US 12,131,446 B2
Self-supervised deblurring
Rajesh Veera Venkata Lakshmi Langoju, Bengaluru (IN); Prasad Sudhakara Murthy, Bengaluru (IN); Utkarsh Agrawal, Bengaluru (IN); Bhushan D. Patil, Pune (IN); and Bipul Das, Chennai (IN)
Assigned to GE Precision Healthcare LLC, Waukesha, WI (US)
Filed by GE Precision Healthcare LLC, Milwaukee, WI (US)
Filed on Jul. 6, 2021, as Appl. No. 17/368,534.
Prior Publication US 2023/0013779 A1, Jan. 19, 2023
Int. Cl. G06T 5/73 (2024.01); G06N 20/00 (2019.01); G06T 3/4053 (2024.01); G06T 5/20 (2006.01)
CPC G06T 5/73 (2024.01) [G06N 20/00 (2019.01); G06T 3/4053 (2013.01); G06T 5/20 (2013.01); G06T 2207/20081 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
a processor that executes computer-executable components stored in a computer-readable memory, the computer-executable components comprising:
a receiver component that accesses an input image generated by an imaging device; and
a training component that trains, in a self-supervised manner based on a point spread function of the imaging device, a machine learning model to deblur the input image, along at least one axis, by a residual blur amount between the point spread function of the imaging device and a target high-resolution point spread function, and wherein the training component updates parameters of the machine learning model based on a shape difference between the point spread function of the imaging device and the target high-resolution point spread function, wherein the shape difference represents the residual blur amount.