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.

公开(公告)号：US20240153238A1

公开(公告)日：2024-05-09

申请号：US17977449

申请日：2022-10-31

Applicant: Samsung Electronics Co., Ltd. ,  POSTECH Research and Business Development Foundation

Inventor： Minsu CHO ,  Heeseung KWON ,  Manjin KIM ,  Suha KWAK

IPC: G06V10/74 ,  G06T7/246 ,  G06T7/73 ,  G06V10/62 ,  G06V10/75 ,  G06V10/764 ,  G06V10/77 ,  G06V10/82 ,  G06V40/20

CPC classification number: G06V10/761 ,  G06T7/248 ,  G06T7/74 ,  G06V10/62 ,  G06V10/751 ,  G06V10/759 ,  G06V10/764 ,  G06V10/7715 ,  G06V10/82 ,  G06V40/20 ,  G06T2207/10016 ,  G06T2207/20084

Abstract: An electronic device using a spatio-temporal self-similarity (STSS) and a method of operating the electronic device are disclosed. The electronic device may generate an STSS tensor including a spatial self-similarity map and spatial cross-similarity maps for each position of a video feature map corresponding to an input video based on a temporal offset and a spatial offset. STSS feature vectors may be generated from the STSS tensor by decreasing a dimension of the spatial offset and maintaining a dimension of the temporal offset for each position of the STSS tensor. An STSS feature map may be generated by integrating the dimension of the temporal offset for each position of the STSS feature vectors. An inference on the input video may be based on a result of adding the STSS feature map to the video feature map.

公开(公告)号：US20240161326A1

公开(公告)日：2024-05-16

申请号：US18342236

申请日：2023-06-27

Applicant: SAMSUNG ELECTRONICS CO., LTD. ,  POSTECH Research and Business Development Foundation

Inventor： Ahyun SEO ,  Minsu CHO ,  Suha KWAK ,  Byungjin KIM

IPC: G06T7/68 ,  G06V10/764 ,  G06V10/77 ,  G06V10/774 ,  G06V10/82

CPC classification number: G06T7/68 ,  G06V10/764 ,  G06V10/7715 ,  G06V10/774 ,  G06V10/82 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: A method may include predicting, using a machine learning model, score maps for each of a plurality of pre-set classes for predetermined symmetry types, using a plurality of pixels included in the feature map, and detecting a symmetry element of the input image based on the predicted score maps.