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{this https URL}{this https URL}.
View on arXiv@article{matteis2025_2503.18674,
title={ Human Motion Unlearning },
author={ Edoardo De Matteis and Matteo Migliarini and Alessio Sampieri and Indro Spinelli and Fabio Galasso },
journal={arXiv preprint arXiv:2503.18674},
year={ 2025 }
}