Skip to content

Latest commit

 

History

History
29 lines (19 loc) · 1.53 KB

README.md

File metadata and controls

29 lines (19 loc) · 1.53 KB
Raw

alt text

This repository contains code to render the ShapeNet and ABC datasets from various poses, lighting and material properties.

Rendering ShapeNet and ABC using Blender 2.79b

Note: there is overlap in the code for ShapeNet and ABC but there are subtle differences that would make a unified codebase more complex without significant gain.

Step 1. Blender Installation for MacOS and Ubuntu Linux (Windows instructions pending)

Download Blender 2.79b for your operating system from the official Blender release.

For MacOS the default installation path is /Applications/Blender/blender.app/Contents/MacOS/blender, and for Linux it involves extracting a blender-2.79b-linux-glibc219-x86_64.tar which makes the path <path to extracted tarball>/blender-2.79b-linux-glibc219-x86_64/blender.

Depending on your OS, add the appropriate path in the data_generation_parameters.json file under the key "blender_path". The file data_generation_paramters.json is used for both ABC and ShapeNet.

Step 2

  1. Download the datasets from their respective locations
  2. Further instructions are included in each dataset directory

Step 3

  1. Postprocess the rendered data to turn the .exr depth outputs into images and min and max values for the depth on the visible object surface using utils/convert_exr.py. This provides absolute depth information.