactions in Complex 3D Environments](https://mlsanity.com/paper/2301.02667/) (2023)
- [TEDi: Temporally-Entangled Diffusion for Long-Term Motion Synthesis](https://mlsanity.com/paper/2307.15042/) (2023)
- [AnyTop: Character Animation Diffusion with Any Topology](https://mlsanity.com/paper/2502.17327/) (2025)
- [SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editing](https://mlsanity.com/paper/2503.13836/) (2025)
- [Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometry](https://mlsanity.com/paper/2303.08658/) (2023)
- [Task-Generic Hierarchical Human Motion Prior using VAEs](https://mlsanity.com/paper/2106.04004/) (2021)
- [Contact-Aware Retargeting of Skinned Motion](https://mlsanity.com/paper/2109.07431/) (2021)
- [Skeleton-free Pose Transfer for Stylized 3D Characters](https://mlsanity.com/paper/2208.00790/) (2022)
- [Dynamic Inertial Poser (DynaIP): Part-Based Motion Dynamics Learning for Enhanced Human Pose Estimation with Sparse Inertial Sensors](https://mlsanity.com/paper/2312.02196/) (2023)
- [Pretrained Diffusion Models for Unified Human Motion Synthesis](https://mlsanity.com/paper/2212.02837/) (2022)
- [GANimator: Neural Motion Synthesis from a Single Sequence](https://mlsanity.com/paper/2205.02625/) (2022)
- [SparsePoser: Real-time Full-body Motion Reconstruction from Sparse Data](https://mlsanity.com/paper/2311.02191/) (2023)
- [OmniMotionGPT: Animal Motion Generation with Limited Data](https://mlsanity.com/paper/2311.18303/) (2023)
- [HUMOS: Human Motion Model Conditioned on Body Shape](https://mlsanity.com/paper/2409.03944/) (2024)
- [Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence](https://mlsanity.com/paper/2508.13139/) (2025)
- [Transfer Learning in Robotics: An Upcoming Breakthrough? A Review of Promises and Challenges](https://mlsanity.com/paper/2311.18044/) (2023)

## Abstract (arXiv)

We introduce a novel deep learning framework for data-driven motion retargeting between skeletons, which may have different structure, yet corresponding to homeomorphic graphs. Importantly, our approach learns how to retarget without requiring any explicit pairing between the motions in the training set. We leverage the fact that different homeomorphic skeletons may be reduced to a common primal skeleton by a sequence of edge merging operations, which we refer to as skeletal pooling. Thus, our main technical contribution is the introduction of novel differentiable convolution, pooling, and unpooling operators. These operators are skeleton-aware, meaning that they explicitly account for the skeleton's hierarchical structure and joint adjacency, and together they serve to transform the original motion into a collection of deep temporal features associated with the joints of the primal skeleton. In other words, our operators form the building blocks of a new deep motion processing framework that embeds the motion into a common latent space, shared by a collection of homeomorphic skeletons. Thus, retargeting can be achieved simply by encoding to, and decoding from this latent space. Our experiments show the effectiveness of our framework for motion retargeting, as well as motion processing in general, compared to existing approaches. Our approach is also quantitatively evaluated on a synthetic dataset that contains pairs of motions applied to different skeletons. To the best of our knowledge, our method is the first to perform retargeting between skeletons with differently sampled kinematic chains, without any paired examples.