# PoseGPT: Quantization-based 3D Human Motion Generation and Forecasting

arXiv: https://arxiv.org/abs/2210.10542 · HTML: https://mlsanity.com/paper/2210.10542/

## Key facts

- Cited by 78 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 75 references that are in the map.
- First posted on arXiv 19 Oct 2022.

## Builds on (most cited first, 30 of 49)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (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)
- [Conditional Image Generation with PixelCNN Decoders](https://mlsanity.com/paper/1606.05328/) (2016)
- [Pixel Recurrent Neural Networks](https://mlsanity.com/paper/1601.06759/) (2016)
- [Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks](https://mlsanity.com/paper/1803.10892/) (2018)
- [VIBE: Video Inference for Human Body Pose and Shape Estimation](https://mlsanity.com/paper/1912.05656/) (2019)
- [Action-Conditioned 3D Human Motion Synthesis with Transformer VAE](https://mlsanity.com/paper/2104.05670/) (2021)
- [Action2Motion: Conditioned Generation of 3D Human Motions](https://mlsanity.com/paper/2007.15240/) (2020)
- [Reliable Fidelity and Diversity Metrics for Generative Models](https://mlsanity.com/paper/2002.09797/) (2020)
- [GRAB: A Dataset of Whole-Body Human Grasping of Objects](https://mlsanity.com/paper/2008.11200/) (2020)
- [On human motion prediction using recurrent neural networks](https://mlsanity.com/paper/1705.02445/) (2017)
- [HuMoR: 3D Human Motion Model for Robust Pose Estimation](https://mlsanity.com/paper/2105.04668/) (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)
- [A Note on the Inception Score](https://mlsanity.com/paper/1801.01973/) (2018)
- [Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory](https://mlsanity.com/paper/2203.13055/) (2022)
- [Deep Learning-Based Human Pose Estimation: A Survey](https://mlsanity.com/paper/2012.13392/) (2020)
- [Long-term Human Motion Prediction with Scene Context](https://mlsanity.com/paper/2007.03672/) (2020)
- [Scaling Autoregressive Video Models](https://mlsanity.com/paper/1906.02634/) (2019)
- [DLow: Diversifying Latent Flows for Diverse Human Motion Prediction](https://mlsanity.com/paper/2003.08386/) (2020)

## Built on by (most cited first, 30 of 78)

- [T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations](https://mlsanity.com/paper/2301.06052/) (2023)
- [MoMask: Generative Masked Modeling of 3D Human Motions](https://mlsanity.com/paper/2312.00063/) (2023)
- [OmniControl: Control Any Joint at Any Time for Human Motion Generation](https://mlsanity.com/paper/2310.08580/) (2023)
- [InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions](https://mlsanity.com/paper/2304.05684/) (2023)
- [Universal Humanoid Motion Representations for Physics-Based Control](https://mlsanity.com/paper/2310.04582/) (2023)
- [Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild](https://mlsanity.com/paper/2406.09905/) (2024)
- [HumanTOMATO: Text-aligned Whole-body Motion Generation](https://mlsanity.com/paper/2310.12978/) (2023)
- [Human Motion Generation: A Survey](https://mlsanity.com/paper/2307.10894/) (2023)
- [HumanMAC: Masked Motion Completion for Human Motion Prediction](https://mlsanity.com/paper/2302.03665/) (2023)
- [PromptHMR: Promptable Human Mesh Recovery](https://mlsanity.com/paper/2504.06397/) (2025)
- [InterMask: 3D Human Interaction Generation via Collaborative Masked Modeling](https://mlsanity.com/paper/2410.10010/) (2024)
- [THOR: Text to Human-Object Interaction Diffusion via Relation Intervention](https://mlsanity.com/paper/2403.11208/) (2024)
- [Hierarchical Generation of Human-Object Interactions with Diffusion Probabilistic Models](https://mlsanity.com/paper/2310.02242/) (2023)
- [QPGesture: Quantization-Based and Phase-Guided Motion Matching for Natural Speech-Driven Gesture Generation](https://mlsanity.com/paper/2305.11094/) (2023)
- [EgoLM: Multi-Modal Language Model of Egocentric Motions](https://mlsanity.com/paper/2409.18127/) (2024)
- [Interactive Humanoid: Online Full-Body Motion Reaction Synthesis with Social Affordance Canonicalization and Forecasting](https://mlsanity.com/paper/2312.08983/) (2023)
- [Revisit Human-Scene Interaction via Space Occupancy](https://mlsanity.com/paper/2312.02700/) (2023)
- [A Survey on Human Interaction Motion Generation](https://mlsanity.com/paper/2503.12763/) (2025)
- [CoMusion: Towards Consistent Stochastic Human Motion Prediction via Motion Diffusion](https://mlsanity.com/paper/2305.12554/) (2023)
- [MotionScript: Natural Language Descriptions for Expressive 3D Human Motions](https://mlsanity.com/paper/2312.12634/) (2023)
- [Stratified Avatar Generation from Sparse Observations](https://mlsanity.com/paper/2405.20786/) (2024)
- [From Isolated Islands to Pangea: Unifying Semantic Space for Human Action Understanding](https://mlsanity.com/paper/2304.00553/) (2023)
- [Language-guided Human Motion Synthesis with Atomic Actions](https://mlsanity.com/paper/2308.09611/) (2023)
- [Aligning Human Motion Generation with Human Perceptions](https://mlsanity.com/paper/2407.02272/) (2024)
- [Dance Like a Chicken: Low-Rank Stylization for Human Motion Diffusion](https://mlsanity.com/paper/2503.19557/) (2025)
- [UnifiedGesture: A Unified Gesture Synthesis Model for Multiple Skeletons](https://mlsanity.com/paper/2309.07051/) (2023)
- [X-Dancer: Expressive Music to Human Dance Video Generation](https://mlsanity.com/paper/2502.17414/) (2025)
- [HERO: Human Reaction Generation from Videos](https://mlsanity.com/paper/2503.08270/) (2025)
- [SocialGen: Modeling Multi-Human Social Interaction with Language Models](https://mlsanity.com/paper/2503.22906/) (2025)
- [Bridging the Gap between Human Motion and Action Semantics via Kinematic Phrases](https://mlsanity.com/paper/2310.04189/) (2023)

## Abstract (arXiv)

We address the problem of action-conditioned generation of human motion sequences. Existing work falls into two categories: forecast models conditioned on observed past motions, or generative models conditioned on action labels and duration only. In contrast, we generate motion conditioned on observations of arbitrary length, including none. To solve this generalized problem, we propose PoseGPT, an auto-regressive transformer-based approach which internally compresses human motion into quantized latent sequences. An auto-encoder first maps human motion to latent index sequences in a discrete space, and vice-versa. Inspired by the Generative Pretrained Transformer (GPT), we propose to train a GPT-like model for next-index prediction in that space; this allows PoseGPT to output distributions on possible futures, with or without conditioning on past motion. The discrete and compressed nature of the latent space allows the GPT-like model to focus on long-range signal, as it removes low-level redundancy in the input signal. Predicting discrete indices also alleviates the common pitfall of predicting averaged poses, a typical failure case when regressing continuous values, as the average of discrete targets is not a target itself. Our experimental results show that our proposed approach achieves state-of-the-art results on HumanAct12, a standard but small scale dataset, as well as on BABEL, a recent large scale MoCap dataset, and on GRAB, a human-object interactions dataset.