Super Resolution#

Detailed Description#

The Berkeley Segmentation Dataset and Benchmark#

Implements loading dataset:

“The Berkeley Segmentation Dataset and Benchmark”: https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/segbench/

Usage:

  1. From link above download BSDS300-images.tgz.

  2. Unpack.

  3. To load data run:

DIV2K dataset: DIVerse 2K#

Implements loading dataset:

“DIV2K dataset: DIVerse 2K”: https://data.vision.ee.ethz.ch/cvl/DIV2K/

Usage:

  1. From link above download ‘Train data (HR images)’ or any other of the dataset files.

  2. Unpack.

  3. To load data run:

The General-100 Dataset#

Implements loading dataset:

“General-100 dataset contains 100 bmp-format images (with no compression). We used this dataset in our FSRCNN ECCV 2016 paper. The size of these 100 images ranges from 710 x 704 (large) to 131 x 112 (small). They are all of good quality with clear edges but fewer smooth regions (e.g., sky and ocean), thus are very suitable for the super-resolution training.”: http://mmlab.ie.cuhk.edu.hk/projects/FSRCNN.html

Usage:

  1. From link above download General-100.zip.

  2. Unpack.

  3. To load data run:

Classes#