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

Source: [PALUM: Part-based Attention Learning for Unified Motion Retargeting](<https://www.sota2.com/research/paper/6965d1996343fa78c8323675>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-14T05:00:12.520Z

Authors: Siqi Liu, Maoyu Wang, Bo Dai, Cewu Lu

Published: 2026-01-12T07:29:44.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Intra-Structural Motion Retargeting on Mixamo](<https://www.sota2.com/research/sota/intra-structural-motion-retargeting-on-mixamo.md>): Intra-Structural Motion Retargeting; Mixamo; MSE (sc+sm): 0.00214.

- [Cross-Structural Motion Retargeting on Mixamo](<https://www.sota2.com/research/sota/cross-structural-motion-retargeting-on-mixamo.md>): Cross-Structural Motion Retargeting; Mixamo; sc+sm MSE: 0.00225.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2601.07272>)

[PDF](<https://arxiv.org/pdf/2601.07272.pdf>)
