Zum Inhalt springen
ModelAufgelistetExtern
Herunterladen

Camera Depth Model L515

This repository contains the Camera Depth Models (CDMs) from the paper: Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots.

ArtOtherVersionCdm l515BBewertung

Modellquelle

Art
Other
Dateigröße
5,09 GB
Version
vCdm l515
Aktualisiert
28. Okt. 2026
Quelle
Hugging Face

Quellenbeschreibung

Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots

This repository contains the Camera Depth Models (CDMs) from the paper: Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots.

Overview

Camera Depth Models (CDMs) are proposed as a simple plugin for daily-use depth cameras. They take RGB images and raw depth signals as input and output denoised, accurate metric depth. This enables policies trained purely in simulation to transfer directly to real robots by providing nearly simulation-level accurate depth perception.

Links

Usage

For detailed installation instructions and further usage examples, please refer to the CDM documentation in the GitHub repository.

CDM Inference Example

To run depth inference on RGB-D camera data, use the following command:

cd cdm
python infer.py \
    --encoder vitl \
    --model-path /path/to/model.pth \
    --rgb-image /path/to/rgb.jpg \
    --depth-image /path/to/depth.png \
    --output result.png

Citation

If you use this work in your research, please cite:

@article{liu2025manipulation,
  title={Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots},
  author={Liu, Minghuan and Zhu, Zhengbang and Han, Xiaoshen and Hu, Peng and Lin, Haotong and 
          Li, Xinyao and Chen, Jingxiao and Xu, Jiafeng and Yang, Yichu and Lin, Yunfeng and 
          Li, Xinghang and Yu, Yong and Zhang, Weinan and Kong, Tao and Kang, Bingyi},
  journal={arXiv preprint},
  year={2025}
}

Quellen

1 Quelle
Hugging FacePrimärVersion f9a13d79e8941da60bcfcefb3b16121cca21d782
huggingface.co/depth-anything/camera-depth-model-l515/tree/f9a13d79e8941da60bcfcefb3b16121cca21d782

Verifiziert 28. Okt.

Modellartefakte

1 Artefakt

cdm_l515.ckpt

ckpt · 5,09 GB · SHA-256 5a909784efe0…29ed · Hugging Face

Download file

Quellenauszüge

2 Auszüge

--- license: cc-by-nc-4.0 pipeline_tag: depth-estimation --- # Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots This repository contains the Camera Depth Models (CDMs) from the paper: [Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots](https://huggingface.co/papers/2509.02530). ## Overview Camera Depth Models (CDMs) are proposed as a simple plugin for daily-use depth cameras. They take RGB images and raw depth signals as input and output denoised, accurate metric depth. This enables policies trained purely in simulation to transfer directly to real robots by providing nearly simulation-level accurate depth perception. ## Links * **Project Page**: [https://manipulation-as-in-simulation.github.io](https://manipulation-as-in-simulation.github.io/) * **Code Repository**: [https://github.com/ByteDance-Seed/manip-as-in-sim-suite](https://github.com/ByteDance-Seed/manip-as-in-sim-suite) ## Usage For detailed installation instructions and further usage examples, please refer to the [CDM documentation in the GitHub repository](https://github.com/ByteDance-Seed/manip-as-in-sim-suite/tree/main/cdm). ### CDM Inference Example To run depth inference on RGB-D camera data, use the following command: ```bash cd cdm python infer.py \ --encoder vitl \ --model-path /path/to/model.pth \ --rgb-image /path/to/rgb.jpg \ --depth-image /path/to/depth.png \ --output result.png ``` ## Citation If you use this work in your research, please cite: ```bibtex @article{liu2025manipulation, title={Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots}, author={Liu, Minghuan and Zhu, Zhengbang and Han, Xiaoshen and Hu, Peng and Lin, Haotong and Li, Xinyao and Chen, Jingxiao and Xu, Jiafeng and Yang, Yichu and Lin, Yunfeng and Li, Xinghang and Yu, Yong and Zhang, Weinan and Kong, Tao and Kang, Bingyi}, journal={arXiv preprint}, year={2025} } ```

Source context: 0 downloads · 3 likes · Pipeline depth-estimation · Repo depth-anything/camera-depth-model-l515