# CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos

arXiv: https://arxiv.org/abs/2601.10632 · HTML: https://mlsanity.com/paper/2601.10632/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 115 of its 124 references that are in the map.
- First posted on arXiv 15 Jan 2026.

## Builds on (most cited first, 30 of 115)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [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)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)
- [Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation](https://mlsanity.com/paper/2311.17117/) (2023)
- [SyncDreamer: Generating Multiview-consistent Images from a Single-view Image](https://mlsanity.com/paper/2309.03453/) (2023)
- [T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations](https://mlsanity.com/paper/2301.06052/) (2023)
- [Executing your Commands via Motion Diffusion in Latent Space](https://mlsanity.com/paper/2212.04048/) (2022)
- [MotionGPT: Human Motion as a Foreign Language](https://mlsanity.com/paper/2306.14795/) (2023)
- [VACE: All-in-One Video Creation and Editing](https://mlsanity.com/paper/2503.07598/) (2025)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [MoMask: Generative Masked Modeling of 3D Human Motions](https://mlsanity.com/paper/2312.00063/) (2023)
- [The KIT Motion-Language Dataset](https://mlsanity.com/paper/1607.03827/) (2016)
- [VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness](https://mlsanity.com/paper/2503.21755/) (2025)
- [Effective Whole-body Pose Estimation with Two-stages Distillation](https://mlsanity.com/paper/2307.15880/) (2023)

## Built on by (most cited first, 6 of 6)

- [UMO: Unified In-Context Learning Unlocks Motion Foundation Model Priors](https://mlsanity.com/paper/2603.15975/) (2026)
- [AnyAct: Towards Human Reenactment of Character Motion From Video](https://mlsanity.com/paper/2605.15497/) (2026)
- [Human-Centric Intelligence in the Era of Foundation Models: A Survey](https://mlsanity.com/paper/2608.18184/) (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)
- [World2Motion: Turning Video World Models into 3D Human Motion Generators](https://mlsanity.com/paper/2609.37004/) (2026)
- [PURE: Refining Feed-forward 3D Reconstruction with Unlabeled Post-training](https://mlsanity.com/paper/2610.14698/) (2026)

## Abstract (arXiv)

In this paper, we find that the generation of 3D human motions and 2D human videos is intrinsically coupled. 3D motions provide the structural prior for plausibility and consistency in videos, while pre-trained video models offer strong generalization capabilities for motions. Based on this, we present CoMoVi, a co-generative framework that generates 3D human motions and videos synchronously within a single diffusion denoising loop. However, since the 3D human motions and the 2D human-centric videos have a modality gap between each other, we propose to project the 3D human motion into an effective 2D human motion representation that effectively aligns with the 2D videos. Then, we design a dual-branch diffusion model to couple human motion and the video generation process with mutual feature interaction and 3D-2D cross attentions. To train and evaluate our model, we curate CoMoVi-Dataset, a large-scale real-world human video dataset with text and motion annotations, covering diverse and challenging human motions. Extensive experiments demonstrate that our method generates high-quality 3D human motion with a better generalization ability and that our method can generate high-quality human-centric videos without external motion references.