公开(公告)号：US20230419654A1

公开(公告)日：2023-12-28

申请号：US18338760

申请日：2023-06-21

Applicant: POSTECH RESEARCH AND BUSINESS DEVELOPMENT FOUNDATION

Inventor： Suha KWAK ,  Taeyoung SON ,  Sohyun LEE

IPC: G06V20/10 ,  G06V10/26 ,  G06V10/44

CPC classification number: G06V20/10 ,  G06V10/26 ,  G06V10/443

Abstract: A device for learning a fog-invariant feature includes a fog-pass filter, which is trained such that fog factors of the same fog domain approach each other and fog factors of different fog domains are apart from each other so as to determine a fog state of an input image as a fog factor, and a segmentation network, which is trained such that a fog style gap between the different fog domains decreases, in which training of the fog-pass filter and training of the segmentation network are alternatively performed by using three fog domain datasets.