US 12,272,030 B2
Building units for machine learning models for denoising images and systems and methods for using same
Bambi L DeLaRosa, Boise, ID (US); Katya Giannios, Boise, ID (US); and Abhishek Chaurasia, Boise, ID (US)
Assigned to Micron Technology, Inc., Boise, ID (US)
Filed by MICRON TECHNOLOGY, INC., Boise, ID (US)
Filed on Aug. 18, 2021, as Appl. No. 17/445,382.
Claims priority of provisional application 63/163,678, filed on Mar. 19, 2021.
Claims priority of provisional application 63/163,688, filed on Mar. 19, 2021.
Claims priority of provisional application 63/163,682, filed on Mar. 19, 2021.
Prior Publication US 2022/0309618 A1, Sep. 29, 2022
Int. Cl. G06T 5/70 (2024.01); G06N 3/048 (2023.01); G06N 3/08 (2023.01); G06T 5/50 (2006.01); G06T 7/00 (2017.01)
CPC G06T 5/70 (2024.01) [G06N 3/048 (2023.01); G06N 3/08 (2013.01); G06T 5/50 (2013.01); G06T 7/0012 (2013.01); G06T 2207/10061 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20216 (2013.01)] 37 Claims
OG exemplary drawing
 
22. A system comprising:
at least one processor; and
at least one non-transitory medium accessible to the processor, the at least one non-transitory medium encoded with instructions that, when executed, cause the system to implement a machine learning model, wherein the machine learning model comprises:
a plurality of building units, wherein individual ones of the building units are configured to receive a first input based on a second image and a second input based at least in part, on the image, and further configured to provide a first output, a second output, and a noise portion; and
a plurality of adders configured to combine the noise portions provided by the plurality of building units to the image to provide output images.