US 12,299,913 B2
Image processing framework for performing object depth estimation
Kuang-Man Huang, Zhubei (TW); and Michel Adib Sarkis, San Diego, CA (US)
Assigned to QUALCOMM Incorporated, San Diego, CA (US)
Filed by QUALCOMM Incorporated, San Diego, CA (US)
Filed on Aug. 29, 2022, as Appl. No. 17/823,033.
Claims priority of provisional application 63/249,514, filed on Sep. 28, 2021.
Prior Publication US 2023/0093827 A1, Mar. 30, 2023
Int. Cl. G06T 17/00 (2006.01); G06T 7/11 (2017.01); G06T 7/50 (2017.01); G06T 7/60 (2017.01)
CPC G06T 7/50 (2017.01) [G06T 7/11 (2017.01); G06T 7/60 (2013.01); G06T 17/00 (2013.01); G06T 2200/08 (2013.01); G06T 2207/20132 (2013.01); G06T 2207/30201 (2013.01); G06T 2210/12 (2013.01); G06T 2210/22 (2013.01)] 30 Claims
OG exemplary drawing
 
1. A method for processing image data, the method comprising:
determining a three-dimensional model corresponding to an object in an input image;
determining, based on the three-dimensional model, an estimated focal length corresponding to the input image;
calculating an estimated depth associated with the object in the input image based on the estimated focal length and an input image focal length;
generating a projected two-dimensional image at least in part by projecting three-dimensional vertices of three-dimensional model to the input image;
determining an object bounding box in the projected two-dimensional image;
generating an attention mask based on the object bounding box;
determining, using a neural network, a depth bias value based on the attention mask and the input image; and
calculating, based on the estimated depth and the depth bias value, a corrected depth associated with the object in the input image.