OpenCV has also other, more advanced,  stereovision algorithms. Some time ago I've tried semi-global block matching (implementation of H. Hirschmuller algorithm) and got very good results. It's pretty fast and gives better results than simple block matching algorithm. See the attached link for documentation of StereoSGBM method in the OpenCV.

If you are looking for implementation of multi-view stereo algorithm (where you have images from more than 2 calibrated cameras) try CMVS software developed by Y. Furukawa. Link is attached.

http://docs.opencv.org/modules/calib3d/doc/camera_calibration_and_3d_reconstruction.html#stereosgbm

http://www.di.ens.fr/cmvs/

Anas Al-Nuaimi

I recommend you to follow this post, from Jay Rambhia, that uses the StereoSGBM algorithm.

I tried it a couple of days ago with great success with 2 ps3 eye cameras, in Linux:

http://www.jayrambhia.com/blog/disparity-maps/

Please note that before applying the StereoSGBM, you first need to calibrate and rectify both image cameras.

For the stereo calibration, follow this link:

http://www.jayrambhia.com/blog/stereo-calibration/

If you need any help please ask me. Right now I am  deeply working in this area.

Best regards

João Martinho Moura