-
公开(公告)号：WO2022197001A1
公开(公告)日：2022-09-22
申请号：PCT/KR2022/003239
申请日：2022-03-08
发明人： BINDIGAN HARIPRASANNA, Pawan Prasad , DAS, Saikat Kumar , K S, Green Rosh , BOREGOWDA, Lokesh Rayasandra , SINGH, Balvinder , PEDDIGARI, Venkat Ramana , SHUKLA, Alok Shankarlal
摘要： A method for removing an artifact in a high resolution image by an electronic device is provided. The method includes receiving the high resolution image comprising the artifact. Further, the method includes downscaling the high resolution image into a plurality of lower resolution images. Further, the method includes removing the artifact from the plurality of lower resolution images by applying at least one first machine learning model from a plurality of machine learning models on the plurality of lower resolution images. Further, the method includes generating a high resolution image free from the artifact by applying at least one second machine learning model from the plurality of machine learning models on an output from the at least one first machine learning model. The output from each of the machine learning model comprises a low resolution image free from the artifact.
-
公开(公告)号：WO2022154167A1
公开(公告)日：2022-07-21
申请号：PCT/KR2021/002665
申请日：2021-03-04
发明人： CHOI, Sungsoo , KIM, Beomsu , YOO, Jisung , LEE, Dasom , SHULKA, Alok Shankarlal , SINGH, Balvinder
摘要： Disclosed is a device and method for processing media data. According to an embodiment, an electronic device may include a memory and at least one processor. The at least one processor may be configured to receive media data, generate tags indicating a degradation type and degradation intensity of degradations detected from the media data by analyzing the media data, determine a degradation enhancement pipeline including at least two degradation enhancement solutions among the plurality of degradation enhancement solutions and an order in which the degradation enhancement solutions are applied, for the media data, based on the tags, obtain enhanced media data by applying the degradation enhancement pipeline to the media data, and output information for recommending the enhanced media data to a user through the display.
-
公开(公告)号：WO2023059058A1
公开(公告)日：2023-04-13
申请号：PCT/KR2022/014980
申请日：2022-10-05
发明人： SINGH, Balvinder , GADDE, Raj Narayana , SHUKLA, Alok Shankarlal , PASUPULETI, Sirish Kumar , PAI, Narasimha Gopalakrishna , NAIR, Prajit Sivasankaran
摘要： Provided are methods and systems for generating metadata pertaining to a RAW frame. The method includes selecting an input frame from a captured RAW frame, a plurality of frames obtained by processing the captured RAW frame, and a scaled RAW frame, selecting identified salient regions in an output frame, constructed from the captured RAW frame, based on errors between regions of the input frame and a corresponding reconstruction of the region of the input frame from the identified salient regions in the output frame, obtaining a plurality of reconstructed frames, reconstructed from a plurality of blocks of each salient region, corresponding to a plurality of regions of the input frame, And generating metadata for reconstructing the captured RAW frame by encoding a plurality of errors between the plurality of reconstructed frames and corresponding plurality of regions of the input frame, and a reconstruction technique used for reconstructing the plurality of reconstructed frames.
-
公开(公告)号：WO2020076128A1
公开(公告)日：2020-04-16
申请号：PCT/KR2019/013388
申请日：2019-10-11
发明人： KINI, Raviprasad Mohan , BHAT, Gururaj , SUDHEENDRA, Pavan , KULKARNI, Girish , MUNIRATHNAM, Vineeth Thanikonda , MURTHY, Sanjay Narasimha , SINGH, Balvinder
摘要： A method for switching between a first lens and a second lens in an electronic device includes displaying, by the electronic device, a first frame showing a field of view (FOV) of the first lens; detecting, by the electronic device, an event that causes the electronic device to transition from displaying the first frame to displaying a second frame showing a FOV of the second lens; generating, by the electronic device and based on the detecting the event, at least one intermediate frame for transitioning from the first frame to the second frame; and switching, by the electronic device and based on the detecting the event, from the first lens to the second lens and displaying the second frame, wherein the at least one intermediate frame is displayed after the displaying the first frame and before the displaying the second frame while the switching is performed.
-
公开(公告)号：WO2020017937A1
公开(公告)日：2020-01-23
申请号：PCT/KR2019/008990
申请日：2019-07-19
发明人： JAISWAL, Swadha , MUKHERJEE, Debayan , AMRIT, Mannu , PAL, Shivi , KULKARNI, Vibha Venkatesh , SUDHEENDRA, Pavan , BAJPAI, Pankaj Kumar , SINGH, Balvinder , PAI, Narasimha Gopalakrishna , MURTHY, Sanjay Narasimha , MUNIRATHNAM, Vineeth Thanikonda
摘要： Embodiments herein disclose a method for recommending an image capture mode by an electronic device (100). The method includes identifying, by the electronic device (100), at least one ROI displayed in a camera preview of the electronic device (100) for capturing an image in a non-ultra-wide image capture mode. Further, the method includes determining, by the electronic device (100), that the at least one ROI is suitable to capture in an ultra-wide image capture mode. Further, the method includes providing, by the electronic device (100), at least one recommendation to switch to the ultra-wide image capture mode from the non-ultra-wide image capture mode for capturing the image.
-
公开(公告)号：WO2022197001A8
公开(公告)日：2022-09-22
申请号：PCT/KR2022/003239
申请日：2022-03-08
发明人： BINDIGAN HARIPRASANNA, Pawan Prasad , DAS, Saikat Kumar , K S, Green Rosh , BOREGOWDA, Lokesh Rayasandra , SINGH, Balvinder , PEDDIGARI, Venkat Ramana , SHUKLA, Alok Shankarlal
IPC分类号： G06T5/00 , G06T3/40 , G06N3/08 , G06T2207/10016 , G06T2207/20016 , G06T2207/20081 , G06T2207/20084 , G06T2207/30242 , G06T3/4046 , G06T5/006 , G06T5/20 , G06V10/20 , G06V10/764 , G06V10/776 , G06V10/82
摘要： A method for removing an artifact in a high resolution image by an electronic device is provided. The method includes receiving the high resolution image comprising the artifact. Further, the method includes downscaling the high resolution image into a plurality of lower resolution images. Further, the method includes removing the artifact from the plurality of lower resolution images by applying at least one first machine learning model from a plurality of machine learning models on the plurality of lower resolution images. Further, the method includes generating a high resolution image free from the artifact by applying at least one second machine learning model from the plurality of machine learning models on an output from the at least one first machine learning model. The output from each of the machine learning model comprises a low resolution image free from the artifact.
-
7.发明申请
公开(公告)号：WO2022060088A1
公开(公告)日：2022-03-24
申请号：PCT/KR2021/012602
申请日：2021-09-15
发明人： KIM, Beomsu , SINGH, Balvinder , SHUKLA, Alok Shankarlal , YOO, Jisung , PAI, Narasimha Gopalakrishna , NAIR, Prajit Sivasankaran , GADDE, Raj Narayana , CHOI, Sungsoo , PASUPULETI, Sirish Kumar
IPC分类号： H04N5/21 , H04N21/466 , H04N21/235 , G06N20/00
摘要： A Method and an electronic device for detecting and removing artifacts/degradations in media. Embodiments trigger detection of artifacts and/or degradations in the media. The detection is triggered automatically or manually. Embodiments generate artifact/quality tag information associated with the media to indicate artifacts and/or degradations present in the media, and store the artifact/quality tag information as metadata or in a database. Embodiments identify, based on the artifact/quality tag information associated with the media, AI based media processing model to be applied on the media to enhance the media. Embodiments select a pipeline of the identified AI based media processing models, arranged in a predetermined order. The AI based media processing models are applied on the media in the predetermined order to enhance the media. Embodiments ensure optimality of the enhancement by determining that aesthetic score of the media has reached a maximum value after the enhancement.
-
-
-
-
-
-
搜索结果
7 条记录 (耗时 0.014 秒)
