-
11.发明申请SYSTEM, METHOD, AND COMPUTER PROGRAM PRODUCT FOR DISPLAYING A SCENE AS A LIGHT FIELD 审中-公开用于将场景显示为光场的系统，方法和计算机程序产品公开(公告)号：US20140327771A1
公开(公告)日：2014-11-06
申请号：US13875238
申请日：2013-05-01
Applicant: NVIDIA CORPORATION
Inventor： Chris A. Malachowsky , David Patrick Luebke , Douglas Robert Lanman
IPC: H04N7/18
CPC classification number: H04N7/18 , G02B3/0006 , G02B27/0025 , G02B27/0075 , G02B27/0093 , G02B27/017 , G09G3/001 , G09G5/00 , G09G2354/00 , H04N5/23293 , H04N7/183 , H04N13/261 , H04N13/307 , H04N13/366
Abstract: A system, method, and computer program product that displays a light field to simulate a reflected scene. The method includes the operations of receiving a scene representing an exterior viewpoint relative to an observer positioned in a vehicle, determining a pre-filtered image that simulates a reflection of the scene, where the pre-filtered image represents a light field and corresponds to a target image that simulates a mirror. The pre-filtered image is displayed as the light field to produce the target image.
Abstract translation: 显示光场以模拟反射场景的系统，方法和计算机程序产品。 该方法包括接收相对于位于车辆中的观察者表示外部视点的场景的操作，确定模拟场景反射的预滤波图像，其中预滤波图像表示光场并对应于 模拟镜像的目标图像。 预过滤图像被显示为光场以产生目标图像。
-
12.发明申请SYSTEM, METHOD, AND COMPUTER PROGRAM PRODUCT FOR SAMPLING A HIERARCHICAL DEPTH MAP 有权用于采样分层深度图的系统，方法和计算机程序产品公开(公告)号：US20140146045A1
公开(公告)日：2014-05-29
申请号：US13685599
申请日：2012-11-26
Applicant: NVIDIA CORPORATION
Inventor： Morgan McGuire , David Patrick Luebke , Michael Thomas Mara
IPC: G06T15/40
CPC classification number: G06T15/405 , G06T15/50 , G06T15/506 , G06T15/55 , G06T15/60 , G06T15/80 , G06T2215/12
Abstract: A system, process, and computer program product are provided for sampling a hierarchical depth map. An approach for sampling the hierarchical depth map includes the steps of generating a hierarchical depth map and reading a value associated with a sample pixel from a target level of the hierarchical depth map based on a difference between the sample pixel and a target pixel. The hierarchical depth map includes at least two levels.
Abstract translation: 提供了系统，过程和计算机程序产品，用于对分层深度图进行采样。 用于对层次深度图进行采样的方法包括以下步骤：基于样本像素和目标像素之间的差异，生成分层深度图并从层次深度图的目标水平读取与样本像素相关联的值。 层次深度图包括至少两个层次。
-
公开(公告)号：US11775829B2
公开(公告)日：2023-10-03
申请号：US18079772
申请日：2022-12-12
Applicant: NVIDIA Corporation
Inventor： Tero Tapani Karras , Samuli Matias Laine , David Patrick Luebke , Jaakko T. Lehtinen , Miika Samuli Aittala , Timo Oskari Aila , Ming-Yu Liu , Arun Mohanray Mallya , Ting-Chun Wang
CPC classification number: G06N3/08 , G06T5/003 , G06T7/73 , G06T9/002 , G06V40/168 , H04N7/157 , H04N19/20 , G06T2207/20081 , G06T2207/20084 , G06T2207/30201
Abstract: A latent code defined in an input space is processed by the mapping neural network to produce an intermediate latent code defined in an intermediate latent space. The intermediate latent code may be used as appearance vector that is processed by the synthesis neural network to generate an image. The appearance vector is a compressed encoding of data, such as video frames including a person's face, audio, and other data. Captured images may be converted into appearance vectors at a local device and transmitted to a remote device using much less bandwidth compared with transmitting the captured images. A synthesis neural network at the remote device reconstructs the images for display.
-
公开(公告)号：US20210150187A1
公开(公告)日：2021-05-20
申请号：US17143516
申请日：2021-01-07
Applicant: NVIDIA Corporation
Inventor： Tero Tapani Karras , Samuli Matias Laine , David Patrick Luebke , Jaakko T. Lehtinen , Miika Samuli Aittala , Timo Oskari Aila , Ming-Yu Liu , Arun Mohanray Mallya , Ting-Chun Wang
Abstract: A latent code defined in an input space is processed by the mapping neural network to produce an intermediate latent code defined in an intermediate latent space. The intermediate latent code may be used as appearance vector that is processed by the synthesis neural network to generate an image. The appearance vector is a compressed encoding of data, such as video frames including a person's face, audio, and other data. Captured images may be converted into appearance vectors at a local device and transmitted to a remote device using much less bandwidth compared with transmitting the captured images. A synthesis neural network at the remote device reconstructs the images for display.
-
公开(公告)号：US10438400B2
公开(公告)日：2019-10-08
申请号：US15453822
申请日：2017-03-08
Applicant: NVIDIA Corporation
Inventor： Anjul Patney , Marco Salvi , Joohwan Kim , Anton S. Kaplanyan , Christopher Ryan Wyman , Nir Benty , David Patrick Luebke , Aaron Eliot Lefohn
Abstract: A method, computer readable medium, and system are disclosed for rendering images utilizing a foveated rendering algorithm with post-process filtering to enhance a contrast of the foveated image. The method includes the step of receiving a three-dimensional scene, rendering the 3D scene according to a foveated rendering algorithm to generate a foveated image, and filtering the foveated image using a contrast-enhancing filter to generate a filtered foveated image. The foveated rendering algorithm may incorporate aspects of coarse pixel shading, mipmapped texture maps, linear efficient anti-aliased normal maps, exponential variance shadow maps, and specular anti-aliasing techniques. The foveated rendering algorithm may also be combined with temporal anti-aliasing techniques to further reduce artifacts in the foveated image.
-
Patent Agency Ranking
公开(公告)号：US10395624B2
公开(公告)日：2019-08-27
申请号：US15880460
申请日：2018-01-25
Applicant: NVIDIA Corporation
Inventor： Qi Sun , Fu-Chung Huang , Joohwan Kim , David Patrick Luebke
IPC: G06T15/20 , G09G5/391 , H04N13/139 , H04N13/383 , G06T15/00
Abstract: A method, computer readable medium, and system are disclosed for adjusting an angular sampling rate during rendering. The method includes the steps of determining a location of a gaze within a displayed scene, and adjusting, during a rendering of the scene, an angular sampling rate used to render at least a portion of the scene, based on the location of the gaze within the displayed scene.
-
17.发明授权公开(公告)号：US10008034B2
公开(公告)日：2018-06-26
申请号：US14058132
申请日：2013-10-18
Applicant: NVIDIA Corporation
Inventor： Morgan McGuire , Cyril Jean-Francois Crassin , David Patrick Luebke , Michael Thomas Mara , Brent L. Oster , Peter Schuyler Shirley , Peter-Pike J. Sloan , Christopher Ryan Wyman
IPC: G06T15/50 , G06T15/55 , G06T15/00 , A63F13/355
CPC classification number: G06T15/55 , A63F13/355 , G06T15/005
Abstract: A system, method, and computer program product are provided for computing indirect lighting in a cloud network. In operation, one or more scenes for rendering are identified. Further, indirect lighting associated with the one or more scenes is identified. Additionally, computation associated with the indirect lighting is performed in a cloud network utilizing at least one of a voxel-based algorithm, a photon-based algorithm, or an irradiance-map-based algorithm.
-
公开(公告)号：US20180158227A1
公开(公告)日：2018-06-07
申请号：US15367086
申请日：2016-12-01
Applicant: NVIDIA Corporation
Inventor： Alexander V. Reshetov , David Patrick Luebke
Abstract: A method, computer readable medium, and system are disclosed for generating and utilizing infinite resolution texture acceleration data structures. The method for generating an infinite resolution texture acceleration data structure includes the steps of receiving an image; generating an infinite resolution texture acceleration data structure associated with the image that includes a texture map, a curve index map, and a curve data map; and storing the infinite resolution texture acceleration data structure in a memory. The texture map is a two-dimensional array of texels, each texel encoding a color value based on the image. The curve data map encodes parameters for at least one curve segment associated with the image. The curve index map associates each texel in the texture map with zero or more curve segments corresponding with the texel.
-
公开(公告)号：US09841537B2
公开(公告)日：2017-12-12
申请号：US13720809
申请日：2012-12-19
Applicant: NVIDIA Corporation
Inventor： David Patrick Luebke , Douglas Lanman , Thomas F. Fox , Gerrit Slavenburg
IPC: G02B27/14 , G03H1/00 , G03B21/60 , G02B27/10 , G09G5/00 , G03B21/26 , G02F1/1335 , G02B3/00 , G02B27/01
CPC classification number: G02B27/01 , G02B3/0006 , G02B27/017 , G02B27/0172 , G02B2027/011 , G02B2027/0123 , G02B2027/0127 , G02B2027/014 , G02B2027/0187
Abstract: In embodiments of the invention, an apparatus may include a display comprising a plurality of pixels and a computer system coupled with the display and operable to instruct the display to display images. The apparatus may further include a microlens array located adjacent to the display and comprising a plurality of microlenses, wherein the microlens array is operable to produce a light field by altering light emitted by the display to simulate an object that is in focus to an observer while the display and the microlens array are located within a near-eye range of the observer.
-
公开(公告)号：US09557565B2
公开(公告)日：2017-01-31
申请号：US13720842
申请日：2012-12-19
Applicant: NVIDIA Corporation
Inventor： David Patrick Luebke , Douglas Lanman , Thomas F. Fox , Gerrit Slavenburg
CPC classification number: G02B27/017 , G02B2027/0127 , G02B2027/014
Abstract: In embodiments of the invention, an apparatus may include a display comprising a plurality of pixels. The apparatus may further include a computer system coupled with the display and operable to instruct the display to display a deconvolved image corresponding to a target image, wherein when the display displays the deconvolved image while located within a near-eye range of an observer, the target image may be perceived in focus by the observer.
Abstract translation: 在本发明的实施例中，装置可以包括包括多个像素的显示器。 该装置还可以包括与显示器耦合的计算机系统，用于指示显示器显示对应于目标图像的去卷积图像，其中当显示器在位于观察者的近眼范围内的情况下显示解卷积图像时， 目标图像可能被观察者焦点所感知。
-
-
-
-
-
-
-
-
-
Search Results
69
records
(took 0.026 seconds)
