公开(公告)号：US20140029821A1

公开(公告)日：2014-01-30

申请号：US13908058

申请日：2013-06-03

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hyong Euk LEE ,  Kyung Hwan KIM ,  Na Hyup KANG ,  Sang Wook KIM ,  Ji Yeon KIM

IPC: G06T7/00

CPC classification number: G06T7/0012 ,  G06T7/11 ,  G06T7/136 ,  G06T7/194 ,  G06T2207/10072 ,  G06T2207/30101

Abstract: A vessel segmentation method includes acquiring an image of a blood vessel, including cross sections, using a contrast medium. The method further includes setting a threshold value for each of the cross sections based on data of an intensity of the contrast medium. The method further includes performing vessel segmentation based on the image and the threshold value for each of the cross sections.

Abstract translation: 血管分割方法包括使用造影剂获取包括横截面的血管图像。 该方法还包括基于造影剂的强度的数据设置每个横截面的阈值。 该方法还包括基于每个横截面的图像和阈值执行血管分割。

公开(公告)号：US20250157213A1

公开(公告)日：2025-05-15

申请号：US18947679

申请日：2024-11-14

Applicant: Samsung Electronics Co., Ltd. ,  UIF (University Industry Foundation), Yonsei University

Inventor： Sehwan KI ,  Daekyu KWON ,  Dongyoung KIM ,  Seon Joo KIM ,  Younghyun JO ,  Hyong Euk LEE

IPC: G06V10/98 ,  G06V10/82

Abstract: A method and apparatus for image quality assessment are provided. The method of image quality assessment includes: accessing a text prompt representing an image-quality attribute of a target image included in a data set; training a target encoder to correspond to a visual-language model (VLM), the training based on data obtained by applying the text prompt to the VLM; and fine-tuning the trained target encoder to perform image-quality assessment.

公开(公告)号：US20250117984A1

公开(公告)日：2025-04-10

申请号：US18910380

申请日：2024-10-09

Applicant: Samsung Electronics Co., Ltd.

Inventor： Lu XU ,  Chao ZHANG ,  Yasi WANG ,  Hyong Euk LEE ,  Qiang WANG

IPC: G06T11/00 ,  G06T7/40 ,  G06T7/50 ,  G06T7/90 ,  G06V10/74 ,  G06V10/77 ,  G06V10/774

Abstract: A processor-implemented method with image generation includes obtaining a first image, determining predicted texture information of a target image corresponding to the first image through a texture prediction model, based on the first image, determining predicted color information of the target image through a color prediction model, based on the first image, and generating the target image based on the first image, using the predicted texture information and the predicted color information, wherein a format of the target image is different from that of the first image.

公开(公告)号：US20240147065A1

公开(公告)日：2024-05-02

申请号：US18341970

申请日：2023-06-27

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Myungsub CHOI ,  Hana LEE ,  Hyong Euk LEE

IPC: H04N23/67 ,  H04N19/117 ,  H04N19/167

CPC classification number: H04N23/675 ,  H04N19/117 ,  H04N19/167 ,  H04N23/672

Abstract: A processor-implemented method includes: generating first input data comprising phase information of an input image; generating second input data in which lens position information is encoded; and determining position information of a lens corresponding to autofocus by inputting the first input data and the second input data to a neural network model.

公开(公告)号：US20230186432A1

公开(公告)日：2023-06-15

申请号：US17718661

申请日：2022-04-12

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

Inventor： Jae Seok CHOI ,  Minsu CHO ,  Sanghyun KIM ,  Jongmin LEE ,  Kinam KWON ,  Geonseok SEO ,  Hyong Euk LEE

IPC: G06T5/00 ,  G06V10/80 ,  G06T7/20 ,  G06V10/74

CPC classification number: G06T5/001 ,  G06V10/806 ,  G06T7/20 ,  G06V10/761 ,  G06T2207/20084

Abstract: A method and apparatus for image restoration based on burst images. The method includes generating a plurality of feature representations corresponding to individual images of a burst image set by encoding the individual images, determining a reference feature representation from among the plurality of feature representations, determining a first comparison pair including the reference feature representation and a first feature representation of the plurality of feature representations, generating a first motion-embedding feature representation of the first comparison pair based on a similarity score map of the reference feature representation and the first feature representation, generating a fusion result by fusing a plurality of motion-embedding feature representations including the first motion-embedding feature representation, and generating at least one restored image by decoding the fusion result.

公开(公告)号：US20230092017A1

公开(公告)日：2023-03-23

申请号：US17678339

申请日：2022-02-23

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Geonseok SEO ,  Nahyup KANG ,  Eunhee KANG ,  Byung In YOO ,  Hyong Euk LEE ,  Jae Seok CHOI

IPC: G06F7/76 ,  G06N3/04 ,  G06F15/80

Abstract: A computing device and an operation method thereof are disclosed. The method includes unshuffling first image data to generate input data, generating output data by implementing a neural network (NN) model provided the input data, and generating second image data by shuffling the output data.

公开(公告)号：US20230081302A1

公开(公告)日：2023-03-16

申请号：US17680934

申请日：2022-02-25

Applicant: Samsung Electronics Co., Ltd.

Inventor： Kinam KWON ,  Junsang YU ,  Sangwon LEE ,  Nahyup KANG ,  Hyong Euk LEE

IPC: G06T5/00

Abstract: A method with image processing includes: setting an offset window for an offset pattern of a kernel offset and an offset parameter for an application intensity of the kernel offset; determining an output kernel by applying the kernel offset to an input kernel based on the offset window and the offset parameter; and adjusting contrast of a degraded image using the output kernel.

公开(公告)号：US20220398695A1

公开(公告)日：2022-12-15

申请号：US17543901

申请日：2021-12-07

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jae Seok CHOI ,  Hyong Euk LEE ,  Geonseok SEO ,  Byung In YOO

IPC: G06T5/00 ,  G06K9/62 ,  G06T7/80

Abstract: Methods and apparatuses with training or image enhancement are disclosed. The image enhancement method includes obtaining an input image, estimating a noise distribution of the input image by implementing a noise model based on the input image, and generating an enhanced image by implementing an image enhancement model dependent on the input image and the estimated noise distribution.

公开(公告)号：US20220276706A1

公开(公告)日：2022-09-01

申请号：US17749290

申请日：2022-05-20

Applicant: Samsung Electronics Co., Ltd.

Inventor： Seungin PARK ,  Hyong Euk LEE

IPC: G06F3/01 ,  G06K9/62 ,  G06T11/00 ,  G06T3/40 ,  G06V10/40 ,  G06V40/20

Abstract: A method with image augmentation includes recognizing, based on a gaze of the user corresponding to the input image, any one or any combination of any two or more of an object of interest of a user, a situation of the object of interest, and a task of the user from partial regions of an input image determining relevant information indicating an intention of the user, based on any two or any other combination of the object of interest of the user, the situation of the object of interest, and the task of the user, and generating a visually augmented image by visually augmenting the input image based on the relevant information.

公开(公告)号：US20200175771A1

公开(公告)日：2020-06-04

申请号：US16782518

申请日：2020-02-05

Applicant: Samsung Electronics Co., Ltd.

Inventor： KeeChang LEE ,  Minsu AHN ,  Inwoo HA ,  Seungin PARK ,  Hyong Euk LEE ,  Heesae LEE

IPC: G06T19/00 ,  G06T19/20 ,  G06F3/0481 ,  G06T15/50

Abstract: A display method includes displaying, in a virtual environment, an object to which a light source is set. The method further includes illuminating an area around the object based on the light source.