|国家预印本平台
首页|Human Motion Unlearning

Human Motion Unlearning

Human Motion Unlearning

来源:Arxiv_logoArxiv
英文摘要

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: \href{https://www.pinlab.org/hmu}{https://www.pinlab.org/hmu}.

Edoardo De Matteis、Matteo Migliarini、Alessio Sampieri、Indro Spinelli、Fabio Galasso

计算技术、计算机技术

Edoardo De Matteis,Matteo Migliarini,Alessio Sampieri,Indro Spinelli,Fabio Galasso.Human Motion Unlearning[EB/OL].(2025-03-24)[2025-08-02].https://arxiv.org/abs/2503.18674.点此复制

评论