Abstract: Techniques and constructs can determine an albedo map and a shading map from a digital image. The albedo and shading maps can be determined based at least in part on a color-difference threshold. A color shading map can be determined based at least in part on the albedo map, and lighting coefficients determined based on the color shading map. The digital image can be adjusted based at least in part on the lighting coefficients. In some examples, respective shading maps can be produced for individual color channels of the digital image. The color shading map can be produced based at least in part on the shading maps. In some examples, a plurality of regions of the digital image can be determined, as can proximity relationships between individual regions. The albedo shading maps can be determined based at least in part on the proximity relationships.

Abstract: Disclosed in some examples, are methods, systems, and machine readable mediums that correct image color casts by utilizing a fully convolutional network (FCN), where the patches in an input image may differ in influence over the color constancy estimation. This influence is formulated as a confidence weight that reflects the value of a patch for inferring the illumination color. The confidence weights are integrated into a novel pooling layer where they are applied to local patch estimates in determining a global color constancy result.

Abstract: Disclosed in some examples, are methods, systems, and machine readable mediums that correct image color casts by utilizing a fully convolutional network (FCN), where the patches in an input image may differ in influence over the color constancy estimation. This influence is formulated as a confidence weight that reflects the value of a patch for inferring the illumination color. The confidence weights are integrated into a novel pooling layer where they are applied to local patch estimates in determining a global color constancy result.

Abstract: Techniques and constructs can determine an albedo map and a shading map from a digital image. The albedo and shading maps can be determined based at least in part on a color-difference threshold. A color shading map can be determined based at least in part on the albedo map, and lighting coefficients determined based on the color shading map. The digital image can be adjusted based at least in part on the lighting coefficients. In some examples, respective shading maps can be produced for individual color channels of the digital image. The color shading map can be produced based at least in part on the shading maps. In some examples, a plurality of regions of the digital image can be determined, as can proximity relationships between individual regions. The albedo shading maps can be determined based at least in part on the proximity relationships.

Abstract: The use of a hybrid camera tool may capture high resolution multispectral images without sacrificing resolution in exchange for spectral accuracy. The capture of a high resolution multispectral image may include forming a high spatial resolution image based on a portion of incoming light and generating a high spectral resolution image that includes multispectral samples based on another portion of the incoming light. The high resolution multispectral image is then synthesized by consolidating the high spatial resolution image with the high spectral resolution image.

Abstract: Some implementations disclosed herein provide techniques and arrangements to render global light transport in real-time or near real-time. For example, in a pre-computation stage, a first computing device may render points of surfaces (e.g., using multiple light bounces and the like). Attributes for each of the points may be determined. A plurality of machine learning algorithms may be trained using particular attributes from the attributes. For example, a first machine learning algorithm may be trained using a first portion of the attributes and a second machine learning algorithm may be trained using a second portion of the attributes. The trained machine learning algorithms may be used by a second computing device to render components (e.g., diffuse and specular components) of indirect shading in real-time.

Abstract: The use of a hybrid camera tool may capture high resolution multispectral images without sacrificing resolution in exchange for spectral accuracy. The capture of a high resolution multispectral image may include forming a high spatial resolution image based on a portion of incoming light and generating a high spectral resolution image that includes multispectral samples based on another portion of the incoming light. The high resolution multispectral image is then synthesized by consolidating the high spatial resolution image with the high spectral resolution image.

Abstract: The use of a hybrid camera tool may capture high resolution multispectral images without sacrificing resolution in exchange for spectral accuracy. The capture of a high resolution multispectral image may include forming a high spatial resolution image based on a portion of incoming light and generating a high spectral resolution image that includes multispectral samples based on another portion of the incoming light. The high resolution multispectral image is then synthesized by consolidating the high spatial resolution image with the high spectral resolution image.

Abstract: Some implementations disclosed herein provide techniques and arrangements to render global light transport in real-time or near real-time. For example, in a pre-computation stage, a first computing device may render points of surfaces (e.g., using multiple light bounces and the like). Attributes for each of the points may be determined. A plurality of machine learning algorithms may be trained using particular attributes from the attributes. For example, a first machine learning algorithm may be trained using a first portion of the attributes and a second machine learning algorithm may be trained using a second portion of the attributes. The trained machine learning algorithms may be used by a second computing device to render components (e.g., diffuse and specular components) of indirect shading in real-time.

Abstract: Some implementations disclosed herein provide techniques and arrangements to render global light transport in real-time or near real-time. For example, in a pre-computation stage, a first computing device may render points of surfaces (e.g., using multiple light bounces and the like). Attributes for each of the points may be determined. A plurality of machine learning algorithms may be trained using particular attributes from the attributes. For example, a first machine learning algorithm may be trained using a first portion of the attributes and a second machine learning algorithm may be trained using a second portion of the attributes. The trained machine learning algorithms may be used by a second computing device to render components (e.g., diffuse and specular components) of indirect shading in real-time.

Abstract: A light gathering process may reduce the computational resources and storage required to render a scene with a participating homogeneous media. According to some implementations, Efficiency may be obtained by evaluating the final radiance along a viewing ray directly from the lighting rays passing near to it, and by rapidly identifying such lighting rays in the scene. To facilitate a search for nearby lighting rays, the lighting rays and viewing rays may be represented as a 6D point and a plane according to the corresponding Plucker coordinates and coefficients, respectively.

Abstract: An exemplary method includes providing image data for an illuminated physical sample of a heterogeneous translucent material, determining one or more material properties of the material based in part on a diffusion equation where one of the material properties is a diffusion coefficient for diffusion of radiation in the material and where the determining includes a regularization term for the diffusion coefficient, mapping the one or more material properties to a virtual object volume, assigning virtual illumination conditions to the virtual object volume, and rendering the virtual object volume using the virtual illumination conditions as a boundary condition for a system of diffusion equations of the virtual object volume. Other methods, devices and systems are also disclosed.

Abstract: The use of a hybrid camera tool may capture high resolution multispectral images without sacrificing resolution in exchange for spectral accuracy. The capture of a high resolution multispectral image may include forming a high spatial resolution image based on a portion of incoming light and generating a high spectral resolution image that includes multispectral samples based on another portion of the incoming light. The high resolution multispectral image is then synthesized by consolidating the high spatial resolution image with the high spectral resolution image.

Abstract: Some implementations disclosed herein provide techniques and arrangements to render global light transport in real-time or near real-time. For example, in a pre-computation stage, a first computing device may render points of surfaces (e.g., using multiple light bounces and the like). Attributes for each of the points may be determined. A plurality of machine learning algorithms may be trained using particular attributes from the attributes. For example, a first machine learning algorithm may be trained using a first portion of the attributes and a second machine learning algorithm may be trained using a second portion of the attributes. The trained machine learning algorithms may be used by a second computing device to render components (e.g., diffuse and specular components) of indirect shading in real-time.

Abstract: An exemplary method includes providing image data for an illuminated physical sample of a heterogeneous translucent material, determining one or more material properties of the material based in part on a diffusion equation where one of the material properties is a diffusion coefficient for diffusion of radiation in the material and where the determining includes a regularization term for the diffusion coefficient, mapping the one or more material properties to a virtual object volume, assigning virtual illumination conditions to the virtual object volume, and rendering the virtual object volume using the virtual illumination conditions as a boundary condition for a system of diffusion equations of the virtual object volume. Other methods, devices and systems are also disclosed.

Abstract: A light gathering process may reduce the computational resources and storage required to render a scene with a participating homogeneous media. According to some implementations, Efficiency may be obtained by evaluating the final radiance along a viewing ray directly from the lighting rays passing near to it, and by rapidly identifying such lighting rays in the scene. To facilitate a search for nearby lighting rays, the lighting rays and viewing rays may be represented as a 6D point and a plane according to the corresponding Plucker coordinates and coefficients, respectively.

Abstract: An exemplary method includes providing image data for an illuminated physical sample of a heterogeneous translucent material, determining one or more material properties of the material based in part on a diffusion equation where one of the material properties is a diffusion coefficient for diffusion of radiation in the material and where the determining includes a regularization term for the diffusion coefficient, mapping the one or more material properties to a virtual object volume, assigning virtual illumination conditions to the virtual object volume, and rendering the virtual object volume using the virtual illumination conditions as a boundary condition for a system of diffusion equations of the virtual object volume. Other methods, devices and systems are also disclosed.

Abstract: Radiometric calibration of an image capture device (e.g., a digital camera) using a single image is described. The single image may be a color image or a grayscale image. The calibration identifies and analyzes edge pixels of the image that correspond to an edge between two colors or grayscale levels of a scene. Intensity distributions of intensities measured from the single image are then analyzed. An inverse response function for the image capture device is determined based on the intensity distributions. For a color image, the radiometric calibration involves calculating an inverse response function that maps measured blended colors of edge pixels and the associated measured component colors into linear distributions. For a grayscale image, the radiometric calibration involves deriving an inverse response function that maps non-uniform histograms of measured intensities into uniform distributions of calibrated intensities.

Abstract: Interactive relighting with dynamic reflectance involves relighting a graphical scene with dynamic changes to the reflectance(s) in the graphical scene. A graphical scene may include source radiance, regions having reflectances, a surface spot, incident radiation from the source radiance at the surface sport, an incident direction, a viewing direction, exit radiance, and so forth. In an example embodiment, a graphical scene is relighted based on at least one adjusted reflectance of the graphical scene using an incident radiance at a surface spot that is separated into respective incident radiance components corresponding to different respective numbers of interreflections in the graphical scene. In another example embodiment, a graphical scene is relighted based on at least one adjusted reflectance of the graphical scene using a tensor representation for a reflectance of a surface spot with the tensor representation being segmented into three adjustable factors for lighting, viewing, and reflectance.

Abstract: The present surface detail rendering technique provides an efficient technique for applying a mesostructure to a macrostructure for an object that minimizes the amount of memory required for pre-computed data. A leap texture is pre-computed for a mesostructure by classifying each voxel in the mesostructure geometry and assigning a value in the leap texture based upon the classification. The value in the leap texture represents a distance to jump along a ray cast in any view direction when a model is decorated with the mesostructure geometry.