CPC G06T 5/50 (2013.01) [G06N 3/04 (2013.01); G06T 3/4023 (2013.01); G06T 9/002 (2013.01); G06T 2207/10021 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20221 (2013.01)] | 19 Claims |
1. A method for generating an image of a scene with corresponding depth map, comprising:
collecting a plurality of copies of a two-dimensional image of the scene;
generating an intermediate image by concatenating the plurality of copies of the two-dimensional image along a first direction;
inputting the intermediate image into a neural network to generate an intermediate depth map corresponding to the intermediate image;
generating, from the intermediate image and the intermediate depth map, the image of the scene with the corresponding depth map;
extracting a plurality of pixels from the image of the scene, each one of the pixels carrying a first set of attributes corresponding to a first height, wherein the first set of attributes comprises a first longitude, a first latitude, a first depth value, and a first color value;
generating, for each one of the pixels, a second set of attributes corresponding to a second height, the second set of attributes comprising a second longitude, a second latitude, a second depth value, and a second color value, wherein the second longitude equals to the first longitude and the second color value equals to the first color value; and
generating a second image with a second depth information based on the second set of attributes of the plurality of pixels.
|