Middlebury Stereo Datasets
Description
The repository contains four groups of stereo datasets. Each stereo dataset is usually with the full-size views and disparity maps.
Access
Link: http://vision.middlebury.edu/stereo/data/
References and Citation
We grant permission to use and publish all images and disparity maps on this website. However, if you use our datasets, we request that you cite the appropriate paper(s): [SS02] for the 2001 datasets, [SS03] for the 2003 datasets, and [SP07] or [HS07] for the 2005 and 2006 datasets.
References
HS07: H. Hirschmüller and D. Scharstein. Evaluation of cost functions for stereo matching. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), Minneapolis, MN, June 2007.In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2003), volume 1, pages 195-202, Madison, WI, June 2003.SP07: D. Scharstein and C. Pal. Learning conditional random fields for stereo. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), Minneapolis, MN, June 2007.SS02: D. Scharstein and R. Szeliski. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision, 47(1/2/3):7-42, April-June 2002.SS03: D. Scharstein and R. Szeliski. High-accuracy stereo depth maps using structured light.