DIYer22/bpycv

Computer vision utils for Blender (generate instance annoatation, depth and 6D pose by one line code)

55
/ 100
Established

This project helps computer vision researchers and robotics engineers efficiently generate synthetic image datasets. It takes 3D models and scene descriptions from Blender and produces rendered images with corresponding ground truth annotations like instance segmentation masks, depth maps, and 6D object poses. This streamlines the creation of diverse training data for tasks such as object detection, segmentation, and pose estimation.

498 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need to create large, varied datasets of synthetic images with detailed ground truth for training computer vision models, especially for robotics or industrial applications.

Not ideal if you are working exclusively with real-world image data or do not have access to 3D object models and Blender for scene setup.

synthetic-data-generation robotics computer-vision-training 3d-rendering dataset-creation
Stale 6m
Maintenance 2 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 18 / 25

How are scores calculated?

Stars

498

Forks

59

Language

Python

License

MIT

Last pushed

Aug 05, 2025

Commits (30d)

0

Dependencies

5

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/DIYer22/bpycv"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.