公开(公告)号：US10713835B2

公开(公告)日：2020-07-14

申请号：US15923272

申请日：2018-03-16

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Pavan Sudheendra ,  Sarvesh ,  Yogesh Manav ,  Adappa M Gourannavar ,  Rahul Varna ,  Sumanta Baruah

IPC: G06T13/80 ,  G06F3/0488 ,  G06F1/16 ,  G06F3/041 ,  G06F3/16 ,  G06T7/20

Abstract: A method for of playing an animation image, the method including: obtaining a plurality of images; displaying a first image of the plurality of images; detecting a first event as a trigger to play the animation image for a first object of the first image; and playing the animation image for the first object using the plurality of images.

公开(公告)号：US09922439B2

公开(公告)日：2018-03-20

申请号：US14809571

申请日：2015-07-27

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Pavan Sudheendra ,  Sarvesh ,  Yogesh Manav ,  Adappa M Gourannavar ,  Rahul Varna ,  Sumanta Baruah

IPC: G06T13/80 ,  G06F3/041 ,  G06F3/16 ,  G06T7/20 ,  G06F3/0488 ,  G06F1/16

CPC classification number: G06T13/80 ,  G06F1/1643 ,  G06F1/1686 ,  G06F1/1694 ,  G06F3/041 ,  G06F3/0488 ,  G06F3/167 ,  G06T7/20

Abstract: A method for of playing an animation image, the method including: obtaining a plurality of images; displaying a first image of the plurality of images; detecting a first event as a trigger to play the animation image for a first object of the first image; and playing the animation image for the first object using the plurality of images.

公开(公告)号：US20230004778A1

公开(公告)日：2023-01-05

申请号：US17857731

申请日：2022-07-05

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sai Karthikey PENTAPATI ,  Amit SHUKLA ,  Kinsuk DAS ,  Raj Narayana GADDE ,  Sandeep MISHRA ,  Sarvesh ,  Sandeep PALAKKAL

IPC: G06N3/04 ,  G06K9/62 ,  G06F7/76

Abstract: The disclosure relates to method and system for on-device inference in a deep neural network (DNN). The method comprises: determining whether one or more layers of the DNN satisfy one of a first, a second and a third condition, the one or more layers including one or more convolution layers and one or more resampling layers; performing the on-device inference based on the determination, wherein performing the on-device inference comprises at least one of: optimizing the one or more convolution layers in the one or more parallel branches based on the one or more layers of the DNN satisfying the first condition, optimizing the at least one of the resampling layers based on the one or more layers of the DNN satisfying the second condition, and modifying operation of the at least one of the resampling layers based on the one or more layers of the DNN satisfying the third condition.

公开(公告)号：US20220385914A1

公开(公告)日：2022-12-01

申请号：US17868421

申请日：2022-07-19

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sirish Kumar PASUPULETI ,  Raj Narayana GADDE ,  Sarvesh ,  Kinsuk DAS ,  Ankit SINGH ,  Sai Harish AVULA

IPC: H04N19/132 ,  H04N19/30 ,  H04N19/86 ,  H04N19/172

Abstract: The present disclosure refers to methods and apparatuses for processing of high-resolution video content. In an embodiment, a method includes generating a first group of video frames from the video content. The first group of video frames has a first resolution lower than a resolution of the video content and a first rate-distortion score. The method further includes generating a second group of video frames from the video content. The second group of video frames has a second resolution lower than the resolution of the video content and a second rate-distortion score. The method further includes selecting an optimal group of video frames from the first and second groups of video frames based on a comparison between the first and second rate-distortion scores. The optimal group of video frames has a rate-distortion score lower than the first and the second rate-distortion scores.

公开(公告)号：US20240267624A1

公开(公告)日：2024-08-08

申请号：US18434056

申请日：2024-02-06

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Raj Narayana GADDE ,  Sarvesh ,  Yathish Reddy ,  Addanki Sankara Rao ,  Pravin Ramachandran Nair

IPC: H04N23/68 ,  H04N5/262 ,  H04N23/65 ,  H04N23/81

CPC classification number: H04N23/683 ,  H04N5/2628 ,  H04N23/65 ,  H04N23/6811 ,  H04N23/6812 ,  H04N23/81

Abstract: A method may comprise detecting at least one motion of the electronic device while capturing a plurality of media frames, determining a type of the at least one motion of the electronic device while capturing the plurality of media frames, determining a variation in the type of the at least one motion of the electronic device over a pre-determined period of time, selecting at least one stabilization procedure from a plurality of stabilization procedures and a frame fusion procedure from a plurality of frame fusion procedures based on the type of the at least one motion of the electronic device and the variation in the type of the at least one motion of the electronic device, and stabilizing, after the capturing of the plurality of media frames, the plurality of media frames based on the at least one selected stabilization procedure and the selected frame fusion procedure.

公开(公告)号：US11450055B2

公开(公告)日：2022-09-20

申请号：US16927621

申请日：2020-07-13

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Pavan Sudheendra ,  Sarvesh ,  Yogesh Manav ,  Adappa M Gourannavar ,  Rahul Varna ,  Sumanta Baruah

IPC: G06T13/80 ,  G06T7/20 ,  G06F3/0488 ,  G06F1/16 ,  G06F3/041 ,  G06F3/16

Abstract: A method for of playing an animation image, the method including: obtaining a plurality of images; displaying a first image of the plurality of images; detecting a first event as a trigger to play the animation image for a first object of the first image; and playing the animation image for the first object using the plurality of images.

公开(公告)号：US11057553B2

公开(公告)日：2021-07-06

申请号：US16503910

申请日：2019-07-05

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sourabh Singh Yadav ,  Pankaj Kumar Bajpai ,  Sarvesh ,  Pranav Prakash Deshpande ,  Lokesh Rayasandra Boregowda ,  Rituparna Sarkar

IPC: H04N5/225 ,  H04N7/14 ,  H04M1/02

Abstract: A device and a method for capturing media by using a device including a plurality of flaps are provided. At least two flaps among the plurality of flaps each include at least one camera. The method includes analyzing preview images of the cameras based on a first media capture mode, adjusting a bend angle between the at least two flaps based on the analysis of the preview images to determine at least one baseline distance, and obtaining at least one media in the first capture mode at the at least one baseline distance.