xyz-ibd

A High-precision Bin-picking Dataset for Object 6D pose estimation and Monocular Depth Estimation

https://github.com/demianhj/xyz-ibd

Science Score: 54.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
○
DOI references
✓
Academic publication links
Links to: arxiv.org
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (11.2%) to scientific vocabulary

Last synced: 6 months ago · JSON representation ·

Repository

A High-precision Bin-picking Dataset for Object 6D pose estimation and Monocular Depth Estimation

Basic Info

Host: GitHub
Owner: demianhj
License: gpl-3.0
Language: Python
Default Branch: main
Size: 121 MB

Statistics

Stars: 4
Watchers: 1
Forks: 1
Open Issues: 1
Releases: 0

Created 10 months ago · Last pushed 9 months ago

Metadata Files

Readme Changelog Contributing License Citation

XYZ-IBD: A High-precision Bin-picking Dataset for Object 6D Pose Estimation Capturing Real-world Industrial Complexity

Welcome to the official repository of XYZ-IBD, a bin-picking dataset that captures real-world industrial complexity for 6D pose estimation.

🔥 Note in this repo, we provide the Docker usage for our bin-picking simulation rendering. The code is based on the BlenderProc.

📦 Dataset Access

🔗 Project Page: xyz-ibd.github.io/XYZ-IBD
🤗 Hugging Face: bop-benchmark/xyzibd
📄 Full Paper: Arxiv

🏆 Ongoing Challenges and Workshops

🚀 Baseline Implementations

We provide reference implementations to kick-start research and benchmarking. Please refer to the baseline repository for the running details.

🛠️ Data Processing & Evaluation

📊 BOP Toolkit Integration
XYZ-IBD is prepared with BOP format(see here for the data format details), and is fully compatible with the bop_toolkit for:
- Data loading and visualization
- Evaluation on BOP Metrics
📊 2D Detection and 6D Pose Evaluation Server
Submit your predictions for evaluation on the official BOP server:
https://bop.felk.cvut.cz/login/?next=/sub_upload/
📊 Monocular Depth Evaluation
Participate in monocular depth leaderboard on Codalab:
https://codalab.lisn.upsaclay.fr/competitions/22870

Docker usage for our bin-picking simulation rendering

Build Docker

python cd docker docker build -t "render_xyz_synthetic" .

Run Docker

```python docker run --gpus all renderxyzsynthetic cd "examples\datasets\deep-tote"

Modify the OUTPUT_DIR and OBJECT FILE in config.yaml to your custom path before run scripts!

Generate the whole synthetic dataset for all objects

blenderproc run render.py --config=config.yaml

Generate the synthetic dataset for specific object

blenderproc run custom.py --config=configphotoneoqiuxiao1.yaml

Post Process the synthetic dataset to BOP Format

blenderproc run genmasks.py --config=configphotoneo_qiuxiao1.yaml ```

Citation

If you find this dataset helpful, please cite this paper @misc{huang2025xyzibdhighprecisionbinpickingdataset, title={XYZ-IBD: High-precision Bin-picking Dataset for Object 6D Pose Estimation Capturing Real-world Industrial Complexity}, author={Junwen Huang and Jizhong Liang and Jiaqi Hu and Martin Sundermeyer and Peter KT Yu and Nassir Navab and Benjamin Busam}, year={2025}, eprint={2506.00599}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2506.00599}, }

📫 Contact

For questions, issues, or collaboration inquiries, feel free to open an issue or reach out via the project page.

Owner

Name: Demian
Login: demianhj
Kind: user

Repositories: 1
Profile: https://github.com/demianhj

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
title: "BlenderProc2"
version: 2.0.0
date-released: 2021-10-12
licence: GNU General Public License v3.0
authors:
  - family-names: Denninger
    given-names: Maximilian
    affiliation: "German Aerospace Center (DLR)"
    email: "maximilian.denninger@dlr.de"
    orcid: "https://orcid.org/0000-0002-1557-2234"
  - family-names: Sundermeyer
    given-names: Martin
    affiliation: "German Aerospace Center (DLR)"
    email: "martin.sundermeyer@dlr.de"
    orcid: "https://orcid.org/0000-0003-0587-9643"
  - family-names: Winkelbauer
    given-names: Dominik
    affiliation: "German Aerospace Center (DLR)"
    email: "dominik.winkelbauer@dlr.de"
    orcid: "https://orcid.org/0000-0001-7443-1071"
  - family-names: Olefir
    given-names: Dmitry
    affiliation: "German Aerospace Center (DLR)"
    orcid: "https://orcid.org/0000-0001-5244-9676"
  - family-names: Hodan
    given-names: Tomas
    affiliation: "Visual Recognition Group, Czech Technical University in Prague"
    email: "hodantom@cmp.felk.cvut.cz"
  - family-names: Zidan
    given-names: Youssef
    affiliation: "German Aerospace Center (DLR)"
  - family-names: Elbadrawy
    given-names: Mohamad
    affiliation: "German Aerospace Center (DLR)"
  - family-names: Knauer
    given-names: Markus
    affiliation: "German Aerospace Center (DLR)"
    email: "markus.knauer@dlr.de"
    orcid: "https://orcid.org/0000-0001-8229-9410"
  - family-names: Katam
    given-names: Harinandan
    affiliation: "German Aerospace Center (DLR)"
  - family-names: Lodhi
    given-names: Ahsan
    affiliation: "German Aerospace Center (DLR)"
  - family-names: Penzkofer
    given-names: Anna
    affiliation: "German Aerospace Center (DLR)"
repository-code: "https://github.com/DLR-RM/BlenderProc/"
url: "https://dlr-rm.github.io/BlenderProc/"
abstract: "BlenderProc is a modular procedural pipeline, which helps in generating real looking images for the training of convolutional neural networks. These can be used in a variety of use cases including segmentation, depth, normal and pose estimation and many others. A key feature of our extension of blender is the simple to use modular pipeline, which was designed to be easily extendable. By offering standard modules, which cover a variety of scenarios, we provide a starting point on which new modules can be created."
keywords:
  - "machine learning"
  - "deep learning"
  - "artificial intelligence"
  - "computer vision"
  - "simulation"
  - "photo realistic rendering"
  - "blender"
  - "robot framework"
  - "dataset generation"
references:
  - type: article
    title: "BlenderProc"
    authors:
      - family-names: Denninger
        given-names: Maximilian
        affiliation: "German Aerospace Center (DLR)"
        email: "maximilian.denninger@dlr.de"
        orcid: "https://orcid.org/0000-0002-1557-2234"
      - family-names: Sundermeyer
        given-names: Martin
        affiliation: "German Aerospace Center (DLR)"
        email: "martin.sundermeyer@dlr.de"
        orcid: "https://orcid.org/0000-0003-0587-9643"
      - family-names: Winkelbauer
        given-names: Dominik
        affiliation: "German Aerospace Center (DLR)"
        email: "dominik.winkelbauer@dlr.de"
        orcid: "https://orcid.org/0000-0001-7443-1071"
      - family-names: Zidan
        given-names: Youssef
        affiliation: "German Aerospace Center (DLR)"
      - family-names: Olefir
        given-names: Dmitry
        affiliation: "German Aerospace Center (DLR)"
        orcid: "https://orcid.org/0000-0001-5244-9676"
      - family-names: Elbadrawy
        given-names: Mohamad
        affiliation: "German Aerospace Center (DLR)"
      - family-names: Lodhi
        given-names: Ahsan
        affiliation: "German Aerospace Center (DLR)"
      - family-names: Katam
        given-names: Harinandan
        affiliation: "German Aerospace Center (DLR)"
    year: 2019
    url: https://arxiv.org/abs/1911.01911
  - type: article
    title: "BlenderProc: Reducing the Reality Gap with Photorealistic Rendering"
    authors:
      - family-names: Denninger
        given-names: Maximilian
        affiliation: "German Aerospace Center (DLR)"
        email: "maximilian.denninger@dlr.de"
        orcid: "https://orcid.org/0000-0002-1557-2234"
      - family-names: Sundermeyer
        given-names: Martin
        affiliation: "German Aerospace Center (DLR)"
        email: "martin.sundermeyer@dlr.de"
        orcid: "https://orcid.org/0000-0003-0587-9643"
      - family-names: Winkelbauer
        given-names: Dominik
        affiliation: "German Aerospace Center (DLR)"
        email: "dominik.winkelbauer@dlr.de"
        orcid: "https://orcid.org/0000-0001-7443-1071"
      - family-names: Olefir
        given-names: Dmitry
        affiliation: "German Aerospace Center (DLR)"
        orcid: "https://orcid.org/0000-0001-5244-9676"
      - family-names: Hodan
        given-names: Tomas
        affiliation: "Visual Recognition Group, Czech Technical University in Prague"
        email: "hodantom@cmp.felk.cvut.cz"
      - family-names: Zidan
        given-names: Youssef
        affiliation: "German Aerospace Center (DLR)"
      - family-names: Elbadrawy
        given-names: Mohamad
        affiliation: "German Aerospace Center (DLR)"
      - family-names: Knauer
        given-names: Markus
        affiliation: "German Aerospace Center (DLR)"
        email: "markus.knauer@dlr.de"
        orcid: "https://orcid.org/0000-0001-8229-9410"
      - family-names: Katam
        given-names: Harinandan
        affiliation: "German Aerospace Center (DLR)"
      - family-names: Lodhi
        given-names: Ahsan
        affiliation: "German Aerospace Center (DLR)"
    year: 2020
    conference: "International Conference on Robotics: Sciene and Systems, RSS 2020"
    url: "https://sim2real.github.io/assets/papers/2020/denninger.pdf"

GitHub Events

Total

Watch event: 2

Last Year

Watch event: 2

Dependencies

.github/workflows/blenderprochelper.yml actions

actions/checkout v2 composite
actions/upload-artifact v3 composite

.github/workflows/draft-pdf.yml actions

actions/checkout v3 composite
openjournals/openjournals-draft-action master composite

docker/Dockerfile docker

nvidia/cudagl 11.4.1-runtime-ubuntu20.04 build

setup.py pypi

setuptools *

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science