README for CMU Geometric Context Dataset
Derek Hoiem, Alexei A. Efros, Martial Hebert
dhoiem@cs.cmu.edu

Copyright (C) 2006 Derek Hoiem, Carnegie Mellon University

Please cite our ICCV'05 Geometric Context from a Single Image if you use 
this dataset.  

Note that all images were contained using Google image search, using 
keywords such as "city", "outdoor", "field", and "road".  The original 
content providers maintain copyrights on these images.

Contents:
  *.jpg: 300 images used for training and testing
  allimsegs2.mat: contains ground truth
	imsegs: for each image contains superpixel images (segimage) and 
	ground truth label for each superpixel (vert_labels, horz_labels)
  rand_indices.mat: 
	cluster_images: indices for learning segmentation
	cv_images: indices for cross-validation (in blocks of 50)