Depth from Disparity via Deep Learning

Depicting the ambiguity we see the P1 and P2, as seen from the optical center (i.e., camera location), which is projected onto the image plane as P1' and P2' are equivalent. Stereo vision systems reference knowledge of two images captured simultaneously from a pair of cameras (i.e., left and right), and with camera parameters, both extrinsic (e.g., cameras' location) and intrinsic (e.g., focal length), assumed known. Stereo is heavily motivated by biology (i.e., using the left and right eyes to capture visual information simultaneously). Classic stereo problems include disparity (camera parameters), depth (estimating the distance between cameras), occlusion, autostereograms, structure from motion (2D to 3D representations of scenes), motion parallax, depth map generation, and texture maps. There are several ways of modeling the problem as shown above.