Depth Enhancement Results for Middlebury Dataset
The ground truth color and depth images are from the Middlebury dataset [1, 2, 3, 4]. Here are the images used in our paper. 
 
Ground truth color  Ground truth depth  Noisy color  Noisy depth  Output color  Output depth 
           
           
           
           
           
           
           
           
           
           
           
           
References 
[1] H. Hirschmuller and D. Scharstein. Evaluation of cost functions for stereo matching. In IEEE CVPR, 2007.
[2] D. Scharstein and C. Pal. Learning conditional random fields for stereo. In IEEE CVPR, 2007.
[3] D. Scharstein and R. Szeliski. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. J. Comput. Vision, 47(1-3):7–42, 2002.
[4] D. Scharstein and R. Szeliski. High-accuracy stereo depth maps using structured light. In IEEE CVPR, pages 195–202, 2003.