Abstract: Neural representations may be used for multi-view reconstruction of scenes. A plurality of color images representing a scene from a plurality of camera poses may be received. For each point of a plurality of points along a ray, a signed distance and a color value may be determined as a function of a feature volume, a first neural network, and a second neural network. A predicted output color may be determined as a function of the density. At least one of the first neural network, the second neural network, the feature volume, or the transformation parameter may be adjusted based on the predicted output color and a corresponding target color obtained based on one of the color images. A three-dimensional representation of the scene may be displayed based on at least one of the first neural network, the second neural network, the feature volume, or the transformation parameter.

Abstract: A multifocal test system is described herein. The system includes a plurality of displays located at different focal distances. Each display includes a plurality of pixels with pixel intensity values. The system includes an eye tracking system that determines eye tracking information about a position of an eye relative to the displays. A controller is configured to determine pixel intensity values based on decomposition of a scene across the plurality of displays, and the position of the eye.

Abstract: Systems and methods for displaying an image across a plurality of displays are described herein. Pixel intensity values in the multifocal display are determined using correlation values and numerical iterations. An eye tracking system measures eye tracking information about a position of a user's eye, and the pixel intensity values are modified based on the eye tracking information. An image is displayed on the plurality of displays based on the determined pixel intensity values. The plurality of displays may be within an HMD, and address vergence accommodation conflict by simulating retinal defocus blur.

Abstract: According to one embodiment, a method includes identifying a scene to be rendered, creating a plurality of light scattering tables within the scene, performing a computation of light extinction and light in-scattering within participating media of the scene, utilizing the plurality of light scattering tables, and during a ray tracing of the scene, approximating spatially heterogeneous media of the scene as spatially homogeneous media of the scene by performing a volume intersection for each light ray associated with the spatially heterogeneous media of the scene to determine a homogeneous scattering coefficient for the light ray, and applying to the spatially heterogeneous media of the scene one of the plurality of light scattering tables, where each of the plurality of light scattering tables corresponds to a single homogeneous scattering coefficient.

Abstract: According to one embodiment, a method includes identifying a scene to be rendered, creating a plurality of light scattering tables within the scene, performing a computation of light extinction and light in-scattering within participating media of the scene, utilizing the plurality of light scattering tables, and during a ray tracing of the scene, determining a homogeneous scattering coefficient for spatially homogeneous media of the scene, and applying to the spatially homogeneous media of the scene one of the plurality of light scattering tables, where each of the plurality of light scattering tables corresponds to a single homogeneous scattering coefficient.

Abstract: Systems and methods for displaying an image across a plurality of displays are described herein. Pixel intensity values in the multifocal display are determined using correlation values and numerical iterations. An eye tracking system measures eye tracking information about a position of a user's eye, and the pixel intensity values are modified based on the eye tracking information. An image is displayed on the plurality of displays based on the determined pixel intensity values. The plurality of displays may be within an HMD, and address vergence accommodation conflict by simulating retinal defocus blur.

Abstract: Systems and methods for displaying an image across a plurality of displays are described herein. Pixel intensity values in the multifocal display are determined using correlation values and numerical iterations. An eye tracking system measures eye tracking information about a position of a user's eye, and the pixel intensity values are modified based on the eye tracking information. An image is displayed on the plurality of displays based on the determined pixel intensity values. The plurality of displays may be within an HMD, and address vergence accommodation conflict by simulating retinal defocus blur.

Abstract: According to one embodiment, a method includes identifying a scene to be rendered, creating a plurality of light scattering tables within the scene, performing a computation of light extinction and light in-scattering within participating media of the scene, utilizing the plurality of light scattering tables, and during a ray tracing of the scene, approximating spatially heterogeneous media of the scene as spatially homogeneous media of the scene by performing a volume intersection for each light ray associated with the spatially heterogeneous media of the scene to determine a homogeneous scattering coefficient for the light ray, and applying to the spatially heterogeneous media of the scene one of the plurality of light scattering tables, where each of the plurality of light scattering tables corresponds to a single homogeneous scattering coefficient.

Abstract: According to one embodiment, a method includes identifying a scene to be rendered, pre-computing one or more lighting elements within the scene, including creating a plurality of light scattering tables, performing, during the pre-computing, a computation of light extinction and light in-scattering within participating media of the scene, utilizing the plurality of light scattering tables, and during a ray tracing of the scene, approximating spatially heterogeneous media of the scene as spatially homogeneous media of the scene by performing a volume intersection for each light ray associated with the spatially heterogeneous media of the scene to determine a homogeneous scattering coefficient for the light ray, and applying to the spatially heterogeneous media of the scene one of the plurality of light scattering tables, where each of the plurality of light scattering tables corresponds to a single homogeneous scattering coefficient, and a table lookup is adjusted for the one of the plurality of light scatteri

Abstract: Systems and methods for displaying an image across a plurality of displays are described herein. Pixel intensity values in the multifocal display are determined using correlation values and numerical iterations. An eye tracking system measures eye tracking information about a position of a user's eye, and the pixel intensity values are modified based on the eye tracking information. An image is displayed on the plurality of displays based on the determined pixel intensity values. The plurality of displays may be within an HMD, and address vergence accommodation conflict by simulating retinal defocus blur.

Abstract: According to one embodiment, a method includes identifying a scene to be rendered, creating a plurality of light scattering tables within the scene, performing a computation of light extinction and light in-scattering within participating media of the scene, utilizing the plurality of light scattering tables, and during a ray tracing of the scene, determining a homogeneous scattering coefficient for spatially homogeneous media of the scene, and applying to the spatially homogeneous media of the scene one of the plurality of light scattering tables, where each of the plurality of light scattering tables corresponds to a single homogeneous scattering coefficient.

Abstract: A multifocal test system is described herein. The system includes a plurality of displays located at different focal distances. Each display includes a plurality of pixels with pixel intensity values. The system includes an eye tracking system that determines eye tracking information about a position of an eye relative to the displays. A controller is configured to determine pixel intensity values based on decomposition of a scene across the plurality of displays, and the position of the eye.

Abstract: A plurality of measured sample data points associated with reflectance on a surface of a material is obtained. A non-parametric densely tabulated one-dimensional representation for a plurality of factors in a microfacet model is generated, using the obtained sample data points.

Abstract: According to one embodiment, a method includes identifying a scene to be rendered, pre-computing one or more lighting elements within the scene, including creating a plurality of light scattering tables, performing, during the pre-computing, a computation of light extinction and light in-scattering within participating media of the scene, utilizing the plurality of light scattering tables, and during a ray tracing of the scene, determining a homogeneous scattering coefficient for spatially homogeneous media of the scene, and applying to the spatially homogeneous media of the scene one of the plurality of light scattering tables, where each of the plurality of light scattering tables corresponds to a single homogeneous scattering coefficient, and a table lookup is adjusted for the one of the plurality of light scattering tables utilizing an analytic correction factor in order to apply the one of the plurality of light scattering tables with a different homogeneous scattering coefficient.

Abstract: According to one embodiment, a method includes identifying a scene to be rendered, pre-computing one or more lighting elements within the scene, including creating a plurality of light scattering tables, performing, during the pre-computing, a computation of light extinction and light in-scattering within participating media of the scene, utilizing the plurality of light scattering tables, and during a ray tracing of the scene, determining a homogeneous scattering coefficient for spatially homogeneous media of the scene, and applying to the spatially homogeneous media of the scene one of the plurality of light scattering tables, where each of the plurality of light scattering tables corresponds to a single homogeneous scattering coefficient, and a table lookup is adjusted for the one of the plurality of light scattering tables utilizing an analytic correction factor in order to apply the one of the plurality of light scattering tables with a different homogeneous scattering coefficient.

Abstract: According to one embodiment, a method includes identifying a scene to be rendered, pre-computing one or more lighting elements within the scene, including creating a plurality of light scattering tables, performing, during the pre-computing, a computation of light extinction and light in-scattering within participating media of the scene, utilizing the plurality of light scattering tables, and during a ray tracing of the scene, approximating spatially heterogeneous media of the scene as spatially homogeneous media of the scene by performing a volume intersection for each light ray associated with the spatially heterogeneous media of the scene to determine a homogeneous scattering coefficient for the light ray, and applying to the spatially heterogeneous media of the scene one of the plurality of light scattering tables, where each of the plurality of light scattering tables corresponds to a single homogeneous scattering coefficient, and a table lookup is adjusted for the one of the plurality of light scatteri

Abstract: Systems, methods and articles of manufacture for sampling visual characteristics of a three-dimensional scene. Embodiments include collecting a plurality of samples within the three-dimensional scene. Upon determining that a combined stratified importance sampling algorithm will result in reduced error for a rendered image of the three-dimensional scene, embodiments collect the plurality of samples using the combined stratified importance sampling algorithm, and otherwise the plurality of samples are collected using a stratified sampling algorithm. The combined stratified importance sampling algorithm integrates an antithetic sampling algorithm. One or more lighting effects for the three-dimensional scene are simulated based on the plurality of samples and data describing one or more light sources for the three-dimensional scene. Embodiments further include rendering the image based on the simulated one or more lighting effects and data describing characteristics of the three-dimensional scene.

Abstract: Methods and systems of joint path importance sampling are provided to construct light paths in participating media. The product of anisotropic phase functions and geometric terms across a sequence of path vertices are considered. A connection subpath is determined to join a light source subpath with a light receiver subpath with multiple intermediate vertices while considering the product of phase functions and geometry terms. A joint probability density function (“PDF”) may be factorized unidirectional or bidirectional. The joint PDF may be factorized into a product of multiple conditional PDFs, each of which corresponds to a sampling routine. Analytic importance sampling may be performed for isotropic scattering, whereas tabulated importance sampling may be performed for anisotropic scattering.

Abstract: The disclosure provides an approach for determining, in 3D rendering, the integrals of visibility-masked spherical functions using visibility silhouettes. For a given shade point, the visibility silhouette for that shade point includes a set of edges from the scene geometry which form the boundaries between visible and invisible regions of a hemisphere having the shade point as its center. For each shade point, a rendering application determines a set of contour edges of scene geometry, the contour edges being a superset of the set of visibility silhouette edges, by querying a 4D dual mesh. The rendering application then evaluates the integral of the visibility-masked spherical function for a given shade point by integrating over segments of discrete u-isolines for which an overlap function indicates that a ray from the shade point would not intersect scene geometry.

Abstract: Systems, methods and articles of manufacture for sampling visual characteristics of a three-dimensional scene. Embodiments include collecting a plurality of samples within the three-dimensional scene. Upon determining that a combined stratified importance sampling algorithm will result in reduced error for a rendered image of the three-dimensional scene, embodiments collect the plurality of samples using the combined stratified importance sampling algorithm, and otherwise the plurality of samples are collected using a stratified sampling algorithm. The combined stratified importance sampling algorithm integrates an antithetic sampling algorithm. One or more lighting effects for the three-dimensional scene are simulated based on the plurality of samples and data describing one or more light sources for the three-dimensional scene. Embodiments further include rendering the image based on the simulated one or more lighting effects and data describing characteristics of the three-dimensional scene.