# PALUM: Part-based Attention Learning for Unified Motion Retargeting

arXiv: https://arxiv.org/abs/2601.07272 · HTML: https://mlsanity.com/paper/2601.07272/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 12 Jan 2026.

## Builds on (most cited first, 9 of 9)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Skeleton-Aware Networks for Deep Motion Retargeting](https://mlsanity.com/paper/2005.05732/) (2020)
- [Neural Kinematic Networks for Unsupervised Motion Retargetting](https://mlsanity.com/paper/1804.05653/) (2018)
- [AnyTop: Character Animation Diffusion with Any Topology](https://mlsanity.com/paper/2502.17327/) (2025)
- [Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometry](https://mlsanity.com/paper/2303.08658/) (2023)
- [Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence](https://mlsanity.com/paper/2508.13139/) (2025)
- [Skinned Motion Retargeting with Dense Geometric Interaction Perception](https://mlsanity.com/paper/2410.20986/) (2024)
- [Pose-aware Attention Network for Flexible Motion Retargeting by Body Part](https://mlsanity.com/paper/2306.08006/) (2023)

## Built on by (most cited first, 3 of 3)

- [UniMate: One Unified Model to Animate Diverse Skeletons](https://mlsanity.com/paper/2609.05415/) (2026)
- [AnyAct: Towards Human Reenactment of Character Motion From Video](https://mlsanity.com/paper/2605.15497/) (2026)
- [Retargeting Motions to Diverse Skeletons via Learnable Flattening](https://mlsanity.com/paper/2609.38578/) (2026)

## Abstract (arXiv)

Retargeting motion between characters with different skeleton structures is a fundamental challenge in computer animation. When source and target characters have vastly different bone arrangements, maintaining the original motion's semantics and quality becomes increasingly difficult. We present PALUM, a novel approach that learns common motion representations across diverse skeleton topologies by partitioning joints into semantic body parts and applying attention mechanisms to capture spatio-temporal relationships. Our method transfers motion to target skeletons by leveraging these skeleton-agnostic representations alongside target-specific structural information. To ensure robust learning and preserve motion fidelity, we introduce a cycle consistency mechanism that maintains semantic coherence throughout the retargeting process. Extensive experiments demonstrate superior performance in handling diverse skeletal structures while maintaining motion realism and semantic fidelity, even when generalizing to previously unseen skeleton-motion combinations. We will make our implementation publicly available to support future research.