The present teaching relates to method, system, medium, and implementation of determining depth information in autonomous driving. Stereo images are first obtained from multiple stereo pairs selected from at least two stereo pairs. The at least two stereo pairs have stereo cameras installed with the same baseline and in the same vertical plane. Left images from the multiple stereo pairs are fused to generate a fused left image and right images from the multiple stereo pairs are fused to generate a fused right image. Disparity is then estimated based on the fused left and right images and depth information can be computed based on the stereo images and the disparity.

A unique method and a device to generate free space “pop-out” & “sink-in” holograms is disclosed herein. The hologram disclosed herein does not use any special medium, mirrors, reflective screens or wearables such as headgear & special glasses. The hologram disclosed herein can be created in free space, outer space or in air, without any other optical components except for the special display screen of the hologram device. This device demonstrates a free space hologram and the hologram Augmented Reality & hologram Virtual Reality. A camera capable of hologram quality images equipped with a smart lens which mimics the human eye by changing it's lens aperture according to the light intensity as the pupil of the human eye and focus & capture “pop-out” & “sink-in” hologram images is disclosed herein. The audio which is incorporated with the device provide multi dimensional multi directional audio effects.

A unique method and a device to generate free space “pop-out” & “sink-in” holograms is disclosed herein. The hologram disclosed herein does not use any special medium, mirrors, reflective screens or wearables such as headgear & special glasses. The hologram disclosed herein can be created in free space, outer space or in air, without any other optical components except for the special display screen of the hologram device. This device demonstrates a free space hologram and the hologram Augmented Reality & hologram Virtual Reality. A camera capable of hologram quality images equipped with a smart lens which mimics the human eye by changing it's lens aperture according to the light intensity as the pupil of the human eye and focus & capture “pop-out” & “sink-in” hologram images is disclosed herein. The audio which is incorporated with the device provide multi dimensional multi directional audio effects.

A method for seamless transition from a 2D surround view to a 3D surround view. The method includes initializing the 2D-SRV processing chain, displaying the 2D surround view while waiting for HLOS handshake to complete and upon completion of a HLOS handshake, initializing a 3D-SRV processing chain and waiting for a 3D-SRV buffer output; disabling the 2D-SRV display pipeline and enabling a 3D-SRV display pipeline; enabling switchback monitor; atomically switching to 3D surround view seamlessly and glitch free; and displaying 3D surround view on a monitor. Another method includes detecting a crash in a HLOS and seamlessly switching to a 2D surround view from a 3D surround view.

A method for seamless transition from a 2D surround view to a 3D surround view. The method includes initializing the 2D-SRV processing chain, displaying the 2D surround view while waiting for HLOS handshake to complete and upon completion of a HLOS handshake, initializing a 3D-SRV processing chain and waiting for a 3D-SRV buffer output; disabling the 2D-SRV display pipeline and enabling a 3D-SRV display pipeline; enabling switchback monitor; atomically switching to 3D surround view seamlessly and glitch free; and displaying 3D surround view on a monitor. Another method includes detecting a crash in a HLOS and seamlessly switching to a 2D surround view from a 3D surround view.

An exemplary extended reality presentation system determines that a depiction of an augmentable object within a field of view takes up a first portion of the field of view, and, in response to this determination, presents a first form of an overlay object within the field of view. The first form of the overlay object is graphically associated with the augmentable object. During the presenting of the first form of the overlay object within the field of view, the system determines that the depiction of the augmentable object has come to take up a second portion of the field of view, and, in response to this determination, replaces the first form of the overlay object with a second form of the overlay object within the field of view. The second form of the overlay object is distinct from the first form. Corresponding methods and systems are also disclosed.

An exemplary extended reality presentation system determines that a depiction of an augmentable object within a field of view takes up a first portion of the field of view, and, in response to this determination, presents a first form of an overlay object within the field of view. The first form of the overlay object is graphically associated with the augmentable object. During the presenting of the first form of the overlay object within the field of view, the system determines that the depiction of the augmentable object has come to take up a second portion of the field of view, and, in response to this determination, replaces the first form of the overlay object with a second form of the overlay object within the field of view. The second form of the overlay object is distinct from the first form. Corresponding methods and systems are also disclosed.

A captured scene captured of a live action scene while a display wall is positioned to be part of the live action scene may be processed. To perform the processing, stereoscopic image data of the live action scene is received, and display wall metadata of the precursor image is determined. Further, a first portion of the stereoscopic image data comprising the stage element in the live action scene is determined based on the stereoscopic image data and the display wall metadata. A second portion of the stereoscopic image data comprising the display wall in the live action scene with the display wall displaying the precursor image is also determined. Thereafter, an image matte for the stereoscopic image data is generated based on the first portion and the second portion.

An electronic device is disclosed. The present electronic device comprises a display, a processor electrically connected with the display so as to control the display, and a memory electrically connected with the processor, wherein the memory includes at least one command, and the processor, by executing at least one command, acquires a plurality of object images corresponding to a plurality of objects in a two-dimensional image, acquires a plurality of three-dimensional modeling images corresponding to the plurality of object images and information related to the plurality of objects by applying the plurality of object images to a plurality of network models, and displays, on the display, the three-dimensional images including the plurality of three-dimensional modeling images on the basis of the information related to the plurality of objects and the location information about the plurality of objects in the two-dimensional image.

An electronic device is disclosed. The present electronic device comprises a display, a processor electrically connected with the display so as to control the display, and a memory electrically connected with the processor, wherein the memory includes at least one command, and the processor, by executing at least one command, acquires a plurality of object images corresponding to a plurality of objects in a two-dimensional image, acquires a plurality of three-dimensional modeling images corresponding to the plurality of object images and information related to the plurality of objects by applying the plurality of object images to a plurality of network models, and displays, on the display, the three-dimensional images including the plurality of three-dimensional modeling images on the basis of the information related to the plurality of objects and the location information about the plurality of objects in the two-dimensional image.