paper-with-me

Papers

Morph: A Motion-free Physics Optimization Framework for Human Motion Generation

2024-11-22 · Zhuo Li, Mingshuang Luo, Ruibing Hou, Xin Zhao, Hao liu, Hong Chang, Zimo Liu, Chen Li

Human motion generation plays a vital role in applications such as digital humans and humanoid robot control. However, most existing approaches disregard physics constraints, leading to the frequent production of physically implausible motions with pronounced artifacts such as floating and foot sliding. In this paper, we propose \textbf{Morph}, a \textbf{Mo}tion-f\textbf{r}ee \textbf{ph}ysics optimization framework, comprising a Motion Generator and a Motion Physics Refinement module, for enhancing physical plausibility without relying on costly real-world motion data. Specifically, the Motion Generator is responsible for providing large-scale synthetic motion data, while the Motion Physics Refinement Module utilizes these synthetic data to train a motion imitator within a physics simulator, enforcing physical constraints to project the noisy motions into a physically-plausible space. These physically refined motions, in turn, are used to fine-tune the Motion Generator, further enhancing its capability. Experiments on both text-to-motion and music-to-dance generation tasks demonstrate that our framework achieves state-of-the-art motion generation quality while improving physical plausibility drastically.

📄 PDF Abstract BibTeX arXiv:2411.14951

Code (0)

등록된 구현이 없습니다.

Tasks

MORPHMotion Generation

Similar Papers 제목 키워드 기반

ReActor: Reinforcement Learning for Physics-Aware Motion Retargeting

2026-05-07 · David Müller, Agon Serifi, Sammy Christen, Ruben Grandia 외 arxiv

Retargeting human kinematic reference motion onto a robot's morphology remains a formidable challenge. Existing methods often produce physical inconsistencies, such as foot sliding, self-collisions, or dynamically infeas…

Reinforcement LearningBilevel Optimization

Human2Humanoid: Physics-Aware Cross-Morphology Motion Retargeting for Humanoid Robots

2026-06-02 · Tianchen Huang, Feiyang Yuan, Junchi Gu, Shurui Fang 외 arxiv

Retargeting human motion to humanoid robots is critical for teleoperation, imitation learning and human-robot interaction. However, it remains challenging because of substantial morphological discrepancies between humans…

Morphology-Conditioned World Model for Cross-Embodiment Quadrupedal Locomotion

2026-04-09 · Mohamad H. Danesh, Chenhao Li, Amin Abyaneh, Anas Houssaini 외 arxiv

World models promise a paradigm shift in robotics, where an agent learns the physics of its environment once and then acquires behaviors efficiently. Yet the learned dynamics models at their core are typically morphology…

Zero-shot Generalization

Rapid tracking through strongly scattering media with physics-informed neuromorphic speckle analysis

2026-04-28 · Yuqing Cao, Shuo Zhu, Rongzhou Chen, Jingyan Chen 외 arxiv

This work addresses the critical problem of tracking fast-moving objects through strongly scattering media in a low-light environment. Different from existing approaches that use frame-based cameras with fixed exposure t…

Walking on Thin Air: Environment-Free Physics-based Markerless Motion Capture

2018-12-04 · Micha Livne, Leonid Sigal, Marcus A. Brubaker, David J. Fleet

We propose a generative approach to physics-based motion capture. Unlike prior attempts to incorporate physics into tracking that assume the subject and scene geometry are calibrated and known a priori, our approach is a…

Markerless Motion Capture