# MoSA: Motion-Coherent Human Video Generation via Structure-Appearance Decoupling

arXiv: https://arxiv.org/abs/2508.17404 · HTML: https://mlsanity.com/paper/2508.17404/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 63 of its 75 references that are in the map.
- First posted on arXiv 24 Aug 2025.

## Builds on (most cited first, 30 of 63)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation](https://mlsanity.com/paper/2311.17117/) (2023)
- [ModelScope Text-to-Video Technical Report](https://mlsanity.com/paper/2308.06571/) (2023)
- [T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations](https://mlsanity.com/paper/2301.06052/) (2023)
- [VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models](https://mlsanity.com/paper/2401.09047/) (2024)
- [Executing your Commands via Motion Diffusion in Latent Space](https://mlsanity.com/paper/2212.04048/) (2022)
- [MoMask: Generative Masked Modeling of 3D Human Motions](https://mlsanity.com/paper/2312.00063/) (2023)
- [PhysDiff: Physics-Guided Human Motion Diffusion Model](https://mlsanity.com/paper/2212.02500/) (2022)
- [The KIT Motion-Language Dataset](https://mlsanity.com/paper/1607.03827/) (2016)
- [Effective Whole-body Pose Estimation with Two-stages Distillation](https://mlsanity.com/paper/2307.15880/) (2023)
- [Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance](https://mlsanity.com/paper/2403.14781/) (2024)
- [CelebV-HQ: A Large-Scale Video Facial Attributes Dataset](https://mlsanity.com/paper/2207.12393/) (2022)
- [Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset](https://mlsanity.com/paper/2307.00818/) (2023)
- [CogVLM2: Visual Language Models for Image and Video Understanding](https://mlsanity.com/paper/2408.16500/) (2024)
- [SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow](https://mlsanity.com/paper/2405.14793/) (2024)
- [Identity-Preserving Text-to-Video Generation by Frequency Decomposition](https://mlsanity.com/paper/2411.17440/) (2024)

## Built on by (most cited first, 4 of 4)

- [DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation](https://mlsanity.com/paper/2511.19365/) (2025)
- [CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos](https://mlsanity.com/paper/2601.10632/) (2026)
- [Marionette: Predicting World States, Rendering Geometry, Painting Appearance](https://mlsanity.com/paper/2608.14530/) (2026)
- [All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation](https://mlsanity.com/paper/2609.27901/) (2026)

## Abstract (arXiv)

Existing video generation models predominantly emphasize appearance fidelity while exhibiting limited ability to synthesize complex human motions, such as whole-body movements, long-range dynamics, and fine-grained human-environment interactions. This often leads to unrealistic or physically implausible movements with inadequate structural coherence. To conquer these challenges, we propose MoSA, which decouples the process of human video generation into two components, i.e., structure generation and appearance generation. MoSA first employs a 3D structure transformer to generate a human motion sequence from the text prompt. The remaining video appearance is then synthesized under the guidance of this structural sequence. We achieve fine-grained control over the sparse human structures by introducing Human-Aware Dynamic Control modules with a dense tracking constraint during training. The modeling of human-environment interactions is improved through the proposed contact constraint. Those two components work comprehensively to ensure the structural and appearance fidelity across the generated videos. This paper also contributes a large-scale human video dataset, which features more complex and diverse motions than existing human video datasets. We conduct comprehensive comparisons between MoSA and a variety of approaches, including general video generation models, human video generation models, and human animation models. Experiments demonstrate that MoSA substantially outperforms existing approaches across the majority of evaluation metrics.