公开(公告)号：US20220147870A1

公开(公告)日：2022-05-12

申请号：US17421292

申请日：2020-01-06

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Vivek AGARWAL ,  Jatin GARG ,  Jayoon KOO ,  Dongjin SEO ,  Kwanki AHN ,  Keuntek LEE

IPC: G06N20/00 ,  G06F16/435 ,  H04N21/466

Abstract: An electronic device according to an embodiment of the disclosure includes: a communicator; a memory storing one or more instructions; at least one processor configured to execute the one or more instructions stored in the memory to collect content metadata and user metadata from a plurality of different servers that provide content, obtain a content latent factor including information about similarities between pieces of the content based on characteristics of the content metadata, by using a first learning network model, obtain a user latent factor related to user preferred content information based on characteristics of the user metadata, by using a second learning network model, obtain a user preference score for the content based on the content latent factor and the user latent factor, by using a third learning network model, and provide a recommended content list based on the user preference score.

公开(公告)号：US20240185603A1

公开(公告)日：2024-06-06

申请号：US18379969

申请日：2023-10-13

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Namuk KIM ,  Cheuihee HAHM ,  Jayoon KOO ,  Wookhyung KIM ,  IIhyun CHO

IPC: G06V20/40 ,  G06V10/22 ,  G06V10/82

CPC classification number: G06V20/41 ,  G06V10/225 ,  G06V10/82 ,  G06V20/46

Abstract: Provided are an electronic device and a control method thereof. The electronic device includes at least one memory storing at least one instruction; and at least one processor connected to the at least one memory and configured to execute the at least one instruction to: input information about a first frame among a plurality of frames to a first object detection network and obtain first information about an object included in the first frame, store the first information in the at least one memory, and input the first information and information about a second frame among the plurality of frames to a second object detection network and obtain second information about an object included in the second frame, wherein the second frame is a next frame following the first frame.

公开(公告)号：US20230403371A1

公开(公告)日：2023-12-14

申请号：US18206459

申请日：2023-06-06

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Xin JIN ,  Guotao SHIN ,  Youxin CHEN ,  Longhai WU ,  Jie CHEN ,  Jayoon KOO ,  Cheulhee HAHM

IPC: H04N7/01 ,  G06T7/246

CPC classification number: H04N7/014 ,  G06T7/246 ,  H04N7/0127 ,  G06T2207/10016 ,  G06T2207/20084

Abstract: A method for generating a video intermediate frame, including obtaining a target video frame pair; constructing an image pyramid for each video frame in the target video frame pair; and generating an intermediate frame of the target video frame pair by using a bidirectional optical flow estimation model and a pixel synthesis model in a layer-by-layer recursive calling manner according to an order of the image pyramid from a high layer to a low layer based on the image pyramid, wherein the generating of the intermediate frame of the target video frame pair comprising: repairing a bidirectional optical flow corresponding to a previous layer using the bidirectional optical flow estimation model, and repairing a previous intermediate frame corresponding to the previous layer using the pixel synthesis model.

公开(公告)号：US20230281829A1

公开(公告)日：2023-09-07

申请号：US18168209

申请日：2023-02-13

Applicant: Samsung Electronics Co., Ltd.

Inventor： Xin JIN ,  Guotao SHEN ,  Youxin CHEN ,  Longhai WU ,  Jie CHEN ,  Jayoon KOO

IPC: G06T7/20 ,  G06T3/00 ,  G06T3/40

CPC classification number: G06T7/20 ,  G06T3/0093 ,  G06T3/40 ,  G06T2207/20016 ,  G06T2207/20084

Abstract: A bidirectional optical flow estimation method and apparatus are provided. The method includes acquiring a target image pair of which optical flow is to be estimated, and constructing an image pyramid for each target image in the target image pair respectively, and performing bidirectional optical flow estimation using a pre-trained optical flow estimation model based on the image pyramid, to obtain bidirectional optical flow between the target images. An optical flow estimation module in the optical flow estimation model is recursively called to perform the bidirectional optical flow estimation sequentially based on images of respective layers in the image pyramid according to a preset order, forward warping towards middle processing is performed on an image of a corresponding layer of the image pyramid before each call of the optical flow estimation module, and an image of an intermediate frame obtained by the forward warping towards middle processing is inputted into the optical flow estimation module. With the disclosure, the efficiency and generalization of bidirectional optical flow estimation can be improved, and model training and optical flow estimation overheads can be reduced.

公开(公告)号：US20230177638A1

公开(公告)日：2023-06-08

申请号：US17312276

申请日：2021-01-11

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Wookhyung KIM ,  Ilhyun CHO ,  Jayoon KOO ,  Namuk KIM

IPC: G06T3/40 ,  G06V10/74 ,  G06V10/82

CPC classification number: G06T3/4046 ,  G06T3/4053 ,  G06V10/761 ,  G06V10/82

Abstract: An artificial intelligence (AI) upscaling apparatus for upscaling a low-resolution image to a high-resolution image includes: a memory storing one or more instructions; and a processor configured to execute the one or more instructions stored in the memory, wherein the processor is configured to: obtain a second image corresponding to a first image, which is downscaled from an original image by an AI downscaling apparatus by using a first deep neural network (DNN); and obtain a third image by upscaling the second image by using a second DNN corresponding to the first DNN, and wherein the second DNN is trained to minimize a difference between a first restored image, which results from applying no pixel movement to an original training image, and second restored images, which result from downscaling, upscaling, and subsequently retranslating one or more translation images obtained by applying pixel movement to the original training image.

公开(公告)号：US20210118093A1

公开(公告)日：2021-04-22

申请号：US17030905

申请日：2020-09-24

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Anant BAIJAL ,  Vivek AGARWAL ,  Jayoon KOO

IPC: G06T3/40 ,  G06T7/11 ,  G06T7/174 ,  G06K9/46 ,  G06N3/08

Abstract: Provided are a computing apparatus for constructing a mosaic image and an operation method of the same. The computing apparatus includes: a memory storing one or more instructions; and a processor configured to execute the one or more instructions stored in the memory to: segment an input image into a plurality of sub areas to obtain a plurality of sub area images, extract a feature from each of the plurality of sub area images, generate a plurality of source images respectively corresponding to the plurality of sub areas using an image generation neural network, the image generation neural network using, as a condition, the feature extracted from each of the plurality of sub area images, and combine the plurality of source images respectively corresponding to the plurality of sub areas to generate a mosaic image.