MACHINE LEARNING MODEL TRAINING FRAMEWORK FOR MULTI-FRAME IMAGE PROCESSING

Title:

MACHINE LEARNING MODEL TRAINING FRAMEWORK FOR MULTI-FRAME IMAGE PROCESSING

Document Type and Number:

WIPO Patent Application WO/2023/149703

Kind Code:

A1

Abstract:

A method for training data generation includes obtaining a first set of image frames of a scene and a second set of image frames of the scene using multiple exposure settings. The method also includes generating an alignment map, a blending map, and an input image using the first set of image frames. The method further includes generating a ground truth image using the alignment map, the blending map, and the second set of image frames. In addition, the method includes using the ground truth image and the input image as an image pair in a training dataset when training a machine learning model to reduce image distortion and noise.

Inventors:

LUU TYLER (US)
GLOTZBACH JOHN WILLIAM (US)
SHEIKH HAMID RAHIM (US)
LEE JOHN SEOKJUN (US)
KIM YOUNGMIN (KR)
CHO JUNKI (KR)
JEON SEUNGCHUL (KR)

Application Number:

PCT/KR2023/001343

Publication Date:

August 10, 2023

Filing Date:

January 30, 2023

Export Citation:

Click for automatic bibliography generation Help

Assignee:

SAMSUNG ELECTRONICS CO LTD (KR)

International Classes:

G06V10/774; G06N20/00; G06V10/24; G06V20/40

Foreign References:

US20190333198A1	2019-10-31
US20190043178A1	2019-02-07
US20210314474A1	2021-10-07
US20200285883A1	2020-09-10
US20210158139A1	2021-05-27