Unsupervised learning of disparity maps from stereo images

Abstract

The visual perception of depth is a striking ability of the human visual system and an active part of research in fields like neurobiology, psychology, robotics, or computer vision. In real world scenarios, many different cues, such as shading, occlusion, or disparity are combined to perceive depth. As can be shown using random dot stereograms, however, disparity alone is sufficient for the generation of depth perception [1]. To compute the disparity map of an image, matching image regions in both images have to be found, ie the correspondence problem has to be solved. After this, it is possible to infer the depth of the scene. Specifically, we address the correspondence problem by inferring the transformations between image patches of the left and the right image. The transformations are modeled as Lie groups which can be learned efficiently [3]. First, we start from the assumption that horizontal disparity is caused by …