Method and system for converting 2D image data to stereoscopic image data

摘要

Methods and Systems are provided for converting a two-dimensional image sequence into a three-dimensional image. In one embodiment, a method for converting a two-dimensional image sequence into a three-dimensional image includes determining camera motion parameters between consecutive images in a monoscopic sequence of reference 2D images, wherein the consecutive images comprise a current reference image and an adjacent image, determining a horizontal disparity map for a target image using the camera motion parameters, determining a disparity probability value for each disparity vector of the disparity map, and determining a target image as a weighted average of pixel values in the current reference image using the disparity probability values, such that the target image and current reference image comprise a stereoscopic image pair.

主权项

1. A method for converting a two-dimensional image sequence into a three-dimensional image, comprising:
determining camera motion parameters between consecutive images in a monoscopic sequence of 2D images, wherein the consecutive images comprise a current reference image and an adjacent image; determining a horizontal disparity map for a target image using the camera motion parameters by constructing a cost function comprising a pixel matching cost function component that determines a cost of matching a pixel in the current reference image to a pixel in the adjacent image under the horizontal disparity map and a smoothing cost function component that considers the similarity of disparity values of neighboring pixel locations in the horizontal disparity map to obtain a smooth horizontal disparity map; determining a disparity probability value for each disparity vector of the disparity map; determining a target image as a weighted average of pixel values in the current reference image using the disparity probability values, such that the target image and current reference image comprise a stereoscopic image pair; determining an amount of vertical camera motion between the current reference image and adjacent image using the camera motion parameters; and performing a planar transform to compute a target image from the current reference image using a planar transformation matrix, if the amount of vertical motion is below a predetermined threshold.