人类运动反学习

Human Motion Unlearning

March 24, 2025

作者: Edoardo De Matteis, Matteo Migliarini, Alessio Sampieri, Indro Spinelli, Fabio Galasso

cs.AI

摘要

我们提出了人体运动遗忘任务，旨在防止生成有害动画的同时保持通用文本到运动生成性能。遗忘有害运动具有挑战性，因为这些运动既可能由显式文本提示生成，也可能由安全运动的隐含有害组合产生（例如，“踢腿”是“抬腿并摆动”）。我们通过从大规模且最新的文本到运动数据集HumanML3D和Motion-X中筛选出有害运动，首次建立了运动遗忘基准。我们提出了基线方法，通过将最先进的图像遗忘技术适配于处理时空信号。最后，我们提出了一种基于潜在代码替换的新型运动遗忘模型，简称LCR。LCR无需训练，适用于当前最先进的文本到运动扩散模型的离散潜在空间。LCR方法简洁，在定性和定量评估中均持续优于基线方法。项目页面：https://www.pinlab.org/hmu{https://www.pinlab.org/hmu}。

English

We introduce the task of human motion unlearning to prevent the synthesis of toxic animations while preserving the general text-to-motion generative performance. Unlearning toxic motions is challenging as those can be generated from explicit text prompts and from implicit toxic combinations of safe motions (e.g., ``kicking" is ``loading and swinging a leg"). We propose the first motion unlearning benchmark by filtering toxic motions from the large and recent text-to-motion datasets of HumanML3D and Motion-X. We propose baselines, by adapting state-of-the-art image unlearning techniques to process spatio-temporal signals. Finally, we propose a novel motion unlearning model based on Latent Code Replacement, which we dub LCR. LCR is training-free and suitable to the discrete latent spaces of state-of-the-art text-to-motion diffusion models. LCR is simple and consistently outperforms baselines qualitatively and quantitatively. Project page: https://www.pinlab.org/hmu{https://www.pinlab.org/hmu}.