An apparatus and method for generating a disparity map in a receiving device, e.g., a set-top box, that enables user control for adjusting image depth in a stereo image set are provided. The apparatus and method provide for receiving a signal comprising a left eye image and a right eye image, encoding the left eye image as a reference image, predictively coding the right eye image using the coded left eye image as the reference image, capturing motion indicators generated during encoding of the right eye image, and generating a disparity map between the left eye image and right eye image using the motion indicators.