SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control

• URL: http://arxiv.org/abs/2512.03028v2
• Date: Wed, 03 Dec 2025 17:44:54 GMT
• Title: SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control
• Authors: Yuxuan Mu, Ziyu Zhang, Yi Shi, Minami Matsumoto, Kotaro Imamura, Guy Tevet, Chuan Guo, Michael Taylor, Chang Shu, Pengcheng Xi, Xue Bin Peng,
• Abstract summary: Motion priors that guide agents toward producing naturalistic behaviors play a pivotal role in creating life-like virtual characters.<n>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.<n>Our method produces high-quality motion comparable to state-of-the-art adversarial imitation learning methods through reusable and modular motion priors.
• Score: 20.779031780374115
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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 training on 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 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 produces high-quality motion comparable to state-of-the-art adversarial imitation learning methods through reusable and modular motion priors. We demonstrate the effectiveness of SMP across a diverse suite of control tasks with physically simulated humanoid characters. Video demo available at https://youtu.be/ravlZJteS20

Related papers

• Imitating What Works: Simulation-Filtered Modular Policy Learning from Human Videos [56.510263910611684]
  We tackle prehensile manipulation, in which tasks involve grasping an object before performing various post-grasp motions.<n>Human videos offer strong signals for learning the post-grasp motions, but they are less useful for learning the prerequisite grasping behaviors.<n>We present Perceive-Simulate-Imitate (PSI), a framework for training a modular manipulation policy using human video motion data.
  arXiv  Detail & Related papers  (2026-02-13T18:59:10Z)
• ResMimic: From General Motion Tracking to Humanoid Whole-body Loco-Manipulation via Residual Learning [59.64325421657381]
  Humanoid whole-body loco-manipulation promises transformative capabilities for daily service and warehouse tasks.<n>We introduce ResMimic, a two-stage residual learning framework for precise and expressive humanoid control from human motion data.<n>Results show substantial gains in task success, training efficiency, and robustness over strong baselines.
  arXiv  Detail & Related papers  (2025-10-06T17:47:02Z)
• Universal Humanoid Motion Representations for Physics-Based Control [71.46142106079292]
  We present a universal motion representation that encompasses a comprehensive range of motor skills for physics-based humanoid control. We first learn a motion imitator that can imitate all of human motion from a large, unstructured motion dataset. We then create our motion representation by distilling skills directly from the imitator.
  arXiv  Detail & Related papers  (2023-10-06T20:48:43Z)
• Neural Categorical Priors for Physics-Based Character Control [12.731392285646614]
  We propose a new learning framework for controlling physics-based characters with significantly improved motion quality and diversity. The proposed method uses reinforcement learning (RL) to initially track and imitate life-like movements from unstructured motion clips. We conduct comprehensive experiments using humanoid characters on two challenging downstream tasks, sword-shield striking and two-player boxing game.
  arXiv  Detail & Related papers  (2023-08-14T15:10:29Z)
• Interactive Character Control with Auto-Regressive Motion Diffusion Models [18.727066177880708]
  We propose A-MDM (Auto-regressive Motion Diffusion Model) for real-time motion synthesis. Our conditional diffusion model takes an initial pose as input, and auto-regressively generates successive motion frames conditioned on previous frame. We introduce a suite of techniques for incorporating interactive controls into A-MDM, such as task-oriented sampling, in-painting, and hierarchical reinforcement learning.
  arXiv  Detail & Related papers  (2023-06-01T07:48:34Z)
• PMP: Learning to Physically Interact with Environments using Part-wise Motion Priors [10.370115975772402]
  We present a method to animate a character incorporating multiple part-wise motion priors (PMP) The proposed PMP allows us to assemble multiple part skills to animate a character, creating a diverse set of motions with different combinations of existing data.
  arXiv  Detail & Related papers  (2023-05-05T02:27:27Z)
• Executing your Commands via Motion Diffusion in Latent Space [51.64652463205012]
  We propose a Motion Latent-based Diffusion model (MLD) to produce vivid motion sequences conforming to the given conditional inputs. Our MLD achieves significant improvements over the state-of-the-art methods among extensive human motion generation tasks.
  arXiv  Detail & Related papers  (2022-12-08T03:07:00Z)
• Weakly-supervised Action Transition Learning for Stochastic Human Motion Prediction [81.94175022575966]
  We introduce the task of action-driven human motion prediction. It aims to predict multiple plausible future motions given a sequence of action labels and a short motion history.
  arXiv  Detail & Related papers  (2022-05-31T08:38:07Z)
• Exploring Versatile Prior for Human Motion via Motion Frequency Guidance [32.50770614788775]
  We learn a framework to learn the versatile motion prior, which models the inherent probability distribution of human motions. For efficient prior representation learning, we propose a global orientation normalization to remove redundant environment information. We then adopt a denoising training scheme to disentangle the environment information from input motion data in a learnable way.
  arXiv  Detail & Related papers  (2021-11-25T13:24:44Z)
• AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control [145.61135774698002]
  We propose a fully automated approach to selecting motion for a character to track in a given scenario. High-level task objectives that the character should perform can be specified by relatively simple reward functions. Low-level style of the character's behaviors can be specified by a dataset of unstructured motion clips. Our system produces high-quality motions comparable to those achieved by state-of-the-art tracking-based techniques.
  arXiv  Detail & Related papers  (2021-04-05T22:43:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.