A stereoscopic image generating method is provided. The method includes: processing a first image to obtain depth data of each pixel in the first image, and generating a first depth-information map, wherein the first depth-information map includes depth information corresponding to each pixel; performing uniform processing on a plurality of edge pixels which are within a predetermined width from a plurality of edges of the first depth-information map, so that the processed edge pixels have the same depth information to establish a second depth-information map; setting a pixel offset corresponding to each pixel in the first image based on the depth information corresponding to each pixel of the second depth-information map; performing pixel offset processing on the first image to generate a second image; and outputting the first image and the second image to the display unit to display a stereoscopic image.

A method for generating stereoscopic images is provided. The method includes: creating a three-dimensional mesh to obtain a stereoscopic scene and capturing a two-dimensional image of the stereoscopic scene; performing image preprocessing to obtain a first image in response to the two-dimensional image not being a side-by-side image; utilizing a graphics processing pipeline to perform depth estimation on the first image to obtain a depth image, to update the three-dimensional mesh according to a depth setting of the depth image, and to map the three-dimensional mesh to a corresponding coordinate system; utilizing the graphics processing pipeline to project the first image onto the mapped three-dimensional mesh to obtain an output three-dimensional mesh, and to capture an output side-by-side image from the output three-dimensional mesh; and utilizing the graphics processing pipeline to weave a left-eye and right-eye image into an output image, and to display the output image.

A method for generating stereoscopic images is provided. The method includes: creating a three-dimensional mesh to obtain a stereoscopic scene and capturing a two-dimensional image of the stereoscopic scene; performing image preprocessing to obtain a first image in response to the two-dimensional image not being a side-by-side image; utilizing a graphics processing pipeline to perform depth estimation on the first image to obtain a depth image, to update the three-dimensional mesh according to a depth setting of the depth image, and to map the three-dimensional mesh to a corresponding coordinate system; utilizing the graphics processing pipeline to project the first image onto the mapped three-dimensional mesh to obtain an output three-dimensional mesh, and to capture an output side-by-side image from the output three-dimensional mesh; and utilizing the graphics processing pipeline to weave a left-eye and right-eye image into an output image, and to display the output image.

This disclosure is directed to coding a multi-view signal, which includes processing a list of plurality of motion vector candidates associated with a coding block of a current picture in a dependent view of the multi-view signal. Such processing includes estimating a first motion vector based on a second motion vector associated with a reference block in a current picture of a reference view of the multi-view signal, the reference block corresponding to the coding block of the current picture in the dependent view. The first motion vector is added into the list, and an index is used that specifies at least one candidate from the list to be used for motion-compensated prediction. The coding block in the current picture is coded by performing the motion-compensated prediction based on the at least one candidate indicated by the index.

This disclosure is directed to coding a multi-view signal, which includes processing a list of plurality of motion vector candidates associated with a coding block of a current picture in a dependent view of the multi-view signal. Such processing includes estimating a first motion vector based on a second motion vector associated with a reference block in a current picture of a reference view of the multi-view signal, the reference block corresponding to the coding block of the current picture in the dependent view. The first motion vector is added into the list, and an index is used that specifies at least one candidate from the list to be used for motion-compensated prediction. The coding block in the current picture is coded by performing the motion-compensated prediction based on the at least one candidate indicated by the index.

In one embodiment, a method includes accessing first image data generated by a first image sensor having a first filter array that has a first filter pattern. The first filter pattern includes a number of first filter types. The method also includes accessing second image data generated by a second image sensor having a second filter array that has a second filter pattern different from the first filter pattern. The second filter pattern includes a number of second filter types, the number of second filter types and the number of first filter types have at least one filter type in common. The method also includes determining a correspondence between one or more first pixels of the first image data and one or more second pixels of the second image data based on a portion of the first image data associated with the filter type in common.

Systems and methods are described for simulating motion parallax in 360-degree video. In an exemplary embodiment for producing video content, a method includes obtaining a source video, based on information received from a client device, determining a selected number of depth layers, producing, from the source video, a plurality of depth layer videos corresponding to the selected number of depth layers, wherein each depth layer video is associated with at least one respective depth value, and wherein each depth layer video includes regions of the source video having depth values corresponding to the respective associated depth value, and sending the plurality of depth layer videos to the client device.

Systems and methods are described for simulating motion parallax in 360-degree video. In an exemplary embodiment for producing video content, a method includes obtaining a source video, based on information received from a client device, determining a selected number of depth layers, producing, from the source video, a plurality of depth layer videos corresponding to the selected number of depth layers, wherein each depth layer video is associated with at least one respective depth value, and wherein each depth layer video includes regions of the source video having depth values corresponding to the respective associated depth value, and sending the plurality of depth layer videos to the client device.

A method for training a depth estimation model with depth hints is disclosed. For each image pair: for a first image, a depth prediction is determined by the depth estimation model and a depth hint is obtained; the second image is projected onto the first image once to generate a synthetic frame based on the depth prediction and again to generate a hinted synthetic frame based on the depth hint; a primary loss is calculated with the synthetic frame; a hinted loss is calculated with the hinted synthetic frame; and an overall loss is calculated for the image pair based on a per-pixel determination of whether the primary loss or the hinted loss is smaller, wherein if the hinted loss is smaller than the primary loss, then the overall loss includes the primary loss and a supervised depth loss between depth prediction and depth hint. The depth estimation model is trained by minimizing the overall losses for the image pairs.

A display of an augmented reality-enabled (AR) device, such as a mobile phone, can be used to transfer a graphical object between a secondary display, such as a computer monitor, that is captured by a camera of the AR device, and AR space, where the object is visible only through the AR interface of the AR device. A graphical object can be selected through the AR interface and, for example, moved around on a canvas of the secondary display by the user of the AR device. When the AR interface is used to move an enabled object near an edge of the canvas or physical boundary of the secondary display, the object as shown on the secondary display can be made to disappear from the secondary display to be replaced by a virtual object shown only on the AR interface in a similar location.