Skip to content

Latest commit

 

History

History

data_preparation

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 
 
 

Dataset Preparation

1. Generate foreground object and mask

We use PASCAL VOC dataset for the foreground.

The data is organised as follows:

├── background
└── VOC2010
    ├── Annotations
    ├── ImageSets
    │   ├── Action
    │   ├── Layout
    │   ├── Main
    │   └── Segmentation
    ├── JPEGImages
    ├── SegmentationClass
    └── SegmentationObject

Run this to generate foreground.

python generate_foreground.py 

2. Prepare Background

We crop DIV2K dataset to 256*256 for background images.

3. Generate Datasets

Run this to generate RGB datasets (./trainset0908).

python generate_motion.py --config ./config.yml 
  • step: the original images with sub-pixel motions

  • gt: the ground-truth of the alpha times maginified images

  • The number behind underscore is magnification factor.