| CPC G06T 3/4053 (2013.01) [G06T 3/4007 (2013.01); G06T 3/4076 (2013.01); G06T 5/00 (2013.01); G06T 5/50 (2013.01); G06T 5/80 (2024.01); H04N 13/106 (2018.05); H04N 13/111 (2018.05); H04N 13/128 (2018.05); H04N 13/139 (2018.05); H04N 23/62 (2023.01); H04N 23/951 (2023.01); G06T 5/20 (2013.01); G06T 5/70 (2024.01); G06T 2207/10004 (2013.01); G06T 2207/10012 (2013.01); G06T 2207/20182 (2013.01); G06T 2207/20192 (2013.01); G06T 2207/20221 (2013.01); H04N 13/156 (2018.05); H04N 13/204 (2018.05); H04N 13/246 (2018.05); H04N 13/271 (2018.05)] | 20 Claims |

|
1. A method for synthesizing high resolution (HR) images, comprising:
acquiring a plurality of low resolution (LR) images from different viewpoints, where the plurality of LR images capture a scene in which depths of points in the scene vary and each of the plurality of LR images differs from other LR images due to scene dependent geometric displacements due to parallax;
determining scene dependent parallax information with respect to the LR images based upon disparity relative to a reference point of view resulting from the depths of points in the captured scene; and
fusing at least portions of the LR images to form a HR image by:
populating a high resolution (HR) grid corresponding to pixel locations of the HR image with LR image samples from the LR images using the scene dependent parallax information; and
interpolating samples at grid position of the HR grid using neighboring available samples from the LR image samples placed on the HR grid;
storing the HR image.
|