Behave Your Motion: Habit-preserved Cross-category Animal Motion Transfer

TL;DR

This paper introduces a novel framework for cross-category animal motion transfer that preserves species-specific habitual behaviors using a habit-preservation module and leverages large language models for transferring to unseen species.

Contribution

It presents a habit-preservation module with category-specific encoders and integrates LLMs for unobserved species, advancing animal motion transfer technology.

Findings

Outperforms existing methods in preserving habitual behaviors

Successfully transfers motion to unseen species

Validated on the new DeformingThings4D-skl dataset

Abstract

Animal motion embodies species-specific behavioral habits, making the transfer of motion across categories a critical yet complex task for applications in animation and virtual reality. Existing motion transfer methods, primarily focused on human motion, emphasize skeletal alignment (motion retargeting) or stylistic consistency (motion style transfer), often neglecting the preservation of distinct habitual behaviors in animals. To bridge this gap, we propose a novel habit-preserved motion transfer framework for cross-category animal motion. Built upon a generative framework, our model introduces a habit-preservation module with category-specific habit encoder, allowing it to learn motion priors that capture distinctive habitual characteristics. Furthermore, we integrate a large language model (LLM) to facilitate the motion transfer to previously unobserved species. To evaluate the effectiveness of our approach, we introduce the DeformingThings4D-skl dataset, a quadruped dataset with skeletal bindings, and conduct extensive experiments and quantitative analyses, which validate the superiority of our proposed model.