Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/guanyingc/tom-net_rendering

TOM-Net: Learning Transparent Object Matting from a Single Image, CVPR 2018
https://github.com/guanyingc/tom-net_rendering

matting pov-ray transparent

Last synced: about 2 months ago
JSON representation

TOM-Net: Learning Transparent Object Matting from a Single Image, CVPR 2018

Awesome Lists containing this project

README

        

# Data Rendering for Transparent Object Matting
**[Learning Transparent Object Matting from a Single Image, CVPR 2018 (Spotlight)](http://gychen.org/TOM-Net/)**,


[Guanying Chen](http://www.gychen.org)\*, [Kai Han](http://www.hankai.org/)\*, [Kwan-Yee K. Wong](http://i.cs.hku.hk/~kykwong/)


(\* indicates equal contribution)

## Introduction
As no off-the-shelf dataset for transparent object matting is available, and it is very tedious and difficult to produce a large real dataset with ground truth object masks, attenuation masks and refractive flow fields, we created a large-scale synthetic dataset by using [POV-Ray](http://www.povray.org/) to render images of synthetic transparent objects.





## Dependencies
- POV-Ray 3.7
- Python 2.7

## Sample Rendering Code
After installing POV-Ray, type the following command to render a transparent object in front of an image and get the ground truth object mask, attenuation mask and refractive flow field.
```
bash render.sh
```
We obtained the ground truth refractive flow field of an object by rendering it in front of a sequence of Gray-coded pattern.

## Generated POV-Ray Objects
We provide the 178K randomly generated POV-Ray objects in `.inc` format for your usage.
```
bash download_objects.sh
```