US 12,394,018 B1
System and methods for low-light image enhancement utilizing denoising preprocessing with wavelet decomposition
Joshua Cooper, Columbia, SC (US); Zhu Li, Overland Park, KS (US); and Charles Yeomans, Orinda, CA (US)
Assigned to ATOMBEAM TECHNOLOGIES INC., Moraga, CA (US)
Filed by AtomBeam Technologies Inc., Moraga, CA (US)
Filed on Oct. 16, 2024, as Appl. No. 18/917,981.
Application 18/917,981 is a continuation in part of application No. 18/624,038, filed on Apr. 1, 2024, granted, now 12,175,638.
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 5/20 (2006.01); G06T 3/40 (2024.01); G06T 5/70 (2024.01); G06V 10/42 (2022.01)
CPC G06T 5/20 (2013.01) [G06T 3/40 (2013.01); G06T 5/70 (2024.01); G06V 10/431 (2022.01); G06T 2207/20084 (2013.01)] 14 Claims
OG exemplary drawing
 
1. A system for image enhancement, comprising:
a computing device comprising at least a memory and a processor;
a denoising preprocessing module comprising a first plurality of programming instructions that, when operating on the processor, cause the computing device to:
create a plurality of subsampled subimages from a raw input image;
analyze the raw input image to determine image characteristics;
determine preprocessing parameters based on the image characteristics;
perform an adaptive wavelet decomposition process on each subimage from the plurality of subimages using the determined preprocessing parameters to generate a plurality of frequency domain subimages;
input each frequency domain subimage from the plurality of frequency domain subimages into a corresponding neural network;
provide an output of each corresponding neural network to an inverse wavelet module; and
provide an output of the inverse wavelet module to an image signal processing pipeline.