Abstract: Paired images of substantially the same scene are captured with the same freestanding sensor. The paired images include reflected light illuminated with controlled polarization states that are different between the paired images. Information from the images is applied to a convolutional neural network (CNN) configured to derive a spatially varying bi-directional reflectance distribution function (SVBRDF) for objects in the paired images. Alternatively, the sensor is fixed and oriented to capture images of an object of interest in the scene while a light source traverses a path that intersects the sensor's field of view. Information from the paired images of the scene and from the images captured of the object of interest when the light source traverses the field of view are applied to a CNN to derive a SVBDRF for the object of interest. The image information and the SVBRDF are used to render a representation with artificial lighting conditions.

Abstract: Paired images of substantially the same scene are captured with the same freestanding sensor. The paired images include reflected light illuminated with controlled polarization states that are different between the paired images. Information from the images is applied to a convolutional neural network (CNN) configured to derive a spatially varying bi-directional reflectance distribution function (SVBRDF) for objects in the paired images. Alternatively, the sensor is fixed and oriented to capture images of an object of interest in the scene while a light source traverses a path that intersects the sensor's field of view. Information from the paired images of the scene and from the images captured of the object of interest when the light source traverses the field of view are applied to a CNN to derive a SVBDRF for the object of interest. The image information and the SVBRDF are used to render a representation with artificial lighting conditions.

Abstract: Paired images of substantially the same scene are captured with the same freestanding sensor. The paired images include reflected light illuminated with controlled polarization states that are different between the paired images. Information from the images is applied to a convolutional neural network (CNN) configured to derive a spatially varying bi-directional reflectance distribution function (SVBRDF) for objects in the paired images. Alternatively, the sensor is fixed and oriented to capture images of an object of interest in the scene while a light source traverses a path that intersects the sensor's field of view. Information from the paired images of the scene and from the images captured of the object of interest when the light source traverses the field of view are applied to a CNN to derive a SVBDRF for the object of interest. The image information and the SVBRDF are used to render a representation with artificial lighting conditions.

Abstract: Paired images of substantially the same scene are captured with the same freestanding sensor. The paired images include reflected light illuminated with controlled polarization states that are different between the paired images. Information from the images is applied to a convolutional neural network (CNN) configured to derive a spatially varying bi-directional reflectance distribution function (SVBRDF) for objects in the paired images. Alternatively, the sensor is fixed and oriented to capture images of an object of interest in the scene while a light source traverses a path that intersects the sensor's field of view. Information from the paired images of the scene and from the images captured of the object of interest when the light source traverses the field of view are applied to a CNN to derive a SVBDRF for the object of interest. The image information and the SVBRDF are used to render a representation with artificial lighting conditions.

Abstract: An image-capture device includes an enclosure, a lens housing, an illumination source and an image sensor. The illumination source surrounds a perimeter of the lens housing. When the illumination source is energized, light oscillating in a first orientation is directed away from the image-capture device. Reflected light encounters a mechanism supported by the enclosure and arranged to limit reflected light to that which is oscillating in a second orientation substantially orthogonal to the first orientation. The image sensor converts the reflected and orientation limited light into a data asset. The illumination source generates a luminous flux at a power level such that the reflected light oscillating in the second orientation incident at the image sensor exceeds a minimal sensitivity of the image sensor.

Abstract: Paired images of substantially the same scene are captured with the same freestanding sensor. The paired images include reflected light illuminated with controlled polarization states that are different between the separate images. A first pixel value from one of the first image and the second image is subtracted from a corresponding pixel value from a remaining one of the first image and the second image. When repeated over the raster of corresponding pixels, a modified image includes an isolated representation of substantially pure specular color data. The captured images and the modified image are stored and used to generate a model. Substantially shadow-free diffuse color and specular color data are applied to texture maps of the model to generate a virtual environment where a virtual light source can be introduced and controlled to achieve desired results absent adverse effects introduced from fixed ambient light sources used in conventional source photography.

Abstract: An image-capture device includes an enclosure, a lens housing, an illumination source and an image sensor. The illumination source surrounds a perimeter of the lens housing. When the illumination source is energized, light oscillating in a first orientation is directed away from the image-capture device. Reflected light encounters a mechanism supported by the enclosure and arranged to limit reflected light to that which is oscillating in a second orientation substantially orthogonal to the first orientation. The image sensor converts the reflected and orientation limited light into a data asset.

Abstract: An image-capture device includes an enclosure, a lens arranged in a lens housing, an illumination source and an image sensor. The illumination source has separately energized light emitters adjacent to the lens housing. When a first light emitter is energized, light oscillating in a first orientation is directed away from the image-capture device. When a second light emitter is energized, light oscillating in a second orientation different from the first orientation is directed away from the image-capture device. Alternatively, an image-capture device includes image sensors, a lens and an illumination source. The illumination source directs emitted light away from the device in different orientations. Light reflected from a subject-of-interest is received in optical paths intersected by respective polarizers. Reflected light passing through a first polarizer is substantially orthogonal to reflected light passing through a second polarizer.

Abstract: Paired images of substantially the same scene are captured with the same freestanding sensor. The paired images include reflected light illuminated with controlled polarization states that are different between the separate images. A first pixel value from one of the first image and the second image is subtracted from a corresponding pixel value from a remaining one of the first image and the second image. When repeated over the raster of corresponding pixels, a modified image includes an isolated representation of substantially pure specular color data. The captured images and the modified image are stored and used to generate a model. Substantially shadow-free diffuse color and specular color data are applied to texture maps of the model to generate a virtual environment where a virtual light source can be introduced and controlled to achieve desired results absent adverse effects introduced from fixed ambient light sources used in conventional source photography.

Abstract: An image-capture device includes an enclosure, a lens arranged in a lens housing, an illumination source and an image sensor. The illumination source has separately energized light emitters adjacent to the lens housing. When a first light emitter is energized, light oscillating in a first orientation is directed away from the image-capture device. When a second light emitter is energized, light oscillating in a second orientation different from the first orientation is directed away from the image-capture device. Alternatively, an image-capture device includes image sensors, a lens and an illumination source. The illumination source directs emitted light away from the device in different orientations. Light reflected from a subject-of-interest is received in optical paths intersected by respective polarizers. Reflected light passing through a first polarizer is substantially orthogonal to reflected light passing through a second polarizer.

Abstract: Paired images of substantially the same scene are captured with the same freestanding sensor. The paired images include reflected light illuminated with controlled polarization states that are different between the separate images. A first pixel value from one of the first image and the second image is subtracted from a corresponding pixel value from a remaining one of the first image and the second image. When repeated over the raster of corresponding pixels, a modified image includes an isolated representation of substantially pure specular color data. The captured images and the modified image are stored and used to generate a model. Substantially shadow-free diffuse color and specular color data are applied to texture maps of the model to generate a virtual environment where a virtual light source can be introduced and controlled to achieve desired results absent adverse effects introduced from fixed ambient light sources used in conventional source photography.

Abstract: Paired images of substantially the same scene are captured with the same freestanding sensor. The paired images include reflected light illuminated with controlled polarization states that are different between the separate images. A first pixel value from one of the first image and the second image is subtracted from a corresponding pixel value from a remaining one of the first image and the second image. When repeated over the raster of corresponding pixels, a modified image includes an isolated representation of substantially pure specular color data. The captured images and the modified image are stored and used to generate a model. Substantially shadow-free diffuse color and specular color data are applied to texture maps of the model to generate a virtual environment where a virtual light source can be introduced and controlled to achieve desired results absent adverse effects introduced from fixed ambient light sources used in conventional source photography.