Dense Policy: Bidirectional Autoregressive Learning of Actions (2D Version)

Authors: <a href="https://selen-suyue.github.io" style="color: maroon; text-decoration: none; font-style: italic;">Yue Su*</a>, <a href="https://scholar.google.com/citations?user=WurpqEMAAAAJ&hl=en" style="color: maroon; text-decoration: none; font-style: italic;">Xinyu Zhan*</a>, <a href="https://tonyfang.net/" style="color: maroon; text-decoration: none; font-style: italic;">Hongjie Fang</a>, <a href="https://hanxue.me/" style="color: maroon; text-decoration: none; font-style: italic;">Han Xue</a>, <a href="https://fang-haoshu.github.io/" style="color: maroon; text-decoration: none; font-style: italic;">Haoshu Fang</a>, <a href="https://dirtyharrylyl.github.io/" style="color: maroon; text-decoration: none; font-style: italic;">Yong-Lu Li</a>, <a href="https://www.mvig.org/" style="color: maroon; text-decoration: none; font-style: italic;">Cewu Lu</a>, <a href="https://lixiny.github.io/" style="color: maroon; text-decoration: none; font-style: italic;">Lixin Yang†</a>

🛫 Getting Started

You can also refer 3D Dense Policy Code.

💻 Installation

Please following the installation guide to install the dsp conda environments and the dependencies, as well as the real robot environments. Also, remember to adjust the constant parameters in dataset/constants.py and utils/constants.py according to your own environment.

📷 Calibration

Please calibrate the camera(s) with the robot before data collection and evaluation to ensure correct spatial transformations between camera(s) and the robot. Please refer to calibration guide for more details.

🛢️ Data Collection

Data will be released soon.

🧑🏻‍💻 Training

conda activate dsp
bash train.sh

🤖 Evaluation

Please follow the deployment guide to modify the evaluation script.

Modify the arguments in eval.sh, then

conda activate dsp
bash eval.sh

✍️ Citation

@InProceedings{DSP,
    author    = {Su, Yue and Zhan, Xinyu and Fang, Hongjie and Xue, Han and Fang, Hao-Shu and Li, Yong-Lu and Lu, Cewu and Yang, Lixin},
    title     = {Dense Policy: Bidirectional Autoregressive Learning of Actions},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2025},
    pages     = {14486-14495}
}

📃 License

<p xmlns:cc="http://creativecommons.org/ns#" xmlns:dct="http://purl.org/dc/terms/"><a property="dct:title" rel="" rel="cc:attributionURL" href="https://selen-suyue.github.io/DspNet/">DSP</a> is licensed under <a href="https://creativecommons.org/licenses/by-nc-sa/4.0/?ref=chooser-v1" target="_blank" rel="license noopener noreferrer" style="display:inline-block;">CC BY-NC-SA 4.0<img style="height:22px!important;margin-left:3px;vertical-align:text-bottom;" src="https://mirrors.creativecommons.org/presskit/icons/cc.svg?ref=chooser-v1" alt=""><img style="height:22px!important;margin-left:3px;vertical-align:text-bottom;" src="https://mirrors.creativecommons.org/presskit/icons/by.svg?ref=chooser-v1" alt=""><img style="height:22px!important;margin-left:3px;vertical-align:text-bottom;" src="https://mirrors.creativecommons.org/presskit/icons/nc.svg?ref=chooser-v1" alt=""><img style="height:22px!important;margin-left:3px;vertical-align:text-bottom;" src="https://mirrors.creativecommons.org/presskit/icons/sa.svg?ref=chooser-v1" alt=""></a></p>