PALUM: Part-based Attention Learning for Unified Motion Retargeting

2026-01-12

AI Summary

This work addresses the challenge of semantic distortion and degraded motion quality in motion retargeting caused by significant structural differences between source and target skeletal topologies. To overcome this, the authors propose an attention-based learning framework grounded in semantic body-part segmentation. The approach groups joints into semantically coherent body regions and leverages an attention mechanism to learn a topology-agnostic motion representation, which is then adapted to the target skeleton by incorporating its specific structural priors. A cycle-consistency constraint is further introduced to preserve semantic coherence throughout the retargeting process. Experimental results demonstrate that the method achieves high-quality, high-fidelity motion retargeting across diverse and even unseen skeleton–motion combinations, significantly enhancing both motion realism and semantic consistency.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Motion and Path Planning
• Machine Learning: Multimodal Learning

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

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.

Problem

• motion retargeting
• skeleton structures
• semantic fidelity
• diverse topologies
• motion realism

Innovation

• part-based attention
• motion retargeting
• skeleton-agnostic representation
• cycle consistency
• spatio-temporal relationships