The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Aug. 19, 2025

Filed:

Oct. 16, 2024
Applicant:

Atombeam Technologies Inc., Moraga, CA (US);

Inventors:

Joshua Cooper, Columbia, SC (US);

Zhu Li, Overland Park, KS (US);

Charles Yeomans, Orinda, CA (US);

Assignee:

ATOMBEAM TECHNOLOGIES INC., Moraga, CA (US);

Attorneys:
Primary Examiner:
Int. Cl.
CPC ...
G06T 5/20 (2006.01); G06T 3/40 (2024.01); G06T 5/70 (2024.01); G06V 10/42 (2022.01);
U.S. Cl.
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);
Abstract

A system and method are disclosed for adaptive low-light image enhancement using AI-based techniques and wavelet decomposition. The system analyzes characteristics of a raw input image, including brightness, contrast, noise levels, and detail complexity. Based on this analysis, an adaptation control subsystem determines optimal preprocessing parameters. These parameters guide an adaptive wavelet decomposition process, creating multiple frequency domain subimages. Each subimage is processed by a specialized neural network, tailored to its frequency range. The outputs of these networks are combined using an inverse wavelet transform, producing a denoised and enhanced image. This image then undergoes final processing in an image signal processing pipeline. The adaptive nature of the system allows for optimized enhancement across a wide range of low-light conditions, effectively balancing noise reduction, detail preservation, and overall image quality improvement.


Find Patent Forward Citations

Loading…