-
公开(公告)号:US11935177B2
公开(公告)日:2024-03-19
申请号:US17632492
申请日:2021-06-15
申请人: NVIDIA Corporation
发明人: Yaobin Ouyang , Nan Lin , Jacopo Pantaleoni , Markus Kettunen , Shiqiu Liu
CPC分类号: G06T15/06 , G06T15/506
摘要: Disclosed are apparatuses, systems, and techniques to render images with global illumination using efficient ray tracing, light source identification, and reservoir resampling that deploys temporal and spatial reservoirs.
-
公开(公告)号:US20220222778A1
公开(公告)日:2022-07-14
申请号:US17710643
申请日:2022-03-31
申请人: NVIDIA Corporation
发明人: Shiqiu Liu , Robert Thomas Pottorff , Guilin Liu , Karan Sapra , Jon Barker , David Tarjan , Pekka Janis , Edvard Olav Valter Fagerholm , Lei Yang , Kevin Jonathan Shih , Marco Salvi , Timo Roman , Andrew Tao , Bryan Christopher Catanzaro
摘要: Apparatuses, systems, and techniques are presented to generate images. In at least one embodiment, one or more neural networks are used to generate one or more images using one or more pixel weights determined based, at least in part, on one or more sub-pixel offset values.
-
公开(公告)号:US20220092736A1
公开(公告)日:2022-03-24
申请号:US17543075
申请日:2021-12-06
申请人: Nvidia Corporation
发明人: Shiqiu Liu , Matthieu Le , Andrew Tao
摘要: Apparatuses, systems, and techniques to enhance video are disclosed. In at least one embodiment, one or more neural networks are used to create a higher resolution video using upsampled frames from a lower resolution video.
-
公开(公告)号:US20210073944A1
公开(公告)日:2021-03-11
申请号:US16565088
申请日:2019-09-09
申请人: Nvidia Corporation
发明人: Shiqiu Liu , Matthieu Le , Andrew Tao
摘要: Apparatuses, systems, and techniques to enhance video are disclosed. In at least one embodiment, one or more neural networks are used to create a higher resolution video using upsampled frames from a lower resolution video.
-
公开(公告)号:US20200349755A1
公开(公告)日:2020-11-05
申请号:US16935431
申请日:2020-07-22
申请人: NVIDIA Corporation
摘要: Disclosed approaches may leverage the actual spatial and reflective properties of a virtual environment—such as the size, shape, and orientation of a bidirectional reflectance distribution function (BRDF) lobe of a light path and its position relative to a reflection surface, a virtual screen, and a virtual camera—to produce, for a pixel, an anisotropic kernel filter having dimensions and weights that accurately reflect the spatial characteristics of the virtual environment as well as the reflective properties of the surface. In order to accomplish this, geometry may be computed that corresponds to a projection of a reflection of the BRDF lobe below the surface along a view vector to the pixel. Using this approach, the dimensions of the anisotropic filter kernel may correspond to the BRDF lobe to accurately reflect the spatial characteristics of the virtual environment as well as the reflective properties of the surface.
-
公开(公告)号:US20200334891A1
公开(公告)日:2020-10-22
申请号:US16920971
申请日:2020-07-06
申请人: NVIDIA Corporation
发明人: Shiqiu Liu
摘要: In various examples, the actual spatial properties of a virtual environment are used to produce, for a pixel, an anisotropic filter kernel for a filter having dimensions and weights that accurately reflect the spatial characteristics of the virtual environment. Geometry of the virtual environment may be computed based at least in part on a projection of a light source onto a surface through an occluder, in order to determine a footprint that reflects a contribution of the light source to lighting conditions of the pixel associated with a point on the surface. The footprint may define a size, orientation, and/or shape of the anisotropic filter kernel and corresponding filter weights. The anisotropic filter kernel may be applied to the pixel to produce a graphically-rendered image of the virtual environment.
-
公开(公告)号:US12039694B2
公开(公告)日:2024-07-16
申请号:US17543075
申请日:2021-12-06
申请人: Nvidia Corporation
发明人: Shiqiu Liu , Matthieu Le , Andrew Tao
IPC分类号: G06F7/57 , A63F13/50 , G06N3/08 , G06T3/4046 , G06T3/4092 , G06T5/70
CPC分类号: G06T3/4046 , A63F13/50 , G06F7/57 , G06N3/08 , G06T3/4092 , G06T5/70 , G06T2207/10016 , G06T2207/10024 , G06T2207/20081 , G06T2207/20084
摘要: Apparatuses, systems, and techniques to enhance video are disclosed. In at least one embodiment, one or more neural networks are used to create a higher resolution video using upsampled frames from a lower resolution video.
-
公开(公告)号:US20230289924A1
公开(公告)日:2023-09-14
申请号:US18317766
申请日:2023-05-15
申请人: NVIDIA Corporation
发明人: Shiqiu Liu , Jacopo Pantaleoni
摘要: Various approaches are disclosed to temporally and spatially filter noisy image data—generated using one or more ray-tracing effects—in a graphically rendered image. Rather than fully sampling data values using spatial filters, the data values may be sparsely sampled using filter taps within the spatial filters. To account for the sparse sampling, locations of filter taps may be jittered spatially and/or temporally. For filtering efficiency, a size of a spatial filter may be reduced when historical data values are used to temporally filter pixels. Further, data values filtered using a temporal filter may be clamped to avoid ghosting. For further filtering efficiency, a spatial filter may be applied as a separable filter in which the filtering for a filter direction may be performed over multiple iterations using reducing filter widths, decreasing the chance of visual artifacts when the spatial filter does not follow a true Gaussian distribution.
-
公开(公告)号:US20230186428A1
公开(公告)日:2023-06-15
申请号:US18106348
申请日:2023-02-06
申请人: NVIDIA Corporation
发明人: Guilin Liu , Andrew Tao , Bryan Christopher Catanzaro , Ting-Chun Wang , Zhiding Yu , Shiqiu Liu , Fitsum Reda , Karan Sapra , Brandon Rowlett
CPC分类号: G06T3/4038 , G06T3/4046 , G06T7/40 , G06N3/08 , G06V10/776 , G06V10/82 , G06V10/454 , G06V10/54 , G06T2207/20081 , G06T2207/20084
摘要: Apparatuses, systems, and techniques for texture synthesis from small input textures in images using convolutional neural networks. In at least one embodiment, one or more convolutional layers are used in conjunction with one or more transposed convolution operations to generate a large textured output image from a small input textured image while preserving global features and texture, according to various novel techniques described herein.
-
公开(公告)号:US11367240B2
公开(公告)日:2022-06-21
申请号:US16920971
申请日:2020-07-06
申请人: NVIDIA Corporation
发明人: Shiqiu Liu
摘要: In various examples, the actual spatial properties of a virtual environment are used to produce, for a pixel, an anisotropic filter kernel for a filter having dimensions and weights that accurately reflect the spatial characteristics of the virtual environment. Geometry of the virtual environment may be computed based at least in part on a projection of a light source onto a surface through an occluder, in order to determine a footprint that reflects a contribution of the light source to lighting conditions of the pixel associated with a point on the surface. The footprint may define a size, orientation, and/or shape of the anisotropic filter kernel and corresponding filter weights. The anisotropic filter kernel may be applied to the pixel to produce a graphically-rendered image of the virtual environment.
-
-
-
-
-
-
-
-
-