Binocular stereo vision is a common technique for the recovery of three-dimensional shape. Underwater, backscatter degrades the image quality and consequently the performance of stereo vision-based 3-D reconstruction techniques. Recently, we proposed a method that exploits the depth cue in the backscatter components of stereo pairs, as an additional constraint for recovering the 3-D scene structure. In this paper, we compare the performance of this method with the application of classic normalized SSD-based minimization to raw underwater data, as well as to de-scattered images. Results of experiments with synthetic and real data are presented to assess the performance of our method with these other techniques.