Abstract: Techniques for training and using machine learning models for video encoding mode selection are described. According to some embodiments, a computer-implemented method includes receiving a live video at a content delivery service, extracting one or more features for a plurality of macroblocks of a frame of the live video, determining an encoding mode from a plurality of encoding modes for each of the plurality of macroblocks of the frame with a machine learning model based at least in part on an input of the one or more features, performing a real time encode of the frame of the live video based at least in part on the determined encoding modes to generate an encoded frame by the content delivery service, and transmitting the encoded frame from the content delivery service to a viewer device.

Abstract: An example lighting assembly may comprise: a mounting frame comprising a plurality of vertical bars positioned on an imaginary cylindrical surface; a plurality of horizontal joists attached to the vertical bars; a plurality of lighting fixtures attached to the mounting frame; and a plurality of camera mounts attached to the mounting frame; wherein the lighting fixtures and camera mounts are positioned to form a pre-defined grid configuration.

Abstract: An example lighting assembly may comprise: a mounting frame comprising a plurality of vertical bars positioned on an imaginary cylindrical surface; a plurality of horizontal joists attached to the vertical bars; a plurality of lighting fixtures attached to the mounting frame; and a plurality of camera mounts attached to the mounting frame; wherein the lighting fixtures and camera mounts are positioned to form a pre-defined grid configuration.

Abstract: An example method of photometric image processing may comprise: receiving a plurality of images of a three-dimensional object, wherein the plurality of images has been acquired by a plurality of cameras using a plurality of illumination and polarization patterns; performing color calibration of the plurality of images to produce a plurality of color-calibrated images; generating, using the plurality of color-calibrated images, a polygonal mesh simulating geometry of the three-dimensional object; producing a plurality of partial UV maps by projecting the plurality of color-calibrated images onto the polygonal mesh; generating a plurality of masks, wherein each mask of the plurality of masks is associated with a camera of the plurality of cameras, wherein the mask defines a UV space region that is covered by a field of view of the camera; blending, using the plurality of masks, the plurality of partial UV maps; and generating one or more texture maps representing the three-dimensional object.

Abstract: An example lighting assembly may comprise: a mounting frame comprising a plurality of vertical bars positioned on an imaginary cylindrical surface; a plurality of horizontal joists attached to the vertical bars; a plurality of lighting fixtures attached to the mounting frame; and a plurality of camera mounts attached to the mounting frame; wherein the lighting fixtures and camera mounts are positioned to form a pre-defined grid configuration.

Abstract: An example lighting assembly may comprise: a mounting frame comprising a plurality of vertical bars positioned on an imaginary cylindrical surface; a plurality of horizontal joists attached to the vertical bars; a plurality of lighting fixtures attached to the mounting frame; and a plurality of camera mounts attached to the mounting frame; wherein the lighting fixtures and camera mounts are positioned to form a pre-defined grid configuration.

Abstract: An example method of photometric image processing may comprise: receiving a plurality of images of a three-dimensional object, wherein the plurality of images has been acquired by a plurality of cameras using a plurality of illumination and polarization patterns; performing color calibration of the plurality of images to produce a plurality of color-calibrated images; generating, using the plurality of color-calibrated images, a polygonal mesh simulating geometry of the three-dimensional object; producing a plurality of partial UV maps by projecting the plurality of color-calibrated images onto the polygonal mesh; generating a plurality of masks, wherein each mask of the plurality of masks is associated with a camera of the plurality of cameras, wherein the mask defines a UV space region that is covered by a field of view of the camera; blending, using the plurality of masks, the plurality of partial UV maps; and generating one or more texture maps representing the three-dimensional object.

Abstract: An example method of photometric image processing may comprise: receiving a plurality of images of a three-dimensional object, wherein the plurality of images has been acquired by a plurality of cameras using a plurality of illumination and polarization patterns; performing color calibration of the plurality of images to produce a plurality of color-calibrated images; generating, using the plurality of color-calibrated images, a polygonal mesh simulating geometry of the three-dimensional object; producing a plurality of partial UV maps by projecting the plurality of color-calibrated images onto the polygonal mesh; generating a plurality of masks, wherein each mask of the plurality of masks is associated with a camera of the plurality of cameras, wherein the mask defines a UV space region that is covered by a field of view of the camera; blending, using the plurality of masks, the plurality of partial UV maps; and generating one or more texture maps representing the three-dimensional object.

Abstract: An example lighting assembly may comprise: a mounting frame comprising a plurality of vertical bars positioned on an imaginary cylindrical surface; a plurality of horizontal joists attached to the vertical bars; a plurality of lighting fixtures attached to the mounting frame; and a plurality of camera mounts attached to the mounting frame; wherein the lighting fixtures and camera mounts are positioned to form a pre-defined grid configuration.

Abstract: An example method of photometric image processing may comprise: receiving a plurality of images of a three-dimensional object, wherein the plurality of images has been acquired by a plurality of cameras using a plurality of illumination and polarization patterns; performing color calibration of the plurality of images to produce a plurality of color-calibrated images; generating, using the plurality of color-calibrated images, a polygonal mesh simulating geometry of the three-dimensional object; producing a plurality of partial UV maps by projecting the plurality of color-calibrated images onto the polygonal mesh; generating a plurality of masks, wherein each mask of the plurality of masks is associated with a camera of the plurality of cameras, wherein the mask defines a UV space region that is covered by a field of view of the camera; blending, using the plurality of masks, the plurality of partial UV maps; and generating one or more texture maps representing the three-dimensional object.