Science Score: 36.0%

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

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
  • DOI references
    Found 1 DOI reference(s) in README
  • Academic publication links
    Links to: arxiv.org, joss.theoj.org
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (14.2%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: Ayas-N
  • License: gpl-3.0
  • Language: Python
  • Default Branch: main
  • Size: 165 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created about 1 year ago · Last pushed about 1 year ago
Metadata Files
Readme Changelog Contributing License Citation

README.md

BlenderProc2

Documentation Open In Collab License: GPL v3

Front readme image

A procedural Blender pipeline for photorealistic rendering.

Documentation | Tutorials | Examples | ArXiv paper | Workshop paper | JOSS article

Features

  • Loading: *.obj, *.ply, *.blend, *.fbx, BOP, ShapeNet, Haven, 3D-FRONT, etc.
  • Objects: Set or sample object poses, apply physics and collision checking.
  • Materials: Set or sample physically-based materials and textures
  • Lighting: Set or sample lights, automatic lighting of 3D-FRONT scenes.
  • Cameras: Set, sample or load camera poses from file.
  • Rendering: RGB, stereo, depth, normal and segmentation images/sequences.
  • Writing: .hdf5 containers, COCO & BOP annotations.

Installation

Via git

I directly cloned the Blenderproc repository, so clone this repository for access to the package.

To still make use of the blenderproc command and therefore use blenderproc anywhere on your system, make a local pip installation:

bash cd BlenderProc pip install -e .

Synthetic Data Generation

To run the synthetic data generation first run:

bash blenderproc run generate.py

This will runs the script that loads up the dune.blend blender scene file. It then randomises the camera location and angle whilst maintaining focus on the cube.

Images that are generated will be placed in the coco_data/images directory.

The bounding boxes from blenderproc are generated in the coco_annotations.json file, but this format isn't suitable for the Ultralytics package which we are using to run the YOLO model.

To generate labels with the correct format, run:

bash python json_parser.py

Which generates bounding boxes for each corresponding image in .txt form in the coco_data/labels directory.

YOLO Model

Owner

  • Name: Jey Son
  • Login: Ayas-N
  • Kind: user

GitHub Events

Total
  • Member event: 1
  • Push event: 1
  • Pull request event: 2
  • Fork event: 1
  • Create event: 3
Last Year
  • Member event: 1
  • Push event: 1
  • Pull request event: 2
  • Fork event: 1
  • Create event: 3

Dependencies

.github/workflows/blenderprochelper.yml actions
  • actions/checkout v2 composite
  • actions/upload-artifact v3 composite
.github/workflows/draft-pdf.yml actions
  • actions/checkout v2 composite
  • actions/upload-artifact v1 composite
  • openjournals/openjournals-draft-action master composite
setup.py pypi
  • setuptools *