公开(公告)号：US10600167B2

公开(公告)日：2020-03-24

申请号：US15874611

申请日：2018-01-18

Applicant: NVIDIA Corporation

Inventor： Christoph H. Schied ,  Marco Salvi ,  Anton S. Kaplanyan ,  Aaron Eliot Lefohn ,  John Matthew Burgess ,  Anjul Patney ,  Christopher Ryan Wyman

IPC: G06T5/20 ,  G06T11/60 ,  G06K9/66 ,  G06K9/62 ,  G06K9/00 ,  G06T1/20 ,  G06T5/00

Abstract: A method, computer readable medium, and system are disclosed for performing spatiotemporal filtering. The method includes the steps of applying, utilizing a processor, a temporal filter of a filtering pipeline to a current image frame, using a temporal reprojection, to obtain a color and auxiliary information for each pixel within the current image frame, providing the auxiliary information for each pixel within the current image frame to one or more subsequent filters of the filtering pipeline, and creating a reconstructed image for the current image frame, utilizing the one or more subsequent filters of the filtering pipeline.

公开(公告)号：US10116916B2

公开(公告)日：2018-10-30

申请号：US15452651

申请日：2017-03-07

Applicant: NVIDIA Corporation

Inventor： Marco Salvi ,  Anjul Patney ,  Aaron Eliot Lefohn

IPC: G06T1/60 ,  G06T11/00 ,  H04N13/122 ,  H04N13/15 ,  G06T11/40 ,  H04N13/106 ,  H04N13/00

Abstract: A method, computer readable medium, and system are disclosed for image processing to reduce aliasing using a temporal anti-aliasing algorithm modified to implement variance clipping. The method includes the step of generating a current frame of image data in a memory. Then, each pixel in the current frame of image data is processed by: sampling a resolved pixel color for a corresponding pixel in a previous frame of image data stored in the memory, adjusting the resolved pixel color based on a statistical distribution of color values for a plurality of samples in the neighborhood of the pixel in the current frame of image data to generate an adjusted pixel color, and blending a color value for the pixel in the current frame of image data with the adjusted pixel color to generate a resolved pixel color for the pixel in the current frame of image data.

公开(公告)号：US20170272722A1

公开(公告)日：2017-09-21

申请号：US15452651

申请日：2017-03-07

Applicant: NVIDIA Corporation

Inventor： Marco Salvi ,  Anjul Patney ,  Aaron Eliot Lefohn

IPC: H04N13/00 ,  G06T1/60 ,  G06T11/00

CPC classification number: H04N13/122 ,  G06T1/60 ,  G06T11/40 ,  H04N13/106 ,  H04N13/15 ,  H04N2013/0081

Abstract: A method, computer readable medium, and system are disclosed for image processing to reduce aliasing using a temporal anti-aliasing algorithm modified to implement variance clipping. The method includes the step of generating a current frame of image data in a memory. Then, each pixel in the current frame of image data is processed by: sampling a resolved pixel color for a corresponding pixel in a previous frame of image data stored in the memory, adjusting the resolved pixel color based on a statistical distribution of color values for a plurality of samples in the neighborhood of the pixel in the current frame of image data to generate an adjusted pixel color, and blending a color value for the pixel in the current frame of image data with the adjusted pixel color to generate a resolved pixel color for the pixel in the current frame of image data.

公开(公告)号：US20160049000A1

公开(公告)日：2016-02-18

申请号：US14645340

申请日：2015-03-11

Applicant: NVIDIA Corporation

Inventor： Anjul Patney ,  Eric B. Enderton ,  Eric B. Lum ,  Marco Salvi ,  Christopher Ryan Wyman ,  Yubo Zhang ,  Yong He ,  G. Evan Hart, JR. ,  Kayvon Fatahalian ,  Yury Uralsky ,  Henry Packard Moreton ,  Aaron Eliot Lefohn

IPC: G06T15/80 ,  G06T1/20

CPC classification number: G06T15/80 ,  G06T1/20 ,  G06T15/005 ,  G06T17/205 ,  G06T2210/36

Abstract: A system, method, and computer program product are provided for performing object-space shading. A primitive defined by vertices in three-dimensional (3D) space that is specific to an object defined by at least the primitive is received and a shading sample rate is computed for the primitive based on a screen-space derivative of coordinates of a pixel fragment transformed into the 3D space. A shader program is executed by a processing pipeline to compute shaded attributes for the primitive according to the computed shading sample rate.

Abstract translation: 提供了一种用于执行对象空间阴影的系统，方法和计算机程序产品。 接收由三维（3D）空间中的至少由原语定义的对象特定的顶点定义的原语，并且基于像素片段的坐标的屏幕空间导数来计算底纹采样率 转化为3D空间。 着色器程序由处理流水线执行，以根据计算的阴影采样率计算原始图像的阴影属性。

公开(公告)号：US20160048999A1

公开(公告)日：2016-02-18

申请号：US14645327

申请日：2015-03-11

Applicant: NVIDIA Corporation

Inventor： Anjul Patney ,  Eric B. Enderton ,  Eric B. Lum ,  Marco Salvi ,  Christopher Ryan Wyman ,  Yubo Zhang ,  Yong He ,  G. Evan Hart, JR. ,  Kayvon Fatahalian ,  Yury Uralsky ,  Henry Packard Moreton ,  Aaron Eliot Lefohn

IPC: G06T15/80 ,  G06T17/20 ,  G06T17/10

CPC classification number: G06T15/80 ,  G06T17/10 ,  G06T17/20 ,  G06T17/205 ,  G06T2200/04 ,  G06T2210/36

Abstract: A system, method, and computer program product are provided fir shading using a dynamic object-space grid. An object defined by triangle primitives in a three-dimensional (3D) space that is specific to the object is received and an object-space shading grid is defined for a first triangle primitive of the triangle primitives based on coordinates of the first triangle primitive in the 3D space. A shader program is executed by a processing pipeline to compute a shaded value at a point on the object-space shading grid for the first triangle primitive.

Abstract translation: 使用动态对象空间网格提供系统，方法和计算机程序产品。 接收由特定于对象的三维（3D）空间中的三角形基元定义的对象，并且基于第一个三角形基元的坐标，为三角形基元的第一个三角形基元定义对象空间阴影网格 3D空间。 着色器程序由处理流程执行，以计算第一个三角形原语的对象空间阴影网格上的一个点处的阴影值。

公开(公告)号：US11861811B2

公开(公告)日：2024-01-02

申请号：US17930668

申请日：2022-09-08

Applicant: NVIDIA Corporation

Inventor： Carl Jacob Munkberg ,  Jon Niklas Theodor Hasselgren ,  Anjul Patney ,  Marco Salvi ,  Aaron Eliot Lefohn ,  Donald Lee Brittain

IPC: G06T5/00 ,  G06T7/246 ,  G06T7/50

CPC classification number: G06T5/002 ,  G06T7/248 ,  G06T7/50 ,  G06T2207/10016 ,  G06T2207/20084

Abstract: A neural network-based rendering technique increases temporal stability and image fidelity of low sample count path tracing by optimizing a distribution of samples for rendering each image in a sequence. A sample predictor neural network learns spatio-temporal sampling strategies such as placing more samples in dis-occluded regions and tracking specular highlights. Temporal feedback enables a denoiser neural network to boost the effective input sample count and increases temporal stability. The initial uniform sampling step typically present in adaptive sampling algorithms is not needed. The sample predictor and denoiser operate at interactive rates to achieve significantly improved image quality and temporal stability compared with conventional adaptive sampling techniques.

公开(公告)号：US20200160590A1

公开(公告)日：2020-05-21

申请号：US16733149

申请日：2020-01-02

Applicant: NVIDIA Corporation

Inventor： Qi Sun ,  Anjul Patney ,  Omer Shapira ,  Morgan McGuire ,  Aaron Eliot Lefohn ,  David Patrick Luebke

IPC: G06T15/20 ,  G06F3/01 ,  G06T19/20 ,  G06T19/00

Abstract: A method, computer readable medium, and system are disclosed for redirecting a user's movement through a physical space while the user views a virtual environment. A temporary visual suppression event is detected when a user's eyes move relative to the user's head while viewing a virtual scene displayed on a display device, an orientation of the virtual scene relative to the user is modified to direct the user to physically move along a planned path through a virtual environment corresponding to the virtual scene, and the virtual scene is displayed on the display device according to the modified orientation.

公开(公告)号：US10573071B2

公开(公告)日：2020-02-25

申请号：US16024609

申请日：2018-06-29

Applicant: NVIDIA Corporation

Inventor： Qi Sun ,  Anjul Patney ,  Omer Shapira ,  Morgan McGuire ,  Aaron Eliot Lefohn ,  David Patrick Luebke

IPC: G06T19/00 ,  G06F3/01 ,  G06T15/00

Abstract: A method, computer readable medium, and system are disclosed for computing a path for a user to move along within a physical space while viewing a virtual environment in a virtual reality system. A path for a user to physically move along through a virtual environment is determined based on waypoints and at least one characteristic of the physical environment within which the user is positioned, position data for the user is received indicating whether and how much a current path taken by the user has deviated from the path, and an updated path is computed through the virtual environment based on the waypoints and the at least one characteristic of the physical environment.

公开(公告)号：US10055883B2

公开(公告)日：2018-08-21

申请号：US14989585

申请日：2016-01-06

Applicant: NVIDIA Corporation

Inventor： Christopher Ryan Wyman ,  Aaron Eliot Lefohn ,  Anjul Patney

IPC: G06T15/60 ,  G06T15/50 ,  G06T15/80

CPC classification number: G06T15/60 ,  G06T15/503 ,  G06T15/506 ,  G06T15/80

Abstract: A method, computer readable medium, and system are disclosed for rendering shadows. A frustum projected from a grid cell corresponding to a light source in light-space is defined and a graphics primitive is determined to intersect the frustum. A light-space visibility buffer is accessed to obtain a set of pixel fragment footprints corresponding to the frustum and it is identified whether each pixel fragment footprint of the pixel fragment footprints is shadowed by the graphics primitive.

公开(公告)号：US20230410375A1

公开(公告)日：2023-12-21

申请号：US18225674

申请日：2023-07-24

Applicant: NVIDIA Corporation

Inventor： Marco Salvi ,  Anjul Patney ,  Aaron Eliot Lefohn ,  Donald Lee Brittain

IPC: G06T9/00 ,  G06N3/084 ,  G06T5/00 ,  G06N3/02 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08 ,  G06T3/00

CPC classification number: G06T9/002 ,  G06N3/084 ,  G06T5/002 ,  G06N3/02 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08 ,  G06T3/0087 ,  G06T2207/20182 ,  G06T2207/20081

Abstract: A method, computer readable medium, and system are disclosed for temporally stable data reconstruction. A sequence of input data including artifacts is received. A first input data frame is processed using layers of a neural network model to produce external state including a reconstructed first data frame that approximates the first input data frame without artifacts. Hidden state generated during processing of the first input data is not provided as an input to the layer to process second input data. The external state is warped, using difference data corresponding to changes between input data frames, to produce warped external state more closely aligned with the second input data frame. The second input data frame is processed, based on the warped external state, using the layers of the neural network model to produce a reconstructed second data frame that approximates the second data frame without artifacts.