# T2M-HiFiGPT: Generating High Quality Human Motion from Textual Descriptions with Residual Discrete Representations

arXiv: https://arxiv.org/abs/2312.10628 · HTML: https://mlsanity.com/paper/2312.10628/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 60 of its 84 references that are in the map.
- First posted on arXiv 17 Dec 2023.

## Builds on (most cited first, 30 of 60)

- [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)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [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)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [AudioLM: a Language Modeling Approach to Audio Generation](https://mlsanity.com/paper/2209.03143/) (2022)
- [T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations](https://mlsanity.com/paper/2301.06052/) (2023)
- [Sequence Level Training with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06732/) (2015)
- [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)
- [MoCoGAN: Decomposing Motion and Content for Video Generation](https://mlsanity.com/paper/1707.04993/) (2017)
- [Action-Conditioned 3D Human Motion Synthesis with Transformer VAE](https://mlsanity.com/paper/2104.05670/) (2021)
- [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)
- [MusicLM: Generating Music From Text](https://mlsanity.com/paper/2301.11325/) (2023)
- [Action2Motion: Conditioned Generation of 3D Human Motions](https://mlsanity.com/paper/2007.15240/) (2020)
- [MotionCLIP: Exposing Human Motion Generation to CLIP Space](https://mlsanity.com/paper/2203.08063/) (2022)
- [TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts](https://mlsanity.com/paper/2207.01696/) (2022)
- [SinGAN: Learning a Generative Model from a Single Natural Image](https://mlsanity.com/paper/1905.01164/) (2019)

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

- [MotionChain: Conversational Motion Controllers via Multimodal Prompts](https://mlsanity.com/paper/2404.01700/) (2024)
- [Contextual Gesture: Co-Speech Gesture Video Generation through Context-aware Gesture Representation](https://mlsanity.com/paper/2502.07239/) (2025)
- [Versatile Multimodal Controls for Expressive Talking Human Animation](https://mlsanity.com/paper/2503.08714/) (2025)
- [Multimodal Generative AI with Autoregressive LLMs for Human Motion Understanding and Generation: A Way Forward](https://mlsanity.com/paper/2506.03191/) (2025)
- [Embracing Aleatoric Uncertainty: Generating Diverse 3D Human Motion](https://mlsanity.com/paper/2508.20604/) (2025)
- [PMG: Progressive Motion Generation via Sparse Anchor Postures Curriculum Learning](https://mlsanity.com/paper/2504.16722/) (2025)
- [Making Pose Representations More Expressive and Disentangled via Residual Vector Quantization](https://mlsanity.com/paper/2508.14561/) (2025)
- [A Survey of Body and Face Motion: Datasets, Performance Evaluation Metrics and Generative Techniques](https://mlsanity.com/paper/2512.09005/) (2025)
- [MoRL: Reinforced Reasoning for Unified Motion Understanding and Generation](https://mlsanity.com/paper/2602.14534/) (2026)
- [A Plug-and-Play 2D Motion Interface for Real-World Motion Language Models](https://mlsanity.com/paper/2608.15984/) (2026)

## Abstract (arXiv)

In this study, we introduce T2M-HiFiGPT, a novel conditional generative framework for synthesizing human motion from textual descriptions. This framework is underpinned by a Residual Vector Quantized Variational AutoEncoder (RVQ-VAE) and a double-tier Generative Pretrained Transformer (GPT) architecture. We demonstrate that our CNN-based RVQ-VAE is capable of producing highly accurate 2D temporal-residual discrete motion representations. Our proposed double-tier GPT structure comprises a temporal GPT and a residual GPT. The temporal GPT efficiently condenses information from previous frames and textual descriptions into a 1D context vector. This vector then serves as a context prompt for the residual GPT, which generates the final residual discrete indices. These indices are subsequently transformed back into motion data by the RVQ-VAE decoder. To mitigate the exposure bias issue, we employ straightforward code corruption techniques for RVQ and a conditional dropout strategy, resulting in enhanced synthesis performance. Remarkably, T2M-HiFiGPT not only simplifies the generative process but also surpasses existing methods in both performance and parameter efficacy, including the latest diffusion-based and GPT-based models. On the HumanML3D and KIT-ML datasets, our framework achieves exceptional results across nearly all primary metrics. We further validate the efficacy of our framework through comprehensive ablation studies on the HumanML3D dataset, examining the contribution of each component. Our findings reveal that RVQ-VAE is more adept at capturing precise 3D human motion with comparable computational demand compared to its VQ-VAE counterparts. As a result, T2M-HiFiGPT enables the generation of human motion with significantly increased accuracy, outperforming recent state-of-the-art approaches such as T2M-GPT and Att-T2M.