人類動作反學習

Human Motion Unlearning

March 24, 2025

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

cs.AI

摘要

我們提出了人體運動遺忘任務，旨在防止生成有害動畫的同時，保持文本到運動生成的一般性能。遺忘有害運動具有挑戰性，因為這些運動既可以由顯式文本提示生成，也可以由安全運動的隱式有害組合產生（例如，「踢腿」是「抬腿和擺腿」的組合）。我們通過從大型且最新的文本到運動數據集HumanML3D和Motion-X中過濾有害運動，提出了首個運動遺忘基準。我們提出了基線方法，通過適應最先進的圖像遺忘技術來處理時空信號。最後，我們提出了一種基於潛在代碼替換的新型運動遺忘模型，簡稱LCR。LCR無需訓練，並且適用於最先進的文本到運動擴散模型的離散潛在空間。LCR方法簡單，在質量和數量上均一致優於基線方法。項目頁面：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}.