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

arXiv: https://arxiv.org/abs/2411.14951 · HTML: https://mlsanity.com/paper/2411.14951/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 1 references that are in the map.
- First posted on arXiv 22 Nov 2024.

## Builds on (most cited first, 1 of 1)

- [MoMask: Generative Masked Modeling of 3D Human Motions](https://mlsanity.com/paper/2312.00063/) (2023)

## Built on by (most cited first, 13 of 13)

- [Diffuse-CLoC: Guided Diffusion for Physics-based Character Look-ahead Control](https://mlsanity.com/paper/2503.11801/) (2025)
- [PP-Motion: Physical-Perceptual Fidelity Evaluation for Human Motion Generation](https://mlsanity.com/paper/2508.08179/) (2025)
- [MotionHiFlow: Text-to-motion via hierarchical flow matching](https://mlsanity.com/paper/2604.23264/) (2026)
- [PhysMoDPO: Physically-Plausible Humanoid Motion with Preference Optimization](https://mlsanity.com/paper/2603.13228/) (2026)
- [No MoCap Needed: Post-Training Motion Diffusion Models with Reinforcement Learning using Only Textual Prompts](https://mlsanity.com/paper/2510.06988/) (2025)
- [PGcGAN: Pathological Gait-Conditioned GAN for Human Gait Synthesis](https://mlsanity.com/paper/2603.14409/) (2026)
- [AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling](https://mlsanity.com/paper/2605.29488/) (2026)
- [Skeleton2Stage: Reward-Guided Fine-Tuning for Physically Plausible Dance Generation](https://mlsanity.com/paper/2602.13778/) (2026)
- [FatigueFusion: Latent Space Fusion for Fatigue-Driven Motion Synthesis](https://mlsanity.com/paper/2604.10199/) (2026)
- [Multi-scale Coarse-to-fine Modeling for Test-time Human Motion Control](https://mlsanity.com/paper/2605.14935/) (2026)
- [SkelMo: Universal Skeletal Motion Generation for 3D Rigged Shapes](https://mlsanity.com/paper/2606.01518/) (2026)
- [Training-free Controllable Human Motion Generation under Heterogeneous Constraints](https://mlsanity.com/paper/2607.01990/) (2026)
- [FlowHMR: Physically Plausible Motion Capture from Video](https://mlsanity.com/paper/2610.03691/) (2026)

## Abstract (arXiv)

Human motion generation has been widely studied due to its crucial role in areas such as digital humans and humanoid robot control. However, many current motion generation approaches disregard physics constraints, frequently resulting in physically implausible motions with pronounced artifacts such as floating and foot sliding. Meanwhile, training an effective motion physics optimizer with noisy motion data remains largely unexplored. In this paper, we propose Morph, a Motion-Free physics optimization framework, consisting of a Motion Generator and a Motion Physics Refinement module, for enhancing physical plausibility without relying on expensive real-world motion data. Specifically, the motion generator is responsible for providing large-scale synthetic, noisy motion data, while the motion physics refinement module utilizes these synthetic data to learn a motion imitator within a physics simulator, enforcing physical constraints to project the noisy motions into a physically-plausible space. Additionally, we introduce a prior reward module to enhance the stability of the physics optimization process and generate smoother and more stable motions. These physically refined motions are then used to fine-tune the motion generator, further enhancing its capability. This collaborative training paradigm enables mutual enhancement between the motion generator and the motion physics refinement module, significantly improving practicality and robustness in real-world applications. Experiments on both text-to-motion and music-to-dance generation tasks demonstrate that our framework achieves state-of-the-art motion quality while improving physical plausibility drastically. Project page: https://interestingzhuo.github.io/Morph-Page/.