A system and method of multiview style transfer apply a style transfer to individual views of a multiview image in a way that produces consistent results across all images. In some embodiments, the multiview style transfer includes receiving first and second images representative of first and second perspectives of a scene and first and second disparity maps corresponding to the first and second images, generating a first stylized image, generating a stylized shifted image based on the first stylized image and the first disparity map, generating a second stylized image based on a guided filter of the stylized shifted image and the second image, and generating a first and second stylized image based on the stylized shifted images and the disparity maps.

A system and method of multiview style transfer apply a style transfer to individual views of a multiview image in a way that produces consistent results across all images. In some embodiments, the multiview style transfer includes receiving first and second images representative of first and second perspectives of a scene and first and second disparity maps corresponding to the first and second images, generating a first stylized image, generating a stylized shifted image based on the first stylized image and the first disparity map, generating a second stylized image based on a guided filter of the stylized shifted image and the second image, and generating a first and second stylized image based on the stylized shifted images and the disparity maps.

A device for optical-field displaying includes: a display screen and a lens unit provided on a light exiting side of the display screen; the lens unit includes a plurality of lenses arranged in an array; the display screen is provided on a focal plane of the plurality of lenses; the display screen includes a first substrate and a second substrate that match; the first substrate is a light-exiting-side substrate, the second substrate includes a plurality of pixel islands arranged in an array; the plurality of pixel islands correspond to the plurality of lenses; a view region formed by light rays emitted by the sub-pixels of the pixel islands and propagated via the corresponding lenses to a human eye is smaller than or equal to a half-pupil region, and light rays of different viewpoints emitted by different sub-pixels of the pixel islands enter different cone cells via the lenses.

Provided is a method including: obtaining a plurality of images corresponding to a plurality of views; identifying at least one view region overlapping with a sub-pixel from among a plurality of view regions corresponding to the plurality of views; identifying a data value corresponding to the sub-pixel for each of at least one image corresponding to the at least one view region; determining an application degree of the data value for each of the at least one image, based on a level of overlap between the sub-pixel and the at least one view region, and determining an output value of the sub-pixel based on a data value adjusted according to the determined application degree; and outputting an image based on output values respectively determined for a plurality of sub-pixels including the sub-pixel.

Implementations of a compressive light field projection system are disclosed herein. In one embodiment, the compressive light field projection system utilizes a pair of light modulators, such as digital micromirror devices (DMDs), that interact to produce a light field. The light field is then projected via a projection lens onto a screen, which may be an angle expanding projection screen that includes a Fresnel lens for straightening the views of the light field and either a double lenticular array of Keplerian lens pairs or a single lenticular, for increasing the field of view. In addition, compression techniques are disclosed for generating patterns to place on the pair of light modulators so as to reduce the number of frames needed to recreate a light field.

Implementations of a compressive light field projection system are disclosed herein. In one embodiment, the compressive light field projection system utilizes a pair of light modulators, such as digital micromirror devices (DMDs), that interact to produce a light field. The light field is then projected via a projection lens onto a screen, which may be an angle expanding projection screen that includes a Fresnel lens for straightening the views of the light field and either a double lenticular array of Keplerian lens pairs or a single lenticular, for increasing the field of view. In addition, compression techniques are disclosed for generating patterns to place on the pair of light modulators so as to reduce the number of frames needed to recreate a light field.

An electronic apparatus includes a stacked display including a plurality of panels, and a processor configured to obtain first light field (LF) images of different viewpoints, input the obtained first LF images to an artificial intelligence model for converting an LF image into a layer stack, to obtain a plurality of layer stacks to which a plurality of shifting parameters indicating depth information in the first LF images are respectively applied, and control the stacked display to sequentially and repeatedly display, on the stacked display, the obtained plurality of layer stacks. The artificial intelligence model is trained by applying the plurality of shifting parameters that are obtained based on the depth information in the first LF images.

An electronic apparatus includes a stacked display including a plurality of panels, and a processor configured to obtain first light field (LF) images of different viewpoints, input the obtained first LF images to an artificial intelligence model for converting an LF image into a layer stack, to obtain a plurality of layer stacks to which a plurality of shifting parameters indicating depth information in the first LF images are respectively applied, and control the stacked display to sequentially and repeatedly display, on the stacked display, the obtained plurality of layer stacks. The artificial intelligence model is trained by applying the plurality of shifting parameters that are obtained based on the depth information in the first LF images.

Described are various embodiments of a multiview system, method and display for rendering multiview content, and viewer localisation system, method and device therefor. In one embodiment, a multiview system is operable to interface with a mobile device of a given viewer, and comprises: a MultiView Display (MVD); a network-interfacing content-controller; one or more emitters disposed and operable to emit a respectively encoded time-variable emission in each of distinct viewing directions; and a mobile application operable on the mobile device of the given user to capture a given one of the encoded time-variable emissions when the mobile device is located so to intersect a corresponding one of the distinct directions so to self-identify the mobile device as being substantially in line with a corresponding one of the distinct viewing directions.

A micro-slit scattering element based backlight, a multiview display, and a method of backlight operation include reflective micro-slit scattering elements configured to provide emitted light having a predetermined light exclusion zone. The micro-slit scattering element based backlight includes a light guide configured to guide light and a plurality of the reflective micro-slit scattering elements having sloped reflective sidewalls configured to reflectively scatter out the guided light as the emitted light. The sloped reflective sidewalls of the reflective micro-slit scattering elements are configured to provide the predetermined light exclusion zone of the emitted light. The multiview display includes the reflective micro-slit scattering elements arranged as an array of micro-slit multibeam elements. The multiview display also includes an array of light valves to modulate the directional light beams to provide the multiview image, except within the predetermined light exclusion zone.