-
公开(公告)号：US20230281766A1
公开(公告)日：2023-09-07
申请号：US17684779
申请日：2022-03-02
Applicant: NVIDIA Corporation
Inventor： Shaveen Kumar , Anjul Patney , Eric Xu , Anton Moor
CPC classification number: G06T5/009 , G06N3/08 , G06T5/002 , G06T5/20 , G06T2207/20028 , G06T2207/20208 , G06T2207/20084 , G06T2207/10016 , G06T2200/24
Abstract: The technology disclosed herein involves using a machine learning model (e.g., CNN) to expand lower dynamic-range image content (e.g., SDR images) into higher dynamic-range image content (e.g., HDR images). The machine learning model can take as input the lower dynamic-range image and can output multiple expansion maps that are used to make the expanded image appear more natural. The expansion maps may be used by image operators to smooth color banding and to dim overexposed regions or user interface elements in the expanded image. The expanded content (e.g., HDR image content) may then be provided to one or more devices for display or storage.
-
公开(公告)号：US20200050923A1
公开(公告)日：2020-02-13
申请号：US16397511
申请日：2019-04-29
Applicant: NVIDIA Corporation
Inventor： Anjul Patney , Aaron Eliot Lefohn
Abstract: Motivated by the ability of humans to quickly and accurately detect visual artifacts in images, a neural network model is trained to identify and locate visual artifacts in a sequence of rendered images without comparing the sequence of rendered images against a ground truth reference. Examples of visual artifacts include aliasing, blurriness, mosaicking, and overexposure. The neural network model provides a useful fully-automated tool for evaluating the quality of images produced by rendering systems. The neural network model may be trained to evaluate the quality of images for video processing, encoding, and/or compression techniques. In an embodiment, the sequence includes at least four images corresponding to a video or animation.
-
公开(公告)号：US09747718B2
公开(公告)日：2017-08-29
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
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.
-
公开(公告)号：US12002189B2
公开(公告)日：2024-06-04
申请号：US17684779
申请日：2022-03-02
Applicant: NVIDIA Corporation
Inventor： Shaveen Kumar , Anjul Patney , Eric Xu , Anton Moor
CPC classification number: G06T5/92 , G06N3/08 , G06T5/20 , G06T5/70 , G06T2200/24 , G06T2207/10016 , G06T2207/20028 , G06T2207/20084 , G06T2207/20208
Abstract: The technology disclosed herein involves using a machine learning model (e.g., CNN) to expand lower dynamic-range image content (e.g., SDR images) into higher dynamic-range image content (e.g., HDR images). The machine learning model can take as input the lower dynamic-range image and can output multiple expansion maps that are used to make the expanded image appear more natural. The expansion maps may be used by image operators to smooth color banding and to dim overexposed regions or user interface elements in the expanded image. The expanded content (e.g., HDR image content) may then be provided to one or more devices for display or storage.
-
公开(公告)号：US11557022B2
公开(公告)日：2023-01-17
申请号：US16718607
申请日：2019-12-18
Applicant: NVIDIA Corporation
Inventor： Carl Jacob Munkberg , Jon Niklas Theodor Hasselgren , Anjul Patney , Marco Salvi , Aaron Eliot Lefohn , Donald Lee Brittain
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.
-
Patent Agency Ranking
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.
-
公开(公告)号：US10362289B2
公开(公告)日：2019-07-23
申请号：US16052537
申请日：2018-08-01
Applicant: NVIDIA Corporation
Inventor： Marco Salvi , Anjul Patney , Aaron Eliot Lefohn
IPC: G06T1/60 , G06T11/40 , H04N13/00 , H04N13/15 , H04N13/106 , H04N13/122
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：US20190035113A1
公开(公告)日：2019-01-31
申请号：US16041502
申请日：2018-07-20
Applicant: NVIDIA Corporation
Inventor： Marco Salvi , Anjul Patney , Aaron Eliot Lefohn , Donald Lee Brittain
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.
-
公开(公告)号：US20210287096A1
公开(公告)日：2021-09-16
申请号：US16818266
申请日：2020-03-13
Applicant: NVIDIA Corporation
Inventor： Anjul Patney , Brandon Lee Rowlett , Yinghao Xu , Andrew Leighton Edelsten , Aaron Eliot Lefohn
Abstract: The disclosed microtraining techniques improve accuracy of trained neural networks by performing iterative refinement at low learning rates using a relatively short series microtraining steps. A neural network training framework receives the trained neural network along with a second training dataset and set of hyperparameters. The neural network training framework produces a microtrained neural network by adjusting one or more weights of the trained neural network using a lower learning rate to facilitate incremental accuracy improvements without substantially altering the computational structure of the trained neural network. The microtrained neural network may be assessed for changes in accuracy and/or quality. Additional microtraining sessions may be performed on the microtrained neural network to further improve accuracy or quality.
-
公开(公告)号：US10922876B2
公开(公告)日：2021-02-16
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
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.
-
-
-
-
-
-
-
-
-
Search Results
33
records
(took 0.016 seconds)
