SMP：基于物理的字符控制的可重用评分匹配运动先验
SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control
AI总结：
本文提出SMP，利用预训练的运动扩散模型和评分蒸馏采样生成可重用的运动先验，适用于多种任务，能合成新风格并产生高质量动作。
摘要：
数据驱动的运动先验在创建逼真虚拟角色中起关键作用。对抗性模仿学习在从参考运动数据中学习运动先验方面效果显著。然而，对抗性先验通常需为每个新控制器重新训练，限制了其重用性。本文提出评分匹配运动先验（SMP），利用预训练的运动扩散模型和评分蒸馏采样生成可重用的运动先验。SMP可在不依赖任何控制策略或任务的情况下预训练于运动数据集。训练后，SMP可冻结并重用于训练新策略以产生自然行为。我们展示了一种在大规模数据集上训练的一般运动先验可被重新用于多种风格特定的先验。此外，SMP能组合不同风格以合成新风格。我们的方法能创建可重用且模块化的运动先验，产生与最先进对抗性模仿学习方法相当的高质量动作。在实验中，我们展示了SMP在多样化的控制任务中，使用物理模拟的人形角色的有效性。视频可在https://youtu.be/jBA2tWk6vzU获取。
英文摘要：
Data-driven motion priors that can guide agents toward producing naturalistic behaviors play a pivotal role in creating life-like virtual characters. Adversarial imitation learning has been a highly effective method for learning motion priors from reference motion data. However, adversarial priors, with few exceptions, need to be retrained for each new controller, thereby limiting their reusability and necessitating the retention of the reference motion data when applied to downstream tasks. In this work, we present Score-Matching Motion Priors (SMP), which leverages pre-trained motion diffusion models and score distillation sampling (SDS) to create reusable task-agnostic motion priors. SMPs can be pre-trained on a motion dataset, independent of any control policy or task. Once trained, SMPs can be kept frozen and reused as general-purpose reward functions to train new policies to produce naturalistic behaviors for downstream tasks. We show that a general motion prior trained on large-scale datasets can be repurposed into a variety of style-specific priors. Furthermore, SMP can compose different styles to synthesize new styles not present in the original dataset. Our method can create reusable and modular motion priors that produce high-quality motions comparable to state-of-the-art adversarial imitation learning methods. In our experiments, we demonstrate the effectiveness of SMP across a diverse suite of control tasks with physically simulated humanoid characters. Video available at https://youtu.be/jBA2tWk6vzU
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
