# MotionCLIP: Exposing Human Motion Generation to CLIP Space

arXiv: https://arxiv.org/abs/2203.08063 · HTML: https://mlsanity.com/paper/2203.08063/

## Key facts

- Cited by 406 papers in the map (data through 7 Oct 2026).
- Builds on 32 of its 50 references that are in the map.
- First posted on arXiv 15 Mar 2022.

## Builds on (most cited first, 30 of 32)

- [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)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [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)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery](https://mlsanity.com/paper/2103.17249/) (2021)
- [CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval](https://mlsanity.com/paper/2104.08860/) (2021)
- [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019)
- [Action-Conditioned 3D Human Motion Synthesis with Transformer VAE](https://mlsanity.com/paper/2104.05670/) (2021)
- [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)
- [CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields](https://mlsanity.com/paper/2112.05139/) (2021)
- [AudioCLIP: Extending CLIP to Image, Text and Audio](https://mlsanity.com/paper/2106.13043/) (2021)
- [The KIT Motion-Language Dataset](https://mlsanity.com/paper/1607.03827/) (2016)
- [Text2Mesh: Text-Driven Neural Stylization for Meshes](https://mlsanity.com/paper/2112.03221/) (2021)
- [BABEL: Bodies, Action and Behavior with English Labels](https://mlsanity.com/paper/2106.09696/) (2021)
- [Language2Pose: Natural Language Grounded Pose Forecasting](https://mlsanity.com/paper/1907.01108/) (2019)
- [CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation](https://mlsanity.com/paper/2110.02624/) (2021)
- [CLIP2Video: Mastering Video-Text Retrieval via Image CLIP](https://mlsanity.com/paper/2106.11097/) (2021)
- [Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders](https://mlsanity.com/paper/1611.02648/) (2016)
- [CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders](https://mlsanity.com/paper/2106.14843/) (2021)
- [Unpaired Motion Style Transfer from Video to Animation](https://mlsanity.com/paper/2005.05751/) (2020)
- [Multi-Person 3D Motion Prediction with Multi-Range Transformers](https://mlsanity.com/paper/2111.12073/) (2021)
- [Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networks](https://mlsanity.com/paper/1705.06400/) (2017)
- [Rhythm is a Dancer: Music-Driven Motion Synthesis with Global Structure](https://mlsanity.com/paper/2111.12159/) (2021)

## Built on by (most cited first, 30 of 406)

- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [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)
- [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)
- [Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures](https://mlsanity.com/paper/2211.07600/) (2022)
- [MoMask: Generative Masked Modeling of 3D Human Motions](https://mlsanity.com/paper/2312.00063/) (2023)
- [Human Motion Diffusion as a Generative Prior](https://mlsanity.com/paper/2303.01418/) (2023)
- [ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model](https://mlsanity.com/paper/2304.01116/) (2023)
- [OmniControl: Control Any Joint at Any Time for Human Motion Generation](https://mlsanity.com/paper/2310.08580/) (2023)
- [MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis](https://mlsanity.com/paper/2212.04495/) (2022)
- [InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions](https://mlsanity.com/paper/2304.05684/) (2023)
- [Teaching CLIP to Count to Ten](https://mlsanity.com/paper/2302.12066/) (2023)
- [InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion](https://mlsanity.com/paper/2308.16905/) (2023)
- [TEACH: Temporal Action Composition for 3D Humans](https://mlsanity.com/paper/2209.04066/) (2022)
- [MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model](https://mlsanity.com/paper/2404.19759/) (2024)
- [GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents](https://mlsanity.com/paper/2303.14613/) (2023)
- [SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models](https://mlsanity.com/paper/2210.05861/) (2022)
- [MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators](https://mlsanity.com/paper/2306.10900/) (2023)
- [CG-HOI: Contact-Guided 3D Human-Object Interaction Generation](https://mlsanity.com/paper/2311.16097/) (2023)
- [MMM: Generative Masked Motion Model](https://mlsanity.com/paper/2312.03596/) (2023)
- [IMos: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactions](https://mlsanity.com/paper/2212.07555/) (2022)
- [Delta Denoising Score](https://mlsanity.com/paper/2304.07090/) (2023)
- [AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism](https://mlsanity.com/paper/2309.00796/) (2023)
- [Motion Mamba: Efficient and Long Sequence Motion Generation](https://mlsanity.com/paper/2403.07487/) (2024)
- [Synthesizing Diverse Human Motions in 3D Indoor Scenes](https://mlsanity.com/paper/2305.12411/) (2023)
- [Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild](https://mlsanity.com/paper/2406.09905/) (2024)
- [Controllable Human-Object Interaction Synthesis](https://mlsanity.com/paper/2312.03913/) (2023)
- [FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing](https://mlsanity.com/paper/2312.15004/) (2023)

## Abstract (arXiv)

We introduce MotionCLIP, a 3D human motion auto-encoder featuring a latent embedding that is disentangled, well behaved, and supports highly semantic textual descriptions. MotionCLIP gains its unique power by aligning its latent space with that of the Contrastive Language-Image Pre-training (CLIP) model. Aligning the human motion manifold to CLIP space implicitly infuses the extremely rich semantic knowledge of CLIP into the manifold. In particular, it helps continuity by placing semantically similar motions close to one another, and disentanglement, which is inherited from the CLIP-space structure. MotionCLIP comprises a transformer-based motion auto-encoder, trained to reconstruct motion while being aligned to its text label's position in CLIP-space. We further leverage CLIP's unique visual understanding and inject an even stronger signal through aligning motion to rendered frames in a self-supervised manner. We show that although CLIP has never seen the motion domain, MotionCLIP offers unprecedented text-to-motion abilities, allowing out-of-domain actions, disentangled editing, and abstract language specification. For example, the text prompt "couch" is decoded into a sitting down motion, due to lingual similarity, and the prompt "Spiderman" results in a web-swinging-like solution that is far from seen during training. In addition, we show how the introduced latent space can be leveraged for motion interpolation, editing and recognition.