公开(公告)号：US12132995B2

公开(公告)日：2024-10-29

申请号：US17793348

申请日：2020-02-17

申请人： Intel Corporation

发明人： Huan Dou ,  Lidong Xu ,  Xiaoxia Cai ,  Chen Wang ,  Yi-Jen Chiu

IPC分类号： H04N23/698 ,  G06T5/77 ,  H04N19/597 ,  H04N19/80 ,  H04N19/86

CPC分类号： H04N23/698 ,  G06T5/77 ,  H04N19/597 ,  H04N19/80 ,  H04N19/86 ,  G06T2207/20081 ,  G06T2207/20084

摘要： An example apparatus for enhancing video includes a decoder to decode a received 360-degree projection format video bitstream to generate a decoded 360-degree projection format video. The apparatus also includes a viewport generator to generate a viewport from the decoded 360-degree projection format video. The apparatus further includes a convolutional neural network (CNN)-based filter to remove an artifact from the viewport to generate an enhanced image. The apparatus further includes a displayer to send the enhanced image to a display.

公开(公告)号：US11750787B2

公开(公告)日：2023-09-05

申请号：US17526633

申请日：2021-11-15

申请人： Intel Corporation

发明人： Mayuresh Varerkar ,  Stanley Baran ,  Michael Apodaca ,  Prasoonkumar Surti ,  Atsuo Kuwahara ,  Narayan Biswal ,  Jill Boyce ,  Yi-Jen Chiu ,  Gokcen Cilingir ,  Barnan Das ,  Atul Divekar ,  Srikanth Potluri ,  Nilesh Shah ,  Archie Sharma

IPC分类号： H04H60/33 ,  H04N13/111 ,  H04N19/597 ,  G06F9/38 ,  G06F3/01 ,  G06N20/00

CPC分类号： H04N13/111 ,  G06F3/012 ,  G06F9/3877 ,  G06N20/00 ,  H04N19/597

摘要： A mechanism is described for facilitating adaptive resolution and viewpoint-prediction for immersive media in computing environments. An apparatus of embodiments, as described herein, includes one or more processors to receive viewing positions associated with a user with respect to a display, and analyze relevance of media contents based on the viewing positions, where the media content includes immersive videos of scenes captured by one or more cameras. The one or more processors are further to predict portions of the media contents as relevant portions based on the viewing positions and transmit the relevant portions to be rendered and displayed.

公开(公告)号：US11616968B2

公开(公告)日：2023-03-28

申请号：US17094742

申请日：2020-11-10

申请人： Intel Corporation

发明人： Zhipin Deng ,  Iole Moccagatta ,  Lidong Xu ,  Wenhao Zhang ,  Yi-Jen Chiu

IPC分类号： H04N19/51 ,  G06T7/238 ,  H04N19/57 ,  H04N19/176 ,  H04N19/593

摘要： Techniques related to motion estimation with neighbor block pattern for video coding.

公开(公告)号：US20230034367A1

公开(公告)日：2023-02-02

申请号：US17955223

申请日：2022-09-28

申请人： Intel Corporation

发明人： Ximin Zhang ,  Yi-Jen Chiu ,  Keith Rowe

IPC分类号： H04N19/117 ,  H04N19/82 ,  H04N19/186 ,  H04N19/172

摘要： Example methods, apparatus, systems and articles of manufacture to implement adaptive loop filter classification and selection for video coding are disclosed. Examples disclosed herein determine whether a collection of available adaptive loop filter sets associated with luma components of the input picture is empty. When the collection of available adaptive loop filter sets is not empty, disclosed examples also enable adaptive loop filtering for the luma components of the input picture, and select at least one of the collection of available adaptive loop filter sets to include in a selection of adaptive loop filter sets for the input picture, with the selection based on an order in which ones of the available adaptive loop filter sets in the collection were derived. Some disclosed examples additionally or alternatively perform block classification to determine accumulated class statistics for derivation of an adaptive loop filter set associated with the input picture.

公开(公告)号：US20220020226A1

公开(公告)日：2022-01-20

申请号：US17388946

申请日：2021-07-29

申请人： Intel Corporation

发明人： Ke Chen ,  Zhipin Deng ,  Xiaoxia Cai ,  Chen Wang ,  Ya-Ti Peng ,  Yi-Jen Chiu ,  Lidong Xu

IPC分类号： G06T19/20 ,  G06T7/90 ,  G06K9/00 ,  G06T5/00 ,  G06T15/00

摘要： Systems, apparatus, articles of manufacture and methods for face augmentation in video are disclosed. An example apparatus includes executable code to detect a face of a subject in the video, detect a gender of the subject based on the face, detect a skin tone of the subject based on the face, apply a first process to smooth skin on the face in the video, apply a second process to change the skin tone of the face, apply a third process to slim the face, apply a fourth process to adjust a size of eyes on the face, and apply a fifth process to remove an eye bag from the face. One or more of the first process, the second process, the third process, the fourth process, or the fifth process adjustable based on one or more of the gender or an age. The example apparatus also includes one or more processors to generate modified video with beauty effects, the beauty effects based on one or more of the first process, the second process, the third process, the fourth process, or the fifth process.

公开(公告)号：US11049266B2

公开(公告)日：2021-06-29

申请号：US16050468

申请日：2018-07-31

申请人： Intel Corporation

发明人： Scott Janus ,  Barnan Das ,  Hugues Labbe ,  Jong Dae Oh ,  Gokcen Cilingir ,  James Holland ,  Narayan Biswal ,  Yi-Jen Chiu ,  Qian Xu ,  Mayuresh Varerkar ,  Sang-Hee Lee ,  Stanley Baran ,  Srikanth Potluri ,  Jason Ross ,  Maruthi Sandeep Maddipatla

IPC分类号： G06T7/262 ,  H04N19/436 ,  G06T3/40 ,  G06T15/08 ,  G06T17/00 ,  G06T7/30

摘要： An apparatus comprises a processor to divide a first point cloud data set frame representing a three dimensional space at a first point in time into a matrix of blocks, determine at least one three dimensional (3D) motion vector for at least a subset of blocks in the matrix of blocks, generate a predicted second point cloud data set frame representing a prediction of the three dimensional space at a second point in time by applying the at least one 3D motion vector to the subset of blocks in the matrix of blocks, compare the predicted second point cloud data set frame to a second point cloud data set frame representing a prediction of the three dimensional space at a second point in time to generate a prediction error parameter, and encode the second point cloud data set frame as a function of the first point cloud data set frame and the at least one three dimensional (3D) motion vector when the prediction error factor is beneath an error threshold to produce an encoded second point cloud data set frame.

公开(公告)号：US10984504B2

公开(公告)日：2021-04-20

申请号：US16453652

申请日：2019-06-26

申请人： Intel Corporation

发明人： Jong Dae Oh ,  Vijay Sundaram ,  Jingyang Xue ,  Yi-Jen Chiu

IPC分类号： G06K9/00 ,  G06T3/40 ,  G06T7/90

摘要： Techniques related to demosaicing for digital image processing are discussed. Such techniques include correcting defective pixels by detecting hot and warm pixels and correcting such detected hot and warm pixels based on neighboring pixels and angle compensation including detecting dominant angles and compensating for such detected angles during demosaicing.

公开(公告)号：US10908679B2

公开(公告)日：2021-02-02

申请号：US15495034

申请日：2017-04-24

申请人： Intel Corporation

发明人： Robert J. Johnston ,  Satyanarayana Avadhanam ,  Changliang Wang ,  Narayan Biswal ,  Archie Sharma ,  Richmond Hicks ,  Joydeep Ray ,  Abhishek R. Appu ,  Stanley J. Baran ,  Sang-Hee Lee ,  Atthar H. Mohammed ,  Jong Dae Oh ,  Hiu-Fai Chan ,  Sumit Mohan ,  Jill M. Boyce ,  Yi-Jen Chiu

IPC分类号： G06F3/01 ,  G06T15/10

摘要： Systems, apparatuses and methods may provide for technology to improve user experience when viewing simulated 3D objects on a display. Head and upper-body movements may be tracked and recognized as gestures to alter the displayed viewing angle. The technology provides for a very natural way to look around, under, or over objects.

公开(公告)号：US20200327702A1

公开(公告)日：2020-10-15

申请号：US16914083

申请日：2020-06-26

申请人： INTEL CORPORATION

发明人： Chen Wang ,  Ximin Zhang ,  Huan Dou ,  Yi-Jen Chiu ,  Sang-Hee Lee

IPC分类号： G06T9/00 ,  G06T3/40 ,  H04N19/30 ,  H04N19/132 ,  H04N19/159 ,  H04N19/184 ,  H04N19/176 ,  G06K9/62 ,  G06N3/08

摘要： Techniques related to accelerated video enhancement using deep learning selectively applied based on video codec information are discussed. Such techniques include applying a deep learning video enhancement network selectively to decoded non-skip blocks that are in low quantization parameter frames, bypassing the deep learning network for decoded skip blocks in low quantization parameter frames, and applying non-deep learning video enhancement to high quantization parameter frames.

公开(公告)号：US20200304710A1

公开(公告)日：2020-09-24

申请号：US16808626

申请日：2020-03-04

申请人： Intel Corporation

发明人： Jill M. Boyce ,  Stanley J. Baran ,  Sumit Mohan ,  Yi-Jen Chiu ,  Jason Tanner ,  Atthar H. Mohammed ,  Richmond Hicks ,  Barnan Das

IPC分类号： H04N5/232 ,  H04N5/247 ,  H04N7/18 ,  H04N21/6587 ,  H04N21/84 ,  H04N21/4728 ,  H04N21/218 ,  H04N21/81 ,  H04L29/06

摘要： Systems, apparatuses and methods may determine, on a per camera basis, an interest level with respect to panoramic video content, identify a subset of cameras in a plurality of cameras for which the interest level is below a threshold, and reduce power consumption in the subset of cameras. Additionally, technology may determine a projection format associated with panoramic video content, identify one or more discontinuous boundaries in the projection format, and modify an encoding scheme associated with the panoramic video content based on the discontinuous boundaries. Moreover, an encoded frame may be assigned to a temporal scalability layer that has a higher priority than a layer to which an asynchronous space warp frame is assigned. Additionally, technology may reduce the encoding complexity of a boundary between an active region and an inactive region in fisheye content.