The SMW Stereo Algorithm

A. Fusiello, V. Roberto and E. Trucco

About the SMW algorithm

SMW (Symmetric Multi-Window) is a new, efficient stereo algorithm addressing robust disparity estimation in the presence of occlusions. The algorithm is an adaptive, multi-window scheme using left-right consistency to compute disparity and its associated uncertainty. A detailed description of the algorithm is available on line. The C-code implementation of SMW is also available .

About this demo

Fill in the forms with the URLs of your left and right images in pgm format. Please note that only the http protocol is implemented. The algorithm assumes that disparities are positive, i.e., the left image points are shifted to the right in the right image. The output consists of two (gif) images, the computed disparity and the uncertainty maps.

Disparity range: from  to 
Left  Image URL: 
Right Image URL: 

Images gallery   
Andrea Fusiello
Dipartimento di Matematica e Informatica
Università di Udine
Via delle Scienze, 206
I-33100 Udine - ITALY