-
公开(公告)号:US20240244172A1
公开(公告)日:2024-07-18
申请号:US18275596
申请日:2021-03-18
Applicant: Intel Corporation
Inventor: Ying Luo , Hua Zhang , Xiaomin Chen , Xin Kang
IPC: H04N13/117 , H04N13/194 , H04N13/332 , H04N13/366 , H04N21/81
CPC classification number: H04N13/117 , H04N13/194 , H04N13/332 , H04N13/366 , H04N21/816
Abstract: Techniques related to viewport selection in immersive video contexts are discussed. Such techniques include generating multiple viewport predictions each for a future time interval and based on different prediction models, ranking the viewport predictions using error descriptors of the prediction models, selecting a viewport prediction for the future time intervals using the ranking, and correcting the selected viewport predictions using the error descriptors.
-
公开(公告)号:US12056786B2
公开(公告)日:2024-08-06
申请号:US17256201
申请日:2018-09-27
Applicant: Intel Corporation
Inventor: Weihan Wang , Jie He , Junhua Hou , Hua Zhang , Xiangning Ma , Zhi Hong Yu
CPC classification number: G06T1/20 , G06F9/45558 , G06F9/5022 , G06F9/5077 , G06F9/542 , G06F2009/45583
Abstract: An apparatus and method are described for graphics virtualization with late synchronization. For example, a virtualized graphics execution environment is implemented on a host, including a hypervisor to virtualize graphics processing resources for one or more virtual machines (VMs). A plurality of graphics commands are received responsive to execution of a graphics application in one of the VMs. The graphics commands are persisted until a frame triggering event is detected. Upon detection of a frame triggering event, the persisted graphics commands are submitted to the host.
-
公开(公告)号:US20240289929A1
公开(公告)日:2024-08-29
申请号:US18573971
申请日:2021-10-28
Applicant: Intel Corporation
Inventor: Yanying Sun , Jianhui Dai , Kin-Hang Cheung , Qingfeng Li , Hua Zhang , Yesheng Xu
Abstract: Methods and apparatus to perform mask-based depth enhancement for multi-view systems are disclosed herein. An example apparatus to adjust an input depth image of an image frame including the input depth image and an input color image includes at least one memory, instructions in the apparatus, and processor circuitry to execute the instructions to identify a color patch and a depth patch for an image pixel in a border area of the image frame, output an adjusted depth map based on at least one of (i) a mismatch between values of the color patch and a center pixel color of the color patch or (ii) a mismatch between values of the depth patch and a center pixel depth of the depth patch, output an adjusted mask map associated with the input depth image based on a position of at least one camera used to capture the image, and perform iterative depth data gap filling based on the adjusted depth map and the adjusted mask map to obtain an adjusted depth image corresponding to the input depth image.
-
公开(公告)号:US20220368946A1
公开(公告)日:2022-11-17
申请号:US17762404
申请日:2019-11-07
Applicant: Intel Corporation
Inventor: Junyong Ding , Mohammad Haghighat , Lei Zhai , Gang Shen , Jianhui Dai , Hua Zhang , Yanying Sun
IPC: H04N19/597 , H04N19/105 , H04N19/44
Abstract: Systems, apparatuses and methods may provide for encoder technology that selects, in response to a request from a client device, a first video stream from a first plurality of video streams dedicated to a first tile in video content and selects, in response to the request, a second video stream from a second plurality of video streams dedicated to a second tile in the video content. The encoder technology may also send the selected first and second video streams to a client device. Additionally, decoder technology may allocate a first decoder device to the first video stream and allocate a second decoder device to the second video stream. In one example, the first video stream and the second video stream include one or more different codec parameter values.
-
-
-