System and method of detecting multiview file format
Systems and methods are directed to multiview format detection. A multiview image that comprises a plurality of tiled view images is accessed. A cross-correlation map from the multiview image may be generated by autocorrelating the multiview image with a shifted copy of the multiview image. The cross-correlation map may be sampled at a plurality of predefined locations of the cross-correlation map to identify a set of cross-correlation values. A multiview format of the multiview image may be detected by classifying a feature set of the multiview image that comprises the set of cross-correlation values. The multiview image may be configured to be rendered on a multiview display based on the multiview format.
1 . A computer-implemented method of multiview format detection, the method comprising:
accessing a multiview image comprising a plurality of tiled view images;
generating a cross-correlation map from the multiview image by autocorrelating the multiview image with a shifted copy of the multiview image;
sampling the cross-correlation map at a plurality of predefined locations of the cross-correlation map to identify a set of cross-correlation values; and
detecting a multiview format of the multiview image by classifying a feature set of the multiview image that comprises the set of cross-correlation values,
wherein the multiview image is configured to be rendered on a multiview display based on the multiview format.
2 . The computer-implemented method of multiview format detection of claim 1 , further comprising:
determining an aspect ratio of the multiview image, wherein the feature set further comprises the aspect ratio.
3 . The computer-implemented method of multiview format detection of claim 1 , wherein at least one of the predefined locations comprises a corner region of the cross-correlation map.
4 . The computer-implemented method of multiview format detection of claim 1 , wherein at least one of the predefined locations comprises a midpoint along one of a length and a width of the cross-correlation map.
5 . The computer-implemented method of multiview format detection of claim 1 , wherein each cross-correlation value of the set of cross-correlation values is determined based on a single cross-correlation value.
6 . The computer-implemented method of multiview format detection of claim 1 , wherein each cross-correlation value of the set of cross-correlation values is determined by averaging values within a corresponding predefined location.
7 . The computer-implemented method of multiview format detection of claim 1 , further comprising:
training a classifier to classify the feature set according to training data, wherein the training data comprises a training set of multiview images and corresponding training labels.
8 . The computer-implemented method of multiview format detection of claim 7 , wherein the training labels comprise labels indicating a single tile format, a 1-by-2 tile format, a 2-by-1 tile format, and a 2-by-2 tile format.
9 . The computer-implemented method of multiview format detection of claim 1 , wherein the multiview display is configured to provide a broad-angle emitted light during a two-dimensional (2D) mode using a broad-angle backlight; and
wherein the multiview display is configured to provide a directional emitted light during a multiview mode using a multiview backlight having an array of multi beam elements, the directional emitted light comprising a plurality of directional light beams provided by each multi beam element of the multi beam element array; and
wherein the multiview display is configured to time multiplex the 2D mode and the multiview mode using a mode controller to sequentially activate the broad-angle backlight during a first sequential time interval corresponding to the 2D mode and the multiview backlight during a second sequential time interval corresponding to the multiview mode; and
wherein directions of the directional light beams correspond to different view directions of the multiview image.
10 . The computer-implemented method of multiview format detection of claim 1 , wherein the multiview display is configured to guide light in a light guide as guided light; and
wherein the multiview display is configured to scatter out a portion of the guided light as directional emitted light using multibeam elements of a multibeam element array, each multibeam element of the multibeam element array comprising one or more of a diffraction grating, a micro-refractive element, and a micro-reflective element.
11 . A multiview display system comprising:
a multiview display configured to display multiview images;
a processor; and
a memory that stores a plurality of instructions that, when executed, cause the processor to:
access a multiview image comprising a plurality of tiled view images;
generate a cross-correlation map from the multiview image by autocorrelating the multiview image with a shifted copy of the multiview image;
sample the cross-correlation map at a plurality of predefined locations of the cross-correlation map to identify a set of cross-correlation values;
input a feature set of the multiview image into a classifier, the feature set comprising the set of cross-correlation values;
retrieve a label from the classifier, the label indicating a multiview format of the multiview image; and
render the multiview image on a multiview display based on the multiview format.
12 . The multiview display system of claim 11 , wherein the plurality of instructions, when executed, further cause the processor to:
determine an aspect ratio of the multiview image, wherein the feature set further comprises the aspect ratio.
13 . The multiview display system of claim 11 , wherein at least one of the predefined locations comprises a corner region of the cross-correlation map.
14 . The multiview display system of claim 11 , wherein at least one of the predefined locations comprises a midpoint along one of a length and a width of the cross-correlation map.
15 . The multiview display system of claim 11 , wherein each cross-correlation value of the set of cross-correlation values is determined based on a single cross-correlation value.
16 . The multiview display system of claim 11 , wherein the classifier is trained using training data, wherein the training data comprises a training set of multiview images and corresponding training labels.
17 . The multiview display system of claim 16 , wherein the training labels comprise labels indicating a single tile format, a 1-by-2 tile format, and a 2-by-1 tile format.
18 . A computer program comprising executable instructions that, when executed by a processor of a computer system, perform operations of multiview format detection, the operations comprising:
accessing a multiview image comprising a plurality of tiled view images;
generating a cross-correlation map from the multiview image by autocorrelating the multiview image with a shifted copy of the multiview image;
sampling the cross-correlation map at a plurality of predefined locations of the cross-correlation map to identify a set of cross-correlation values;
detecting a multiview format of the multiview image by classifying a feature set of the multiview image that comprises the set of cross-correlation values; and
interlacing pixels of the tiled view images of the multiview image upon detecting the multiview format.
19 . The computer program of claim 18 , wherein the operations further comprise:
determining an aspect ratio of the multiview image, wherein the feature set further comprises the aspect ratio.
20 . The computer program of claim 18 , wherein the multiview format is a 1-by-2 tile format, a 2-by-1 tile format, or a 2-by-2 tile format.