Abstract: A color mapping technique that provides an intuitive visualization of surface normals is described. The surface normals can be associated with a mesh for a virtual object to be displayed in augmented reality. The color mapping technique can map a unit sphere in a color space to an octahedron. The vertices of the octahedron can be aligned with prime colors of the color space. To perform the alignment, a rotation and shear matrix can be determined from coordinates for octahedron positions and coordinates of colors in the color space. The rotation and shear can provide that each region of the unit color sphere is dominated by a single prime color, with gradients between prime colors being visually balanced. Surface normals of a mesh for a virtual object can be visualized using the color mapping, and a viewer can readily determine how distant in terms of rotation two surface normals are from each other.

Abstract: A color mapping technique that provides an intuitive visualization of surface normals is described. The surface normals can be associated with a mesh for a virtual object to be displayed in augmented reality. The color mapping technique can map a unit sphere in a color space to an octahedron. The vertices of the octahedron can be aligned with prime colors of the color space. To perform the alignment, a rotation and shear matrix can be determined from coordinates for octahedron positions and coordinates of colors in the color space. The rotation and shear can provide that each region of the unit color sphere is dominated by a single prime color, with gradients between prime colors being visually balanced. Surface normals of a mesh for a virtual object can be visualized using the color mapping, and a viewer can readily determine how distant in terms of rotation two surface normals are from each other.

Abstract: Enhanced techniques for volumetric stage mapping based on a calibration object are described. An example method includes obtaining a plurality of images of a calibration object, the images being obtained from a plurality of image sensors positioned about the calibration object, and the calibration object having location information associated with a volumetric capture surface on which the calibration object is located; generating, based on the images, a reconstructed object associated with the calibration object, the reconstructed object representing a three-dimensional representation of the calibration object; determining reconstruction quality information associated with the reconstructed object, the determination being based on a ground-truth representation of the calibration object; and outputting the reconstruction quality information.

Abstract: A color mapping technique that provides an intuitive visualization of surface normals is described. The surface normals can be associated with a mesh for a virtual object to be displayed in augmented reality. The color mapping technique can map a unit sphere in a color space to an octahedron. The vertices of the octahedron can be aligned with prime colors of the color space. To perform the alignment, a rotation and shear matrix can be determined from coordinates for octahedron positions and coordinates of colors in the color space. The rotation and shear can provide that each region of the unit color sphere is dominated by a single prime color, with gradients between prime colors being visually balanced. Surface normals of a mesh for a virtual object can be visualized using the color mapping, and a viewer can readily determine how distant in terms of rotation two surface normals are from each other.

Abstract: Enhanced techniques for volumetric stage mapping based on a calibration object are described. An example method includes obtaining a plurality of images of a calibration object, the images being obtained from a plurality of image sensors positioned about the calibration object, and the calibration object having location information associated with a volumetric capture surface on which the calibration object is located; generating, based on the images, a reconstructed object associated with the calibration object, the reconstructed object representing a three-dimensional representation of the calibration object; determining reconstruction quality information associated with the reconstructed object, the determination being based on a ground-truth representation of the calibration object; and outputting the reconstruction quality information.

Abstract: Systems and methods for enhanced depth determination using projection spots. An example method includes obtaining images of a real-world object, the images being obtained from image sensors positioned about the real-world object, and the images depicting projection spots projected onto the real-world object via projectors positioned about the real-world object. A projection spot map is accessed, the projection spot map including information indicative of real-world locations of projection spots based locations of the projection spots in the obtained images. Location information is assigned to the projection spots based on the projection spot map. Generation of a three-dimensional representation of the real-world object is caused.

Abstract: A color mapping technique that provides an intuitive visualization of surface normals is described. The surface normals can be associated with a mesh for a virtual object to be displayed in augmented reality. The color mapping technique can map a unit sphere in a color space to an octahedron. The vertices of the octahedron can be aligned with prime colors of the color space. To perform the alignment, a rotation and shear matrix can be determined from coordinates for octahedron positions and coordinates of colors in the color space. The rotation and shear can provide that each region of the unit color sphere is dominated by a single prime color, with gradients between prime colors being visually balanced. Surface normals of a mesh for a virtual object can be visualized using the color mapping, and a viewer can readily determine how distant in terms of rotation two surface normals are from each other.