---
license: cc-by-nc-sa-4.0
pipeline_tag: text-to-3d
---

# <img src="https://huggingface.co/AIGeeksGroup/ReMoMask/resolve/main/assets/remomask_logo.png" alt="logo" width="30"/> ReMoMask: Retrieval-Augmented Masked Motion Generation

This is the official repository for the paper [ReMoMask: Retrieval-Augmented Masked Motion Generation](https://huggingface.co/papers/2508.02605).

-   📚 [Paper](https://huggingface.co/papers/2508.02605)
-   🌐 [Project Page](https://aigeeksgroup.github.io/ReMoMask/)
-   💻 [Code](https://github.com/AIGeeksGroup/ReMoMask)

https://github.com/user-attachments/assets/3f29c0c5-abb8-4fd1-893c-48ac82b79532

## Abstract

Text-to-Motion (T2M) generation aims to synthesize realistic and semantically aligned human motion sequences from natural language descriptions. However, current approaches face dual challenges: Generative models (e.g., diffusion models) suffer from limited diversity, error accumulation, and physical implausibility, while Retrieval-Augmented Generation (RAG) methods exhibit diffusion inertia, partial-mode collapse, and asynchronous artifacts. To address these limitations, we propose ReMoMask, a unified framework integrating three key innovations: 1) A Bidirectional Momentum Text-Motion Model decouples negative sample scale from batch size via momentum queues, substantially improving cross-modal retrieval precision; 2) A Semantic Spatio-temporal Attention mechanism enforces biomechanical constraints during part-level fusion to eliminate asynchronous artifacts; 3) RAG-Classier-Free Guidance incorporates minor unconditional generation to enhance generalization. Built upon MoMask's RVQ-VAE, ReMoMask efficiently generates temporally coherent motions in minimal steps. Extensive experiments on standard benchmarks demonstrate the state-of-the-art performance of ReMoMask, achieving a 3.88% and 10.97% improvement in FID scores on HumanML3D and KIT-ML, respectively, compared to the previous SOTA method RAG-T2M.

## Framework

An overview of the ReMoMask framework:

![framework](https://github.com/AIGeeksGroup/ReMoMask/raw/main/assets/framework.png)

## Sample Usage

To run a local demo for motion generation, you can use the provided `demo.py` script from the GitHub repository.

First, ensure you have the environment set up as described in the [GitHub repository's Prerequisite section](https://github.com/AIGeeksGroup/ReMoMask#prerequisite).

Then, run the demo with a text prompt:
```bash
python demo.py --gpu_id 0 --ext exp1 --text_prompt "A person is walking on a circle." --checkpoints_dir logs --dataset_name humanml3d --mtrans_name pretrain_mtrans --rtrans_name pretrain_rtrans
# change pretrain_mtrans and pretrain_rtrans to your mtrans and rtrans after your training done
```
- `--repeat_times`: number of replications for generation, default `1`.
- `--motion_length`: specify the number of poses for generation.

The output will be saved in `./outputs/exp1/`.

## Citation

If you find our work helpful or inspiring, please feel free to cite it.

```bibtex
@article{li2025remomask,
  title={ReMoMask: Retrieval-Augmented Masked Motion Generation},
  author={Li, Zhengdao and Wang, Siheng and Zhang, Zeyu and Tang, Hao},
  journal={arXiv preprint arXiv:2508.02605},
  year={2025}
}
```