In some aspects, the techniques described herein relate to systems, methods, and computer readable media for generating, based on a set of images, a temporal pixel image comprising a set of temporal pixels, where each temporal pixel in the set of temporal pixels comprises a set of pixel values at an associated position from each image of the set of images. For a first temporal pixel from the set of temporal pixels, saturation data comprising a set of saturation values is generated, where each saturation value of the set of saturation values is associated with a pixel value of the set of pixel values of the first temporal pixel, and each pixel value is compared to a metric to determine a corresponding saturation value.

In some aspects, the techniques described herein relate to systems, methods, and computer readable media for data pre-processing for stereo-temporal image sequences to improve three-dimensional data reconstruction. In some aspects, the techniques described herein relate to systems, methods, and computer readable media for improved correspondence refinement for image areas affected by oversaturation. In some aspects, the techniques described herein relate to systems, methods, and computer readable media configured to fill missing correspondences to improve three-dimensional (3-D) reconstruction. The techniques include identifying image points without correspondences, using existing correspondences and/or other information to generate approximated correspondences, and cross-checking the approximated correspondences to determine whether the approximated correspondences should be used for the image processing.

The invention relates to a method for calibrating color components of the sensors of a multi-camera device. The method comprises capturing images by more than one sensor of a multi-camera device (910); creating a pool of images of the captured images (920); extracting a first set of color correction parameters utilizing the pool of images (930); extracting a second set of color correction parameters utilizing the pool of images, wherein the second set of color correction parameters has the smallest errors relative to the first set of color correction parameters (940); and calibrating color components of said more than one sensors of the multi-camera device according to the second set of color correction parameters (950).

An electrically controlled spectacle includes a spectacle frame and optoelectronic lenses housed in the frame. The lenses include a left lens and a right lens, each of the optoelectrical lenses having a plurality of states, wherein the state of the left lens is independent of the state of the right lens. The electrically controlled spectacle also includes a control unit housed in the frame, the control unit being adapted to control the state of each of the lenses independently.

A main video sequence of a live action scene is captured along with ancillary device data to provide corresponding volumetric information about the scene. The volumetric data can then be used to visually remove or replace objects in the main video sequence. A removed object is replaced by the view that would have been captured by the main video sequence had the removed object not been present in the live action scene at the time of capturing.

An imagery processing system determines pixel color values for pixels of captured imagery from volumetric data, providing alternative pixel color values. A main imagery capture device, such as a camera, captures main imagery such as still images and/or video sequences, of a live action scene. Alternative devices capture imagery of the live action scene, in some spectra and form, and capture information related to pixel color values for multiple depths of a scene, which can be processed to provide reconstruction.

Systems and methods for automatically optimizing pairs of stereo images are presented. Pixels in an image pair are reprojected from their raw format to a common pixel-space coordinate system. The image pair is masked to remove pixels that do not appear in both images. Each image undergoes a local enhancement process. The local enhancements are processed into a global enhancement for each image of the image pair. A factor is calculated to balance the left and right images with each other. A brightness factor for the image pair is calculated. The enhancements, including the balancing and brightness factors, are then mapped to their respective images.

A method for compressing geometric data and video is disclosed. The method includes receiving video and associated geometric data for a physical location, generating a background video from the video, and generating background geometric data for the geometric data outside of a predetermined distance from a capture point for the video as a skybox sphere at a non-parallax distance. The method further includes generating a geometric shape for a first detected object within the predetermined distance from the capture point from the geometric data, generating shape textures for the geometric shape from the video, and encoding the background video and shape textures as compressed video along with the geometric shape and the background geometric data as encoded volumetric video.

An electrically controlled spectacle includes a spectacle frame and optoelectronic lenses housed in the frame. The lenses include a left lens and a right lens, each of the optoelectrical lenses having a plurality of states, wherein the state of the left lens is independent of the state of the right lens. The electrically controlled spectacle also includes a control unit housed in the frame, the control unit being adapted to control the state of each of the lenses independently.

In some aspects, the techniques described herein relate to systems, methods, and computer readable media for data pre-processing for stereo-temporal image sequences to improve three-dimensional data reconstruction. In some aspects, the techniques described herein relate to systems, methods, and computer readable media for improved correspondence refinement for image areas affected by oversaturation. In some aspects, the techniques described herein relate to systems, methods, and computer readable media configured to fill missing correspondences to improve three-dimensional (3-D) reconstruction. The techniques include identifying image points without correspondences, using existing correspondences and/or other information to generate approximated correspondences, and cross-checking the approximated correspondences to determine whether the approximated correspondences should be used for the image processing.