# Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model

arXiv: https://arxiv.org/abs/2404.01862 · HTML: https://mlsanity.com/paper/2404.01862/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 63 of its 80 references that are in the map.
- First posted on arXiv 2 Apr 2024.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [Improved Techniques for Training Score-Based Generative Models](https://mlsanity.com/paper/2006.09011/) (2020)
- [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://mlsanity.com/paper/2310.04378/) (2023)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [First Order Motion Model for Image Animation](https://mlsanity.com/paper/2003.00196/) (2020)
- [Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation](https://mlsanity.com/paper/2311.17117/) (2023)
- [A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild](https://mlsanity.com/paper/2008.10010/) (2020)
- [VideoGPT: Video Generation using VQ-VAE and Transformers](https://mlsanity.com/paper/2104.10157/) (2021)
- [Generative Adversarial Networks: An Overview](https://mlsanity.com/paper/1710.07035/) (2017)
- [Image Inpainting for Irregular Holes Using Partial Convolutions](https://mlsanity.com/paper/1804.07723/) (2018)
- [MagicVideo: Efficient Video Generation With Latent Diffusion Models](https://mlsanity.com/paper/2211.11018/) (2022)
- [Faster Segment Anything: Towards Lightweight SAM for Mobile Applications](https://mlsanity.com/paper/2306.14289/) (2023)
- [Effective Whole-body Pose Estimation with Two-stages Distillation](https://mlsanity.com/paper/2307.15880/) (2023)

## Built on by (most cited first, 30 of 35)

- [CamI2V: Camera-Controlled Image-to-Video Diffusion Model](https://mlsanity.com/paper/2410.15957/) (2024)
- [RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control](https://mlsanity.com/paper/2502.10059/) (2025)
- [TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation](https://mlsanity.com/paper/2410.04221/) (2024)
- [A Comprehensive Survey on Human Video Generation: Challenges, Methods, and Insights](https://mlsanity.com/paper/2407.08428/) (2024)
- [Lodge++: High-quality and Long Dance Generation with Vivid Choreography Patterns](https://mlsanity.com/paper/2410.20389/) (2024)
- [EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation](https://mlsanity.com/paper/2504.09209/) (2025)
- [Mitigating Error Accumulation in Co-Speech Motion Generation via Global Rotation Diffusion and Multi-Level Constraints](https://mlsanity.com/paper/2511.10076/) (2025)
- [AudCast: Audio-Driven Human Video Generation by Cascaded Diffusion Transformers](https://mlsanity.com/paper/2503.19824/) (2025)
- [LiON-LoRA: Rethinking LoRA Fusion to Unify Controllable Spatial and Temporal Generation for Video Diffusion](https://mlsanity.com/paper/2507.05678/) (2025)
- [PersonaGesture: Single-Reference Co-Speech Gesture Personalization for Unseen Speakers](https://mlsanity.com/paper/2605.06064/) (2026)
- [3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation](https://mlsanity.com/paper/2602.03796/) (2026)
- [Video Motion Graphs](https://mlsanity.com/paper/2503.20218/) (2025)
- [Stereo-Talker: Audio-driven 3D Human Synthesis with Prior-Guided Mixture-of-Experts](https://mlsanity.com/paper/2410.23836/) (2024)
- [View-Consistent Diffusion Representations for 3D-Consistent Video Generation](https://mlsanity.com/paper/2511.18991/) (2025)
- [Kling-MotionControl Technical Report](https://mlsanity.com/paper/2603.03160/) (2026)
- [Cosh-DiT: Co-Speech Gesture Video Synthesis via Hybrid Audio-Visual Diffusion Transformers](https://mlsanity.com/paper/2503.09942/) (2025)
- [OmniMotion: Multimodal Motion Generation with Continuous Masked Autoregression](https://mlsanity.com/paper/2510.14954/) (2025)
- [AnyLogo: Symbiotic Subject-Driven Diffusion System with Gemini Status](https://mlsanity.com/paper/2409.17740/) (2024)
- [MMGT: Motion Mask Guided Two-Stage Network for Co-Speech Gesture Video Generation](https://mlsanity.com/paper/2505.23120/) (2025)
- [Multi-human Interactive Talking Dataset](https://mlsanity.com/paper/2508.03050/) (2025)
- [SimInterview: Transforming Business Education through Large Language Model-Based Simulated Multilingual Interview Training System](https://mlsanity.com/paper/2508.11873/) (2025)
- [Self-Supervised Learning of Deviation in Latent Representation for Co-speech Gesture Video Generation](https://mlsanity.com/paper/2409.17674/) (2024)
- [OLMD: Orientation-aware Long-term Motion Decoupling for Continuous Sign Language Recognition](https://mlsanity.com/paper/2503.08205/) (2025)
- [Audio-driven Gesture Generation via Deviation Feature in the Latent Space](https://mlsanity.com/paper/2503.21616/) (2025)
- [Democratizing High-Fidelity Co-Speech Gesture Video Generation](https://mlsanity.com/paper/2507.06812/) (2025)
- [ReactMotion: Generating Reactive Listener Motions from Speaker Utterance](https://mlsanity.com/paper/2603.15083/) (2026)
- [SubjectAnchor: Subject-Aware Memory-to-Video for Multi-Shot Storytelling](https://mlsanity.com/paper/2609.34502/) (2026)
- [Co-speech Gesture Video Generation via Motion-Based Graph Retrieval](https://mlsanity.com/paper/2512.02576/) (2025)
- [Gesture2Speech: How Far Can Hand Movements Shape Expressive Speech?](https://mlsanity.com/paper/2603.19831/) (2026)
- [Mamba-Enhanced Implicit Motion Learning for Audio-Driven Portrait Animation](https://mlsanity.com/paper/2606.03402/) (2026)

## Abstract (arXiv)

Co-speech gestures, if presented in the lively form of videos, can achieve superior visual effects in human-machine interaction. While previous works mostly generate structural human skeletons, resulting in the omission of appearance information, we focus on the direct generation of audio-driven co-speech gesture videos in this work. There are two main challenges: 1) A suitable motion feature is needed to describe complex human movements with crucial appearance information. 2) Gestures and speech exhibit inherent dependencies and should be temporally aligned even of arbitrary length. To solve these problems, we present a novel motion-decoupled framework to generate co-speech gesture videos. Specifically, we first introduce a well-designed nonlinear TPS transformation to obtain latent motion features preserving essential appearance information. Then a transformer-based diffusion model is proposed to learn the temporal correlation between gestures and speech, and performs generation in the latent motion space, followed by an optimal motion selection module to produce long-term coherent and consistent gesture videos. For better visual perception, we further design a refinement network focusing on missing details of certain areas. Extensive experimental results show that our proposed framework significantly outperforms existing approaches in both motion and video-related evaluations. Our code, demos, and more resources are available at https://github.com/thuhcsi/S2G-MDDiffusion.