# MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation

arXiv: https://arxiv.org/abs/2401.11115 · HTML: https://mlsanity.com/paper/2401.11115/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 45 of its 54 references that are in the map.
- First posted on arXiv 20 Jan 2024.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 30 of 45)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [VIBE: Video Inference for Human Body Pose and Shape Estimation](https://mlsanity.com/paper/1912.05656/) (2019)
- [Executing your Commands via Motion Diffusion in Latent Space](https://mlsanity.com/paper/2212.04048/) (2022)
- [Jukebox: A Generative Model for Music](https://mlsanity.com/paper/2005.00341/) (2020)
- [Action-Conditioned 3D Human Motion Synthesis with Transformer VAE](https://mlsanity.com/paper/2104.05670/) (2021)
- [Semi-Supervised Learning with Deep Generative Models](https://mlsanity.com/paper/1406.5298/) (2014)
- [TEMOS: Generating diverse human motions from textual descriptions](https://mlsanity.com/paper/2204.14109/) (2022)
- [AI Choreographer: Music Conditioned 3D Dance Generation with AIST++](https://mlsanity.com/paper/2101.08779/) (2021)
- [Action2Motion: Conditioned Generation of 3D Human Motions](https://mlsanity.com/paper/2007.15240/) (2020)
- [TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts](https://mlsanity.com/paper/2207.01696/) (2022)
- [The KIT Motion-Language Dataset](https://mlsanity.com/paper/1607.03827/) (2016)
- [EDGE: Editable Dance Generation From Music](https://mlsanity.com/paper/2211.10658/) (2022)
- [Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory](https://mlsanity.com/paper/2203.13055/) (2022)
- [Character Controllers Using Motion VAEs](https://mlsanity.com/paper/2103.14274/) (2021)
- [Synthesis of Compositional Animations from Textual Descriptions](https://mlsanity.com/paper/2103.14675/) (2021)
- [Monocular Expressive Body Regression through Body-Driven Attention](https://mlsanity.com/paper/2008.09062/) (2020)
- [Human Motion Prediction via Spatio-Temporal Inpainting](https://mlsanity.com/paper/1812.05478/) (2018)
- [Ambient Diffusion: Learning Clean Distributions from Corrupted Data](https://mlsanity.com/paper/2305.19256/) (2023)
- [Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agents](https://mlsanity.com/paper/2101.11101/) (2021)
- [Learning to Generate Diverse Dance Motions with Transformer](https://mlsanity.com/paper/2008.08171/) (2020)

## Built on by (most cited first, 10 of 10)

- [Large Motion Model for Unified Multi-Modal Motion Generation](https://mlsanity.com/paper/2404.01284/) (2024)
- [Text-controlled Motion Mamba: Text-Instructed Temporal Grounding of Human Motion](https://mlsanity.com/paper/2404.11375/) (2024)
- [SCENIC: Scene-aware Semantic Navigation with Instruction-guided Control](https://mlsanity.com/paper/2412.15664/) (2024)
- [SceneMI: Motion In-betweening for Modeling Human-Scene Interactions](https://mlsanity.com/paper/2503.16289/) (2025)
- [Motion Synthesis with Sparse and Flexible Keyjoint Control](https://mlsanity.com/paper/2503.15557/) (2025)
- [FORCE: Physics-aware Human-object Interaction](https://mlsanity.com/paper/2403.11237/) (2024)
- [CrowdMoGen: Zero-Shot Text-Driven Collective Motion Generation](https://mlsanity.com/paper/2407.06188/) (2024)
- [PP-Motion: Physical-Perceptual Fidelity Evaluation for Human Motion Generation](https://mlsanity.com/paper/2508.08179/) (2025)
- [GIRAF: Towards Generalizable Human Interactions with Articulated Objects](https://mlsanity.com/paper/2607.07880/) (2026)
- [OpenDance: Multimodal Controllable 3D Dance Generation with Large-scale Internet Data](https://mlsanity.com/paper/2506.07565/) (2025)

## Abstract (arXiv)

Controllable generation of 3D human motions becomes an important topic as the world embraces digital transformation. Existing works, though making promising progress with the advent of diffusion models, heavily rely on meticulously captured and annotated (e.g., text) high-quality motion corpus, a resource-intensive endeavor in the real world. This motivates our proposed MotionMix, a simple yet effective weakly-supervised diffusion model that leverages both noisy and unannotated motion sequences. Specifically, we separate the denoising objectives of a diffusion model into two stages: obtaining conditional rough motion approximations in the initial T-T^* steps by learning the noisy annotated motions, followed by the unconditional refinement of these preliminary motions during the last T^* steps using unannotated motions. Notably, though learning from two sources of imperfect data, our model does not compromise motion generation quality compared to fully supervised approaches that access gold data. Extensive experiments on several benchmarks demonstrate that our MotionMix, as a versatile framework, consistently achieves state-of-the-art performances on text-to-motion, action-to-motion, and music-to-dance tasks. Project page: https://nhathoang2002.github.io/MotionMix-page/