-
公开(公告)号：US20240394830A1
公开(公告)日：2024-11-28
申请号：US18433133
申请日：2024-02-05
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Sajid Sadi , Varun Menon , Siddarth Ravichandran , Chuhua Wang , Hyun Jae Kang , Rahul Lokesh , Vignesh Gokul
Abstract: Synthesizing high-resolution input for rendering a digital human includes generating, with a generative artificial intelligence (AI) model, a distorted image of the digital human by enhancing a region of interest (ROI) within the distorted image relative to other regions of the distorted image. The generative AI model is previously trained against a distorted control image generated using a distortion function to distort a control image used to guide image generation by the generative AI model. The distorted control image is generated by reconfiguring and augmenting pixels of the control image. An undistorted image of the digital human is generated using a reverse distortion function to reverse distortion of the distorted image.
-
公开(公告)号：US20180204059A1
公开(公告)日：2018-07-19
申请号：US15841157
申请日：2017-12-13
Applicant: Samsung Electronics Co., Ltd.
Inventor： Stanislaw Antol , Abhijit Bendale , Simon J. Gibbs , Won J. Jeon , Hyun Jae Kang , Jihee Kim , Bo Li , Anthony S. Liot , Lu Luo , Pranav K. Mistry , Zhihan Ying
Abstract: A method includes retrieving, by a device, contextual information based on at least one of an image, the device, user context, or a combination thereof. At least one model is identified from multiple models based on the contextual information and at least one object recognized in an image based on at least one model. At least one icon is displayed at the device. The at least one icon being associated with at least one of an application, a service, or a combination thereof providing additional information.
-
公开(公告)号：US12169880B2
公开(公告)日：2024-12-17
申请号：US17967868
申请日：2022-10-17
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Ondrej Texler , Dimitar Petkov Dinev , Ankur Gupta , Hyun Jae Kang , Anthony Sylvain Jean-Yves Liot , Siddarth Ravichandran , Sajid Sadi
Abstract: Image generation using a hierarchical, model-based system includes generating a first region of an image using a first neural network model. The first region of the image is provided to a second neural network model as input. A second region of the image is generated using the second neural network model. The second region of the image shares a boundary with at least a portion of the first region of the image.
-
公开(公告)号：US20240394855A1
公开(公告)日：2024-11-28
申请号：US18433157
申请日：2024-02-05
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Sajid Sadi , Varun Menon , Siddarth Ravichandran , Hyun Jae Kang , Anil Unnikrishnan , Anthony Sylvain Jean-Yves Liot
Abstract: Synthesizing high-resolution data includes distorting, with a distortion function, a region of interest (ROI) within an input of inferential data. The distorting generates distortion data within which the ROI is enhanced relative to other regions of the distortion data. A generative artificial intelligence (AI) model generates synthetic data in response to input of the distortion data. The generative AI model is trained against a distorted ground truth generated using the distortion function to distort one or more regions of interest ROI within source data used to guide the generative AI model in generating the synthetic data.
-
公开(公告)号：US20240354996A1
公开(公告)日：2024-10-24
申请号：US18428487
申请日：2024-01-31
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Varun Menon , Siddarth Ravichandran , Ankur Gupta , Hyun Jae Kang , Sajid Sadi
IPC: G06T9/00 , G06V10/764
CPC classification number: G06T9/00 , G06V10/764
Abstract: Autoregressive content rendering for temporally coherent video generation includes generating, by an autoencoder, a plurality of predicted images. The plurality of predicted images is fed back to the autoencoder network. The plurality of predicted images may be encoded by the autoencoder network to generate a plurality of encoded predicted images. The autoencoder network encodes a plurality of keypoint images to generate a plurality of encoded keypoint images. One or more predicted images of the plurality of predicted images are generated by the autoencoder network by decoding a selected encoded keypoint image of the plurality of encoded keypoint images with an encoded predicted image of the plurality of encoded predicted images of a prior iteration of the autoencoder network.
-
Patent Agency Ranking
公开(公告)号：US20240221254A1
公开(公告)日：2024-07-04
申请号：US18342726
申请日：2023-06-27
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Hyun Jae Kang , Siddarth Ravichandran , Ondrej Texler , Dimitar Petkov Dinev , Anthony Sylvain Jean-Yves Liot , Sajid Sadi
Abstract: Image-to-image translations using 1D inputs includes concatenating multiple 1D vectors forming a concatenated 1D vector. The multiplicity of 1D vectors includes 1D vectors of at least two different modalities. An encoded 1D vector is generated by encoding the concatenated 1D vector. An encoded 2D array of features is generated by reshaping an arrangement of features of the encoded 1D feature vector. An image of a virtual human is generated by decoding the encoded 2D array.
-
公开(公告)号：US20240331088A1
公开(公告)日：2024-10-03
申请号：US18422466
申请日：2024-01-25
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Rahul Lokesh , Sandipan Banerjee , Hyun Jae Kang , Ondrej Texler , Sajid Sadi
IPC: G06T3/4053 , G06T3/4046
CPC classification number: G06T3/4053 , G06T3/4046
Abstract: An ultralight rendering system is capable of generating first content locally within a first data processing system. The first data processing system is capable of monitoring for second content conveyed from a second data processing system. The first data processing system plays a version of the first content. The first data processing system is capable of dynamically switching, by the first data processing system, between playing the version of the first content and playing a version of the second content based on receipt of the second content by the first data processing system.
-
公开(公告)号：US20240323459A1
公开(公告)日：2024-09-26
申请号：US18419123
申请日：2024-01-22
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Anthony Sylvain Jean-Yves Liot , Anil Unnikrishnan , Sajid Sadi , Sandipan Banerjee , Vignesh Gokul , Janvi Chetan Palan , Hyun Jae Kang , Ondrej Texler
IPC: H04N21/231 , H04N21/266 , H04N21/845
CPC classification number: H04N21/23106 , H04N21/266 , H04N21/8455
Abstract: Computer-implemented content delivery includes caching a source content having a plurality of bridge points. A user event indicating an interaction with a user is received. The user event is received during playback of the source content. In response to the user event, a template is selected from a plurality of cached templates. The template corresponds to a bridge point selected from the plurality of bridge points of the source content as an exit point from the source content. In response to the user event, a bridge is dynamically generated. The bridge links the bridge point with the template. In response to the user event, a target content is selected from a plurality of cached target contents. In response to the user event, the bridge, the template, and the target content is conveyed to a device of the user for playback following the bridge point of the source content.
-
公开(公告)号：US10902262B2
公开(公告)日：2021-01-26
申请号：US15875393
申请日：2018-01-19
Applicant: Samsung Electronics Co., Ltd.
Inventor： Stanislaw Antol , Abhijit Bendale , Simon J. Gibbs , Won J. Jeon , Hyun Jae Kang , Jihee Kim , Bo Li , Anthony S. Liot , Lu Luo , Pranav K. Mistry , Zhihan Ying
IPC: G06K9/00 , H04L29/08 , G06T19/00 , G06N20/00 , G06N3/08 , G06K9/62 , G06F11/30 , H04L29/06 , G06F11/34 , G06N5/02 , G06T11/00 , G06K9/32 , G06K9/66 , G06F3/14
Abstract: One embodiment provides a method comprising classifying one or more objects present in an input comprising visual data by executing a first set of models associated with a domain on the input. Each model corresponds to an object category. Each model is trained to generate a visual classifier result relating to a corresponding object category in the input with an associated confidence value indicative of accuracy of the visual classifier result. The method further comprises aggregating a first set of visual classifier results based on confidence value associated with each visual classifier result of each model of the first set of models. At least one other model is selectable for execution on the input based on the aggregated first set of visual classifier results for additional classification of the objects. One or more visual classifier results are returned to an application running on an electronic device for display.
-
公开(公告)号：US10573633B2
公开(公告)日：2020-02-25
申请号：US15830988
申请日：2017-12-04
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Tae Sun Kim , Hyun Jae Kang , Tae Hoi Park , Jin Seong Lee , Eun Sol Choi , Min Keun Kwak , Byung Kap Kim , Sung Won Choi
IPC: H01L23/48 , H01L27/02 , G06F17/50 , H01L23/522 , H01L23/528 , G03F7/20 , H01L23/544
Abstract: A semiconductor device includes a first overlay group and a second overlay group disposed on a semiconductor substrate. The first overlay group includes first lower overlay patterns which extend in a first direction, first upper overlay patterns overlapping the first lower overlay patterns, and first via overlay patterns interposed between the first lower overlay patterns and the first upper overlay patterns. The second overlay group includes second lower overlay patterns which extend in a second direction, second upper overlay patterns overlapping the second lower overlay patterns, and second via overlay patterns interposed between the second lower overlay patterns and the second upper overlay patterns. The second lower overlay patterns include end portions adjacent to and spaced apart from the first overlay group.
-
-
-
-
-
-
-
-
-
Search Results
21
records
(took 0.019 seconds)
