Method and apparatus for converting 2-dimensional image into 3-dimensional image by adjusting depth of the 3-dimensional image

摘要

Provided are an apparatus and method for converting a two-dimensional (2D) image into a three-dimensional (3D) image. The method includes generating a first depth map by estimating depth information of an input image, wherein the input image is a 2D image; analyzing characteristics of the input image; predicting an error of the first depth map; determining a parameter for adjusting the first depth map based on the analyzed characteristics of the input image and the predicted error of the first depth map; adjusting the first depth map based on the determined parameter; and generating a 3D image of the input image based on the adjusted first depth map.

主权项

1. A method of converting an image, the method comprising:
generating a first depth map by estimating depth information of a single two-dimensional (2D) image; analyzing characteristics of the single 2D image by analyzing at least one of a spatial structure, a temporal structure and a spatio-temporal complexity of the single 2D image; determining at least one analytic parameter based on the at least one of the analyzed spatial structure, the temporal structure and the spatio-temporal complexity of the single 2D image; predicting an error of the first depth map corresponding to inaccurately estimated depth information of the single 2D image; determining a parameter for adjusting the first depth map based on the at least one analytic parameter and the predicted error of the first depth map; adjusting the first depth map based on the determined parameter for adjusting the first depth map; and generating a three-dimensional (3D) image of the single 2D image based on the adjusted first depth map, wherein the determining the parameter for adjusting the first depth map comprises:
determining an error prediction parameter based on the predicted error of the first depth map; andobtaining an error control parameter by combining the analytic parameter and the error prediction parameter, wherein the analyzing the characteristics of the single 2D image further comprises:
determining a depth map model of the single 2D image; anddetermining a similarity between the depth map model and the single 2D image by analyzing the characteristics of the single 2D image, wherein the predicting the error of the first depth map comprises predicting the error of the first depth map based on the similarity, and wherein the depth map model comprises a sample image.