Electronic device, and method for displaying three-dimensional image

Abstract

An electronic device according to an embodiment of the present disclosure may comprise: a display; at least one processor; and at least one memory storing instructions, wherein the instructions, when executed individually or collectively by the at least one processor, cause the electronic device to: identify a specific object in an image; identify at least one movement point of a virtual camera on the basis of the location of the specific object; identify a movement trajectory on the basis of the at least one movement point; capture an image on the basis of the movement trajectory; and display the image on the display and / or store the image in the at least one memory.

Description

Electronic devices and methods for displaying three-dimensional images

[0001] The present disclosure relates to an electronic device and a method for displaying a three-dimensional image.

[0002] Typically, electronic devices can convert two-dimensional (2D) images into three-dimensional (3D) images and provide them to users. For example, an electronic device can determine depth information based on a 2D image and convert it into a 3D mesh to create a voluminous 3D image. Through the 3D image generated by the electronic device's conversion of a 2D image, the user can enhance their user experience.

[0003] The above information may be provided as background art to aid in understanding the present disclosure. No claim or determination is made as to whether any of the above-described matters constitute prior art related to the present disclosure.

[0004] An electronic device according to one embodiment of the present disclosure may include a display.

[0005] An electronic device according to one embodiment of the present disclosure may include at least one processor.

[0006] An electronic device according to one embodiment of the present disclosure may include at least one memory for storing instructions.

[0007] The instructions according to one embodiment of the present disclosure, when individually or collectively executed by the at least one processor, may cause the electronic device to identify a specific object in an image.

[0008] The instructions according to one embodiment of the present disclosure, when individually or collectively executed by the at least one processor, may cause the electronic device to identify at least one movement point of the virtual camera based on the location of the specific object.

[0009] The instructions according to one embodiment of the present disclosure, when individually or collectively executed by the at least one processor, may cause the electronic device to determine a movement trajectory based on the at least one movement point.

[0010] The instructions according to one embodiment of the present disclosure, when individually or collectively executed by the at least one processor, may cause the electronic device to capture a 3D (three-dimensional) image based on the movement trajectory, and display the 3D image on the display and / or store the 3D image in the at least one memory.

[0011] A method for displaying a 3D image of an electronic device according to one embodiment of the present disclosure may include an operation of identifying a specific object in an image.

[0012] A method for displaying a 3D image of an electronic device according to one embodiment of the present disclosure may include an operation of identifying at least one movement point of a virtual camera based on a location of the specific object.

[0013] A method for displaying a 3D image of an electronic device according to one embodiment of the present disclosure may include an operation of confirming a movement trajectory based on at least one movement point.

[0014] A method for displaying a 3D image of an electronic device according to one embodiment of the present disclosure may include an operation of capturing an image based on the movement trajectory.

[0015] A method for displaying a 3D image of an electronic device according to one embodiment of the present disclosure may include an operation of displaying the image on the display and / or storing the image in at least one memory.

[0016] In connection with the description of the drawings, the same or similar reference numerals may be used for the same or similar components.

[0017] FIG. 1 is a block diagram of an exemplary electronic device capable of performing the operations described within the present disclosure.

[0018] FIG. 2 is a drawing showing a 3D (three dimensional) image program (200) according to one embodiment of the present disclosure.

[0019] Figure 3 is a flowchart illustrating a three-dimensional image display method according to one embodiment of the present invention.

[0020] FIG. 4 is a diagram illustrating a method for an electronic device to recognize a specific object in an image according to an embodiment of the present disclosure.

[0021] FIG. 5 is a diagram illustrating a method for an electronic device to recognize a specific object in an image according to an embodiment of the present disclosure.

[0022] FIG. 6 is a diagram illustrating a method for an electronic device to recognize a specific object in an image according to an embodiment of the present disclosure.

[0023] FIG. 7 is a diagram illustrating a method by which an electronic device according to one embodiment of the present disclosure recognizes a face of a specific object in an image and finds its gaze.

[0024] FIG. 8 is a diagram illustrating a method by which an electronic device according to one embodiment of the present disclosure recognizes a face of a specific object in an image and finds its gaze.

[0025] FIG. 9 is a diagram illustrating a method for an electronic device according to an embodiment of the present disclosure to identify a start point and an end point.

[0026] FIG. 10 is a diagram illustrating a method for an electronic device to identify a starting point according to an embodiment of the present disclosure.

[0027] FIG. 11 is a diagram illustrating a method for an electronic device to identify an end point according to an embodiment of the present disclosure.

[0028] FIG. 12 is a diagram illustrating a method for an electronic device according to an embodiment of the present disclosure to identify a passing point based on a start point and an end point.

[0029] FIG. 13 is a diagram illustrating a method for an electronic device to determine a start point and an end point when a specific object does not include a face according to one embodiment of the present disclosure.

[0030] FIG. 14 is a diagram illustrating a case in which a plurality of specific objects are included in an image according to one embodiment of the present disclosure.

[0031] FIG. 15 is a diagram illustrating a method for an electronic device to identify a start point, a pass point, and an end point in FIG. 14 according to one embodiment of the present disclosure.

[0032] FIG. 16 is a diagram illustrating a method for an electronic device to determine a movement trajectory according to one embodiment of the present disclosure.

[0033] FIG. 17 is a diagram illustrating a method for an electronic device to identify movement trajectories when a plurality of specific objects are included in an image according to one embodiment of the present disclosure.

[0034] FIG. 18 is a diagram showing the direction of a virtual camera when an electronic device according to an embodiment of the present disclosure captures a specific object of an image along a movement trajectory.

[0035] FIG. 19 is a diagram schematically illustrating the movement time of a virtual camera between moving points according to one embodiment of the present disclosure.

[0036] FIG. 20 is a diagram illustrating a method for capturing a 3D image by applying a glambot shooting effect to a specific object included in an image by an electronic device according to an embodiment of the present disclosure.

[0037] FIG. 21 is a diagram illustrating a user interface in which the position movement and zoom effect of a moving point can be changed according to user input according to one embodiment of the present disclosure.

[0038] Hereinafter, various embodiments of the present disclosure will be described in detail with reference to the accompanying drawings, thereby enabling those skilled in the art to easily implement the present disclosure. The present disclosure may be implemented in various forms and is not limited to the embodiments described herein.

[0039] When a typical electronic device displays a 3D image generated by converting a 2D image, if the 3D image is displayed statically or the 3D effect is not expressed well, there is a problem in that the user cannot feel the difference between the 2D image and the 3D image.

[0040] An electronic device and a three-dimensional image display method according to one embodiment of the present disclosure can display a 3D image generated based on a 2D image as an image captured in a virtual space.

[0041] An electronic device and a three-dimensional image display method according to one embodiment of the present disclosure can display a 3D image generated based on a 2D image as an image and / or video taken in a virtual space.

[0042] An electronic device and a three-dimensional image display method according to one embodiment of the present disclosure can naturally provide a user with a 3D image generated based on a 2D image by displaying the generated 3D image as an image and / or video taken in a virtual space.

[0043] FIG. 1 is a block diagram of an exemplary electronic device (100) capable of performing the operations described within the present disclosure.

[0044] Referring to FIG. 1, the electronic device (100) may be one of various forms of electronic devices, such as a notebook (190), smartphones (191) having various form factors (e.g., a bar-type smartphone (191-1), a foldable-type smartphone (191-2), or a sliderable (or rollable) type smartphone (191-3)), a tablet (192), a cellular phone (not shown), and other similar computing devices (not shown). The components, their relationships, and their functions illustrated in FIG. 1 are exemplary only and do not limit the implementations described or claimed in the present disclosure. The electronic device (100) may be referred to as a mobile device, a user device, a multi-function device, a portable device, or a server.

[0045] The electronic device (100) may include components including at least one processor (110) (hereinafter referred to as processor (110)), at least one memory (120) (hereinafter referred to as memory (120)), at least one display (140) (hereinafter referred to as display (140)), at least one image sensor (150) (hereinafter referred to as image sensor (150)), at least one communication circuit (160) (hereinafter referred to as communication circuit (160)), and / or at least one sensor (170) (hereinafter referred to as sensor (170)). The above components are merely exemplary. For example, the electronic device (100) may include other components (e.g., power management integrated circuitry (PMIC), audio processing circuitry, an antenna, a rechargeable battery, or an input / output interface). For example, some components may be omitted from the electronic device (100). For example, some components may be integrated into one component.

[0046] The processor (110) may be implemented as one or more IC (integrated circuit (or circuitry)) chips and may perform various data processing. The processor (110) may include at least one electrical circuit and may individually or collectively perform distributed processing of instructions (or programs, data, etc.) stored in the memory (120). The processor (110) may include a processor assembly including one or more processing circuits. The processor (110) may include any processing circuit operative to control the performance and operations of one or more components (e.g., the memory (120), the display (140), the image sensor (150), the communication circuit (160), and / or the sensor (170)) of the electronic device (100). For example, the processor (110) (e.g., the application processor (AP)) may be implemented as a system on chip (SoC) (e.g., a single chip or a chipset). For example, the processor (110) may be implemented with multiple cores (or at least one core circuit), multiple chips, or multiple chipsets. For example, the processor (110) may include one or more processing circuits. For example, the processor (110) may include one or more processing circuits configured to individually and / or collectively perform various functions of the present disclosure. As a non-limiting example, at least a portion of the processor (110) may be included in a first chip of the electronic device (100), and at least another portion of the processor (110) may be included in a second chip of the electronic device (100) that is different from the first chip of the electronic device (100).

[0047] For example, the processor (110) may include a central processing unit (CPU) (111), a graphics processing unit (GPU) (112), a neural processing unit (NPU) (113), an image signal processor (ISP) (114), a display controller (115), a memory controller (116), a storage controller (117), a communication processor (CP) (118), and / or a sensor interface (119). These components of the processor (110) are merely exemplary. For example, the processor (110) may further include other components. For example, some components of the processor (110) may be omitted from the processor (110). For example, some components of the processor (110) may be included as separate components of the electronic device (100) outside the processor (110). For example, some components of the processor (110) (e.g., memory controller (116)) may be included within other components (e.g., at least a portion of memory (120), an interface (e.g., available for connection to at least one component of the electronic device (100)), a display (140) and / or an image sensor (150)).

[0048] The processor (110) may cause other components of the electronic device (100) to perform various operations by executing instructions stored in the memory (120). The CPU (111) (or central processing circuit) may be configured to control components of the processor (110) based on the execution of instructions stored in the memory (120) (e.g., volatile memory (121) and / or non-volatile memory (122)). The GPU (112) (or graphics processing circuit) may be configured to execute parallel operations (e.g., rendering). The NPU (113) (or neural processing circuit, or artificial intelligence (AI) chip) may be configured to execute operations for an artificial intelligence model (e.g., convolution computation). The ISP (114) (or image signal processing circuit) may be configured to process a raw image acquired through the image sensor (150) into a format suitable for a component within the electronic device (100) or a component of the processor (110). The display controller (115) (or display control circuit, or display processing unit (DPU)) may be configured to process an image acquired from the CPU (111), the GPU (112), the ISP (114), or the memory (120) (e.g., the volatile memory (121)) into a format suitable for the display (140). The memory controller (116) (or memory control circuit) may be configured to control reading data from the volatile memory (121) and writing data to the volatile memory (121). The storage controller (117) (or storage control circuit) may be configured to control reading data from the nonvolatile memory (122) and writing data to the nonvolatile memory (122).The CP (118) (communication processing circuit) may be configured to process data acquired from a component of the processor (110) into a format suitable for transmission to another electronic device via the communication circuit (160), or to process data acquired from another electronic device via the communication circuit (160) into a format suitable for processing by the component of the processor (110). For example, the communication circuit (160) may include one or more communication circuits. The sensor interface (119) (or sensing data processing circuit, sensor hub) may be configured to process data about the state of the electronic device (100) and / or the state of the surroundings of the electronic device (100), acquired via the sensor (170), into a format suitable for the component of the processor (110).

[0049] The memory (120) may include one or more storage media (or one or more storage devices). For example, the memory (120) may include a memory assembly including one or more storage media. For example, the one or more storage media may include permanent memory (e.g., non-volatile memory (122)) such as a hard drive, flash memory, read-only memory (ROM), semi-permanent memory (e.g., volatile memory (121)) such as random access memory (RAM), any other suitable type of storage (or storage assembly), or any combination thereof. The memory (120) may include cache memory, which is one or more different types of memory used to temporarily store data for a function or feature of the electronic device (100). As a non-limiting example, the cache memory may be included within the processor (110). The memory (120) may be fixedly embedded within the electronic device (100) or incorporated into one or more suitable types of components (e.g., a subscriber identity module (SIM) card and / or a secure digital (SD) card) that may be repeatedly inserted into and removed from the electronic device (100).

[0050] For example, the memory (120) may store one or more software applications, such as an operating system (or system) software application, a firmware software application, a driver software application, a plug-in (e.g., add-in, add-on, and / or applet) software application, and / or any other suitable software applications. For example, the one or more software applications may include instructions executable by the processor (110). For example, the memory (120) may store instructions callable by an application programming interface (API). For example, the memory (120) may store instructions within a library.

[0051] FIG. 2 is a drawing showing a 3D (three dimensional) image program (200) according to one embodiment of the present disclosure.

[0052] In one embodiment, the electronic device (100) may include a 3D image program (200). The processor (110) of FIG. 1 may store the 3D image program (200). The memory (120) of FIG. 1 may store the 3D image program (200). The 3D image program (200) stored in the memory (120), when executed by the processor (110), may cause the electronic device (100) (or the processor (110)) to perform a 3D image display method (e.g., the 3D image display method of FIG. 3 described below).

[0053] In one embodiment, a three dimensional (3D) imaging program (200) may include a segment engine (210), a depth heat map (220), a saliency learning model (230), a face detection model (240), a virtual camera (250), and / or a trajectory generation model (260).

[0054] In one embodiment, each of the segmentation engine (210), depth heat map (220), attention learning model (230), face recognition model (240), virtual camera (250), and trajectory generation model (260) may be artificial intelligence-based (e.g., generative AI).

[0055] In one embodiment, the segmentation engine (210), depth heat map (220), attention learning model (230), face recognition model (240), virtual camera (250), and trajectory generation model (260) may be one artificial intelligence-based (e.g., generative AI).

[0056] In one embodiment, an artificial intelligence-based (e.g., generative AI) system, under the control of a processor (110), may perform at least some operations of a segmentation engine (210), a depth heat map (220), an attention learning model (230), a face recognition model (240), a virtual camera (250), and / or a trajectory generation model (260) based on inputs defined by prompts.

[0057] In one embodiment, a segmentation engine (210) can perform segmentation on an image. The electronic device (100) can detect and classify objects in an image using the segmentation engine (210). The electronic device (100) can identify the boundaries of objects included in an image and recognize the objects using the segmentation engine (210).

[0058] In one embodiment, the depth heat map (220) can express the depth of a corresponding location using the color of each pixel. The depth heat map (220) can infer and find the perspective of a 2D (two-dimensional) image, and convert an object included in the 2D image into a 3D mesh based on the depth information. The depth heat map (220) can separate the foreground layer and the background layer based on the part with the greatest change in the Z coordinate in the converted 3D space, and identify the layer separated as the foreground as a region of interest and / or a specific object. The depth heat map (220) can identify the object located at the frontmost position on the image as a region of interest and / or a specific object based on the condition of the weight.

[0059] In one embodiment, the attention learning model (230) can automatically detect and identify important and / or noticeable parts of an image or video. The attention learning model (230) can evaluate the likelihood that each pixel within the image or video will receive attention. The attention learning model (230) can analyze information surrounding the pixel, such as color, contrast, and texture, to evaluate the likelihood of receiving attention. Based on the evaluation of the likelihood of receiving attention, the attention learning model (230) can identify an area corresponding to a specific score or higher as a region of interest and / or a specific object.

[0060] In one embodiment, the instructions stored in the memory (130), when executed by at least one processor (110), may cause the electronic device (100) to identify regions of interest and / or specific objects in an image using at least one of a segmentation engine (210), a depth heat map (220), or an attention learning model (230).

[0061] In one embodiment, instructions stored in memory (130), when executed by at least one processor (110), may cause the electronic device (100) to identify a region of interest and / or a specific object in an image using the segmentation engine (210).

[0062] In one embodiment, instructions stored in memory (130), when executed by at least one processor (110), may cause the electronic device (100) to identify a region of interest and / or a specific object in an image using a depth heat map (220).

[0063] In one embodiment, instructions stored in memory (130), when executed by at least one processor (110), may cause the electronic device (100) to identify regions of interest and / or specific objects in an image using an attention learning model (230).

[0064] In one embodiment, the region of interest and / or specific object can be identified by processing the intersecting regions among the regions of interest and / or specific objects identified by the segment engine (210), the depth heat map (220), and / or the attention learning model (230).

[0065] In one embodiment, the instructions stored in the memory (130), when executed by at least one processor (110), may cause the electronic device (100) to identify a region of interest and / or a specific object by combining weights for the regions identified by the segmentation engine (210), the depth heat map (220), and / or the attention learning model (230) and identifying the region with the highest average as the region of interest and / or the specific object.

[0066] In one embodiment, instructions stored in the memory (130) among the regions of interest and / or specific objects identified by the segmentation engine (210), the depth heat map (220), and / or the attention learning model (230), when executed by at least one processor (110), may cause the electronic device (100) to assign different accuracy weights to the regions of interest and / or specific objects identified by the segmentation engine (210). For example, among the regions of interest and / or specific objects identified by the segment engine (210), the depth heat map (220), and / or the attention learning model (230), the instructions stored in the memory (130), when executed by at least one processor (110), can cause the electronic device (100) to give the highest accuracy weight to the regions of interest or specific objects identified by the segment engine (210), to give the lowest accuracy weight to the regions of interest and / or specific objects identified by the attention learning model (230), and to set the accuracy weight to the regions of interest and / or specific objects identified by the depth heat map (220) between the segment engine (210) and the attention learning model (230).

[0067] In one embodiment, the electronic device (100) may perform a condition for identifying a region of interest and / or a specific object in an image based on the results of an interest region learning model (e.g., segmentation engine (210), depth heat map (220), and / or attention learning model (230)). For example, by using an attention learning model (230) learned for a region of interest and / or a specific object that a person feels emotionally, the electronic device (100) may increase the accuracy of identifying a region of interest and / or a specific object and enable the user to obtain a desired result.

[0068] In one embodiment, the instructions stored in the memory (130), when executed by at least one processor (110), may cause the electronic device (100) to assign different weights to each region of interest learning model (e.g., segmentation engine (210), depth heat map (220), and / or saliency learning model (230)). For example, since there is no guarantee that a region of interest and / or a specific object perceived by a person and a saliency region of interest and / or a specific object identified using the saliency learning model (230) are expressed as a 3D object on a 3D image, the lowest weight may be assigned to the region of interest and / or the specific object identified using the saliency learning model (230).

[0069] In one embodiment, the face recognition model (240) can recognize faces in regions of interest and / or specific objects identified using the segmentation engine (210), depth heat map (220), and / or attention learning model (230). The faces can include not only human faces but also animal faces. The face recognition model (240) can identify the direction of gaze on the face.

[0070] In one embodiment, the instructions stored in the memory (130), when executed by at least one processor (110), may cause the electronic device (100) to recognize a face in a region of interest and / or a specific object identified using the facial recognition model (240) and / or to determine a direction of gaze from the face.

[0071] For example, a face recognition model (240) can identify the gaze through three types of position information: pitch, yaw, and roll of the face.

[0072] In one embodiment, the X and Y axes of the virtual camera (250) can be directed to a point where the Z axis of the line of sight of a face in 3D space intersects the Z axis at which the virtual camera (250) is positioned, thereby moving the position of the virtual camera (250) to a point in 3D space where the line of sight is directed, and the direction of the virtual camera (250) can be set to form a 90 degree angle with the X and Y axes of the line of sight, thereby making it look straight at the eyes of a specific object, and thus making the virtual camera (250) move in the direction in which the specific object is looking and then stare straight at the specific object. In this way, the face recognition model (240) can detect the line of sight of a specific object based on the position and direction of the virtual camera (250) looking straight at (or making eye contact with) a specific object (e.g., 410 of FIG. 4).

[0073] In one embodiment, the instructions stored in the memory (130), when executed by at least one processor (110), cause the electronic device (100) to move the position of the virtual camera (250) to a location where the gaze is looking in the 3D space by moving the X and Y axes of the virtual camera (250) to a point where the Z axis of the gaze that the face is looking at in the 3D space meets the Z axis at which the virtual camera (250) is located, and to set the direction of the virtual camera (250) to form a 90 degree angle with the X and Y axes of the gaze so that the virtual camera (250) can look straight at the eyes of a specific object, thereby moving the virtual camera (250) in the direction that the specific object is looking at to look straight at the specific object, thereby finding the gaze of a specific object (410) based on the position and direction of the virtual camera (250) facing the specific object.

[0074] In one embodiment, the virtual camera (250) can freely change its position or adjust its direction within the 3D modeling environment, and capture specific objects from various angles and / or viewpoints. The virtual camera (250) can zoom in or out on objects in the image through various lens effects, such as wide-angle, telephoto, and standard, just like a real camera within the 3D modeling environment. The virtual camera (250) can automatically track specific objects within the 3D modeling environment, or implement animations that move along preset paths. The virtual camera (250) can adjust the depth of field (DOF) within the 3D modeling environment to blur the background and focus on specific objects.

[0075] In one embodiment, the instructions stored in the memory (130), when executed by at least one processor (110), may cause the electronic device (100) to freely change position or adjust direction within a 3D modeling environment using the virtual camera (250) and to photograph a specific object from various angles or various viewpoints.

[0076] In one embodiment, the trajectory generation model (260) can identify a start point where the movement of the virtual camera (250) for generating a 3D image begins, an end point where the movement of the virtual camera (250) ends, and a passing point passing through the start point and the end point based on the direction of the gaze identified through the face recognition model (240).

[0077] In one embodiment, the trajectory generation model (260) can generate a movement trajectory of a virtual camera (250) based on a start point, an end point, and a passing point.

[0078] In one embodiment, the instructions stored in the memory (130), when executed by at least one processor (110), may cause the electronic device (100) to identify a start point where movement of a virtual camera (250) for generating a 3D image begins, an end point where movement of the virtual camera (250) ends, and a passing point passing through the start point and the end point based on a direction of the gaze identified using the trajectory generation model (260).

[0079] In one embodiment, the instructions stored in the memory (130), when executed by at least one processor (110), may cause the electronic device (100) to generate a movement trajectory of a virtual camera (250) based on a start point, an end point, and a passing point.

[0080] In one embodiment, a virtual camera (250) can generate 3D images by photographing a region of interest and / or a specific object along a movement trajectory of a 3D modeling environment.

[0081] In one embodiment, the instructions stored in the memory (130), when executed by at least one processor (110), may cause the electronic device (100) to generate a 3D image by photographing a region of interest and / or a specific object along a movement trajectory of a 3D modeling environment using a virtual camera (250).

[0082] Figure 3 is a flowchart illustrating a three-dimensional image display method according to one embodiment of the present invention.

[0083] According to one embodiment, in operation 301, instructions stored in memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify a specific object in an image.

[0084] In one embodiment, the image may include a photograph stored in memory (120) or a gallery application. The image may include a two-dimensional image. The electronic device (100) may acquire an image captured by a camera via an image sensor (150). The electronic device (100) may receive (e.g., download) the image via a communication circuit (150).

[0085] According to one embodiment, in operation 301, instructions stored in memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify a specific object in an image using at least one of a segmentation engine (210), a depth heat map (220), or an attention learning model (230).

[0086] In one embodiment, an image may contain a single specific object. However, this is not limited to the above, and an image may contain multiple specific objects.

[0087] According to one embodiment, in operation 301, instructions stored in memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify a plurality of specific objects in an image using at least one of a segmentation engine (210), a depth heat map (220), or an attention learning model (230).

[0088] In one embodiment, a particular object may include an animal or a person. However, this is not limited to the particular object, and a particular object may include an object.

[0089] According to one embodiment, in operation 303, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify at least one movement point of the virtual camera (250) based on a location of a specific object including an animal or a person. The movement point may include a point where the virtual camera (250) should capture a 3D image of the specific object in a 3D modeling environment. The movement point may include a start point and an end point. The movement point may include a start point, a passage point, and an end point. The passage point may include a plurality of passage points.

[0090] According to one embodiment, in operation 303, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to recognize a face in a specific object including an animal or person identified using the facial recognition model (240).

[0091] According to one embodiment, in operation 303, instructions stored in memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify a direction of gaze on a face using a facial recognition model (240).

[0092] According to one embodiment, in operation 303, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify a start point where movement of a virtual camera (250) for generating a 3D image begins, an end point where movement of the virtual camera (250) ends, and a passing point passing through the start point and the end point based on a direction of gaze identified through a facial recognition model (240).

[0093] In one embodiment, the starting point may include a gaze direction. The starting point may include a location that is at least a first specified distance away from a specific object. The ending point may include a location rotated 180 degrees from the starting point. The ending point may include a direction opposite to the gaze direction. The ending point may include a direction rotated 180 degrees relative to the gaze direction. The ending point may include a location that is at least a second specified distance away from a specific object. The ending point may include a direction opposite to the starting point with respect to the center point of the face.

[0094] In one embodiment, a pass-through point may include a location that is more than a third specified distance away from a particular object. The pass-through point may include a location midway between a start point and an end point.

[0095] According to one embodiment, if the specific object includes an animal or a person but does not include a face, or if the specific object is an object, in operation 303, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to determine at least one movement point of the virtual camera (250) based on the location of the specific object.

[0096] According to one embodiment, if a particular object includes an animal or a person but does not include a face, in operation 303, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify the center of the object as a starting point and the center of the image as an ending point.

[0097] According to one embodiment, if the specific object is a thing, in operation 303, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify a specific location in the left direction of the specific object as a starting point and to identify a specific location in the right direction of the specific object as an ending point. At this time, the passing point may include a location in the middle of the starting point and the ending point. However, the present invention is not limited thereto, and if the specific object is a thing, in operation 303, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify a specific location in the right direction of the specific object as a starting point and to identify a specific location in the left direction of the specific object as an ending point. If the specific object is a thing, in operation 303, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify a specific position in the upper direction of the specific object as a starting point and to identify a specific position in the lower direction of the specific object as an ending point. If the specific object is a thing, in operation 303, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify a specific position in the lower direction of the specific object as a starting point and to identify a specific position in the upper direction of the specific object as an ending point.

[0098] According to one embodiment, if the image includes a plurality of specific objects, in operation 303, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify a specific object located at the far left as a starting point and a specific object located at the far right as an ending point. In this case, the passing point may include a specific object located between the starting point and the ending point. However, the present invention is not limited thereto, and if the image includes a plurality of specific objects, in operation 303, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify a specific object located at the far right as a starting point and a specific object located at the far left as an ending point.

[0099] According to one embodiment, when a particular object is a thing, in operation 303, instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to display a user interface on the display (140) in which the position of a moving point can be changed by user input.

[0100] According to one embodiment, when a particular object is a thing, in operation 303, instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to display on the display (140) a user interface in which the order of movement points can be changed by user input.

[0101] According to one embodiment, when a specific object is a thing, in operation 303, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to display a user interface on the display (140) that allows the user to change the zoom in / out when taking a picture of a specific object from a moving point by user input.

[0102] According to one embodiment, in operation 305, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to determine a movement trajectory based on at least one movement point. The movement trajectory may include a trajectory along which the virtual camera (250) moves while photographing a specific object in a 3D modeling environment. The movement trajectory may include a direction in which the virtual camera (250) photographs the specific object in the 3D modeling environment. The direction in which the virtual camera (250) photographs the specific object in the 3D modeling environment may always be directed toward the specific object.

[0103] In one embodiment, a movement trajectory may include a trajectory that moves a movement point in a curve. The movement trajectory may include a start point, an end point, and a passing point. The movement trajectory may include a Bezier curve or a cardinal spline.

[0104] In one embodiment, the movement trajectory may include a trajectory that moves the movement point in a straight line. The movement trajectory may include a start point and an end point. For example, if a specific object includes an animal or a person but does not include a face, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify the center of the object as the start point and the center of the image as the end point. In this case, a passing point may not be identified, and the movement trajectory may be generated as a straight line.

[0105] In one embodiment, a virtual camera (250) that photographs a specific object along a movement trajectory may not end the photographing at the end point, but may cycle back to the start point and photograph the specific object in a circular manner according to the movement point.

[0106] In one embodiment, in operation 305, instructions stored in memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to make the movement time between movement points of the virtual camera (250) the same or linear.

[0107] In one embodiment, in operation 305, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to differentially distribute the movement time between movement points of the virtual camera (250). For example, the movement time of the virtual camera (250) between a start point and a passing point may be longer than the movement time of the virtual camera (250) between a passing point and an end point.

[0108] According to one embodiment, in operation 307, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to capture an image based on the movement trajectory. The image captured based on the movement trajectory may include at least one of a 3D image or a 2D image. According to one embodiment, in operation 307, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to capture a 3D image based on the movement trajectory.

[0109] According to one embodiment, when capturing a 3D image based on a movement trajectory, in operation 307, instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to capture an image of a specific object while moving the virtual camera (250) based on the movement trajectory.

[0110] According to one embodiment, when moving a virtual camera (250) based on a movement trajectory and taking a picture of a specific object, in operation 307, instructions stored in the memory (120) can cause the electronic device (100) to zoom in or out and take a picture of a specific object based on a movement point when individually or collectively executed by at least one processor (110).

[0111] For example, if the specific object includes a face, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to cause the virtual camera (250) to zoom in and photograph the specific object from a starting point. If the specific object includes a face, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to cause the virtual camera (250) to zoom in and photograph the specific object from a passing point. If the specific object includes a face, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to cause the virtual camera (250) to zoom in and photograph the specific object from a ending point.

[0112] For example, if the specific object does not include a face or if the specific object is an object, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to cause the virtual camera (250) to zoom in and photograph the specific object from a starting point. If the specific object includes a face, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to cause the virtual camera (250) to zoom in and photograph the specific object from an ending point.

[0113] According to one embodiment, in operation 309, instructions stored in memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to display a 3D image on a display (140) or store the image in memory (130).

[0114] FIG. 4 is a diagram illustrating a method by which an electronic device (100) recognizes a specific object (410) in an image (400) according to one embodiment of the present disclosure.

[0115] In one embodiment, screen 401 is a diagram illustrating a method for recognizing a specific object (410) in an image (400) using a segmentation engine (210). Referring to screen 401, the segmentation engine (210) can perform segmentation on the image (400). The electronic device (100) can recognize and classify a specific object (410) (e.g., a cat) in the image (400) using the segmentation engine (210). The electronic device (100) can identify a boundary of a specific object (410) included in the image (400) and recognize the specific object (410) using the segmentation engine (210).

[0116] In one embodiment, a particular object (410) may include a region of interest. The particular object (410) or region of interest may include an area or object that the user wishes to capture in a 3D image.

[0117] FIG. 5 is a diagram illustrating a method by which an electronic device (100) recognizes a specific object (410) in an image (400) according to one embodiment of the present disclosure.

[0118] In one embodiment, screens 501, 503, and 505 are diagrams illustrating a method for recognizing a specific object (410) in an image (400) using a depth heat map (220).

[0119] In screen 501, a depth heat map (220) can represent the depth of an object (410) (e.g., a cat) using the color of each pixel in the image (400).

[0120] On screen 503, the depth heat map (220) can infer and find the perspective of a 2D image, and convert objects included in the 2D image into a 3D mesh based on the depth information.

[0121] In screen 505, the depth heat map (220) separates the foreground and background layers from the image (400) based on the part with the greatest change in the Z coordinate in the transformed 3D space, and the layer separated as the foreground can be identified as a specific object (410).

[0122] FIG. 6 is a diagram illustrating a method by which an electronic device (100) recognizes a specific object (410) in an image (400) according to one embodiment of the present disclosure.

[0123] In one embodiment, screen 601 is a diagram illustrating a method for recognizing a specific object (410) in an image (400) using an attention learning model (230).

[0124] In screen 601, the attention learning model (230) can evaluate the likelihood that each pixel in the image (400) will be noticed. Based on the evaluation of the likelihood of being noticed, the attention learning model (230) can identify an area corresponding to a specific score or higher as a specific object (410) (e.g., a cat).

[0125] FIG. 7 is a diagram illustrating a method by which an electronic device (100) according to one embodiment of the present disclosure recognizes a face of a specific object (410) in an image (400) and finds a gaze.

[0126] FIG. 8 is a diagram illustrating a method by which an electronic device (100) according to one embodiment of the present disclosure recognizes a face of a specific object (410) in an image (400) and finds a gaze.

[0127] Referring to FIG. 7, the electronic device (100) can identify three pieces of position information (710) regarding the pitch, yaw, and roll of the face of a specific object (410) using a face recognition model (240). The electronic device (100) can identify gaze information (720) or gaze (720) based on the three pieces of position information (710) regarding the face of a specific object (410).

[0128] Referring to FIG. 8, the electronic device (100) can move the virtual camera (250) from the default position (801) to the point where the Z axis of the line of sight of the face in 3D space meets the Z axis of the virtual camera (250) based on three pieces of location information (710), thereby moving the virtual camera (250) to the position (802) of the virtual camera (250) to the place where the line of sight is looking in 3D space. The electronic device (100) can enable the eyes of a specific object (410) to be looked straight ahead by setting the angle (830) (approximately: 90 degrees) of the virtual camera (250) to form a 90 degree angle with the X and Y axes of the line of sight. The electronic device (100) can move the virtual camera (250) in the direction in which a specific object (410) is looking so that the virtual camera (250) looks directly at the specific object (410), thereby finding the gaze of the specific object (410) based on the position and direction of the virtual camera (250) facing (eye contact) the specific object (410).

[0129] In one embodiment, the electronic device (100) may find the gaze of a specific object (410) to confirm the starting point (e.g., 802) of the movement trajectory of the virtual camera (250) when generating an image of the specific object (410) using the virtual camera (250). For example, since the virtual camera (250) may move and zoom in the direction in which it makes eye contact with a person or animal included in the image, natural presentation of the movement of the person or animal in the 3D image generated by the electronic device (100) may be possible. In addition, since the virtual camera (250) may move and zoom in the direction in which it makes eye contact with a person or animal included in the image, the direction in which the person or animal is looking in the 3D image generated by the electronic device (100) may also include information about a region of interest and / or a specific object (410) included in the image. Therefore, when a movement trajectory of a virtual camera (250) is generated by focusing on the gaze of a specific object (410) included in an image, a high level of user satisfaction with the 3D image generated by the electronic device (100) can be provided.

[0130] FIG. 9 is a diagram illustrating a method for an electronic device (100) according to one embodiment of the present disclosure to identify a start point (910) and an end point (920).

[0131] FIG. 10 is a diagram illustrating a method for an electronic device (100) to identify a starting point (910) according to one embodiment of the present disclosure.

[0132] FIG. 11 is a diagram illustrating a method for an electronic device (100) to identify an end point (920) according to one embodiment of the present disclosure.

[0133] FIG. 9 is a drawing showing a start point (910) and an end point (920) on a 2D image, and FIGS. 10 and 11 are drawings showing the start point (910) and end point (920) of FIG. 9 in a 3D modeling environment.

[0134] Referring to FIGS. 9, 10, and 11, a start point (910) may include a position at which a video of a specific object (410) included in an image (400) begins to be captured using a virtual camera (250). An end point (920) may include a position at which a video of a specific object (410) included in an image (400) ends to be captured using a virtual camera (250).

[0135] FIG. 9, FIG. 10 and FIG. 11 are drawings for sequentially explaining a method for an electronic device (100) according to one embodiment of the present disclosure to identify a start point (910) and an end point (920) centered on a specific object (410) included in an image (400).

[0136] Referring to FIGS. 9, 10, and 11, a starting point (910) may include a direction of a gaze of a specific object (410). The starting point (910) may include a location that is spaced apart from the specific object (410) by a specific distance (D1). The ending point (920) may include a location that is rotated 180 degrees from the starting point (910). The ending point (920) may include a direction opposite to the direction of the gaze of the specific object (410). The ending point (920) may include a direction that is rotated 180 degrees relative to the direction of the gaze of the specific object (410). The ending point (920) may include a location that is spaced apart from the specific object by a specific distance (D2). The ending point (920) may include an opposite direction of the starting point (910) with respect to the center point (901) of the face.

[0137] In one embodiment, the starting point (910) and the ending point (920) may be spaced apart from the center point (901) by a specific distance (D1, D2), respectively. In one embodiment, the starting point (910) may include a gaze direction. The starting point may include a location spaced apart from a specific object (410) (or the center point (901) of the specific object (410)) by a specific distance (D1).

[0138] In one embodiment, the end point (920) may include a position rotated 180 degrees from the start point (910). The end point (920) may include a direction opposite to the direction of the gaze. The end point (920) may include a direction rotated 180 degrees from the direction of the gaze. The end point (920) may include a position spaced apart from a specific object (410) (or a center point (901) of the specific object (410)) by a specific distance (D2). The end point (920) may include a direction opposite to the start point (910) with respect to the center point (901) of the face.

[0139] FIGS. 9, 10, and 11 illustrate a method for an electronic device (100) to identify a start point (910) and an end point (920) based on a case where a specific object (410) included in an image (400) includes a face and a viewpoint. However, if a specific object (410) included in an image (400) includes a face but viewpoint analysis is impossible or difficult, for example, if a face image included in the specific object (410) is small or a side view, instructions stored in a memory (120) can cause the electronic device (100) to identify a start point (910) and an end point (920) centered on the face regardless of the gaze when individually or collectively executed by at least one processor (110).

[0140] For example, if a specific object (410) included in an image (400) includes a face but viewpoint analysis is impossible or difficult, instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), can cause the electronic device (100) to set the center of the face as the center point (901), identify a specific point in the left direction from the center point (901) as the start point (910), and identify a specific point in the right direction from the center point (901) as the end point (920).

[0141] However, it is not limited thereto, and when a specific object (410) included in an image (400) includes a face but viewpoint analysis is impossible or difficult, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), can cause the electronic device (100) to set the center of the face as the center point (901), identify a specific point in the right direction from the center point (901) as the start point (910), and identify a specific point in the left direction from the center point (901) as the end point (920).

[0142] Additionally, a case in which a specific object (410) included in an image (400) does not include a face can be explained with reference to FIG. 13 described below.

[0143] FIG. 12 is a diagram illustrating a method for an electronic device (100) according to one embodiment of the present disclosure to identify a passing point (1210) based on a start point (910) and an end point (920).

[0144] Screen 1201 is a drawing showing a passing point (1210) on a 2D image, and screen 1203 is a drawing showing a passing point (1210) in a 3D modeling environment.

[0145] Referring to screen 1201, a pass point (1210) may include an intermediate position between a start point (910) and an end point (920) on the X, Y coordinates of a 2D coordinate system.

[0146] Referring to screen 1203, in order to prevent the virtual camera (250) in a 3D modeling environment from penetrating and shooting a specific object (410) included in an image (400), the electronic device (100) can, under the control of at least one processor (110), identify a passing point (1210) at a location spaced apart by a specific distance (D3) from the Z coordinate of the specific object (410).

[0147] Referring to screen 1203, in order to prevent the virtual camera (250) in a 3D modeling environment from penetrating and shooting a specific object (410) included in an image (400), the electronic device (100), under the control of at least one processor (110), can identify a point where a path (1211) connecting a start point (910) and an end point (920) does not pass through a specific object (410), as a passing point (1210).

[0148] In one embodiment, in a 3D modeling environment, a specific object (410) may be located at a position (1211) having the largest Z coordinate value, and the electronic device (100), under the control of at least one processor (110), may identify a position that is a specific distance (D3) away from the position (1212) having the largest Z coordinate of the specific object (410) as a passing point (1210). When capturing a 3D image, the virtual camera (250) may move while looking at the specific object (410) from the passing point (1210).

[0149] In one embodiment, the movement point and movement trajectory are trajectories or flight paths along which the virtual camera (250) moves within the image, and the electronic device (100) generates a virtual path to provide the user with an effect as if the virtual camera (250) is moving while looking at a specific object, and verifies the start point, end point, and / or passing point of the virtual path and the movement trajectory, and provides the user with a scene as if the virtual camera (250) is moving and filming along the movement point and movement trajectory.

[0150] In one embodiment, a specific object in 3D space can be moved to view the object by using the virtual camera (250) as a passing point at the location where the value of the Z-axis coordinate is the largest.

[0151] FIG. 13 is a diagram illustrating a method for an electronic device (100) to identify a start point (1330) and an end point (1320) when a specific object (1310) does not include a face according to one embodiment of the present disclosure.

[0152] In FIG. 12, a specific object (410) (e.g., a cat) contains a face, but in FIG. 13, a specific object (1310) (e.g., a person) does not contain a face.

[0153] Referring to FIG. 13, if a specific object (1310) includes an animal or a person but does not include a face, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify the center of the specific object (1310) as a starting point (1330) and the center of the image as an ending point (1320). The passing point (not shown) may include a position intermediate the starting point (1330) and the ending point (1320).

[0154] In one embodiment, if a particular object (1310) includes an animal or a person but does not include a face, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify the center of the particular object (1310) as a start point (1330) and the center of the image as an end point (1320) without separately identifying a center point or a passing point.

[0155] In one embodiment, if a specific object (1310) includes an animal or a person but does not include a face, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to capture a 3D image using the virtual camera (250) by zooming in on the specific object (1310) from a starting point (1330) and gradually zooming out on the specific object (1310) as the virtual camera (250) moves toward an ending point (1320).

[0156] However, it is not limited thereto, and if a specific object (1310) includes an animal or a person but does not include a face, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to capture a 3D image using the virtual camera (250) by zooming in on the specific object (1310) from the start point (1330) and gradually enlarging the specific object (1310) as the virtual camera (250) moves to the end point (1320).

[0157] FIG. 14 is a diagram illustrating a case in which a plurality of specific objects (1410, 1420, 1430, 1440) are included in an image (1400) according to one embodiment of the present disclosure.

[0158] FIG. 14 illustrates an image (1400) according to one embodiment of the present disclosure, wherein each of a plurality of specific objects (1410, 1420, 1430, 1440) included therein may include a face.

[0159] Referring to FIG. 14, when a plurality of specific objects (1410, 1420, 1430, 1440) are included in an image (1400), instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify the specific object (1410) located at the far left as a starting point and the specific object (1440) located at the far right as an ending point. At this time, the passing points may include specific objects (1420, 1430) located between the starting point and the ending point. However, this is not limited thereto, and if the image includes a plurality of specific objects, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify the specific object (1440) on the far right as a starting point and the specific object (1410) on the far left as an ending point.

[0160] In one embodiment, when the image (1400) includes a plurality of specific objects (1410, 1420, 1430, 1440), the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify the center point (1411) of the leftmost specific object (1410) as a starting point and to identify the center point (1441) of the rightmost specific object (1440) as an ending point. In this case, the passing points may include the center points (1421, 1431) of the specific objects (1420, 1430) located between the starting point and the ending point. However, this is not limited thereto, and if the image includes a plurality of specific objects, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify the specific object (1440) on the far right as a starting point and the specific object (1410) on the far left as an ending point.

[0161] In one embodiment, when multiple passing points (e.g., 1420, 1430) are generated, the length of the path along which the virtual camera (250) for generating a 3D image moves may become longer. When the length of the path along which the virtual camera (250) for generating a 3D image moves becomes longer, the playback time of the entire 3D image may also increase. When multiple passing points (e.g., 1420, 1430) are generated, in order to shorten the playback time of the 3D image, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may compensate the movement time of the virtual camera (250) for capturing a 3D image so as to correspond to the time for capturing a 3D image for a single specific object by causing the electronic device (100) to capture the 3D image.

[0162] FIG. 15 is a diagram illustrating a case in which a plurality of specific objects (1510, 1520, 1530, 1540) are included in an image (1500) according to one embodiment of the present disclosure.

[0163] Each of the plurality of specific objects (1410, 1420, 1430, 1440) included in the image (1400) of FIG. 14 includes a face, but at least some of the plurality of specific objects (1510, 1520, 1530, 1540) may include objects that do not include faces. For example, in the image (1500), only a specific object (1530) may include a face, and the remaining specific objects (1510, 1520, 1540) may be objects or may not include faces.

[0164] Referring to FIG. 15, when a plurality of specific objects (1510, 1520, 1530, 1540) are included in an image (1500), instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify the specific object (1510) located at the far left as a starting point and the specific object (1540) located at the far right as an ending point. At this time, the passing points may include specific objects (1520, 1530) located between the starting point and the ending point. However, this is not limited thereto, and if the image includes a plurality of specific objects, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify the specific object (1540) on the far right as a starting point and the specific object (1510) on the far left as an ending point.

[0165] In one embodiment, when the image (1400) includes a plurality of specific objects (1510, 1520, 1530, 1540), the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify the center point (1511) of the leftmost specific object (1510) as a starting point and to identify the center point (1541) of the rightmost specific object (1540) as an ending point. In this case, the passing points may include the center points (1521, 1531) of the specific objects (1520, 1530) located between the starting point and the ending point. However, this is not limited thereto, and if the image includes a plurality of specific objects, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify the specific object (1540) on the far right as a starting point and the specific object (1510) on the far left as an ending point.

[0166] In one embodiment, when multiple passing points (e.g., 1520, 1530) are generated, the length of the path along which the virtual camera (250) for generating a 3D image moves may become longer. When the length of the path along which the virtual camera (250) for generating a 3D image moves becomes longer, the playback time of the entire 3D image may also increase. When multiple passing points (e.g., 1520, 1530) are generated, in order to shorten the playback time of the 3D image, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may compensate the movement time of the virtual camera (250) for capturing a 3D image so as to correspond to the time for capturing a 3D image for a single specific object by the electronic device (100).

[0167] FIG. 16 is a diagram illustrating a method for an electronic device (100) according to one embodiment of the present disclosure to confirm a movement trajectory (1610).

[0168] According to one embodiment, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify a movement trajectory (1610) based on at least one movement point (910, 920, 1210). The movement trajectory (1610) may include a trajectory along which the virtual camera (250) moves while photographing a specific object (410) in a 3D modeling environment. The movement trajectory (1610) may include a direction in which the virtual camera (250) photographs the specific object in the 3D modeling environment. The direction in which the virtual camera (250) photographs the specific object in the 3D modeling environment may always be directed toward the specific object.

[0169] In one embodiment, the movement trajectory (1610) may include a trajectory that moves along a curve through at least one movement point (910, 920, 1210). The movement trajectory (1610) may include a start point (910), an end point (920), and a passing point (1210). The movement trajectory (1610) may include a Bezier curve or a Cardinal Spline.

[0170] In one embodiment, the movement trajectory (1610) of the virtual camera (250) also draws a complex movement path when a number of complex passing points are generated. When a Bezier Curve or Cardinal Spline is used, the movement can include all movement points, and since natural movement is possible by moving in a curve between movement points, the Bezier Curve or Cardinal Spline can be included.

[0171] In one embodiment, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to move the virtual camera (250) around a specific object (410) by drawing a curve (e.g., a movement trajectory (1610)) along X, Y, Z coordinates when capturing a 3D image.

[0172] In one embodiment, the movement trajectory (1610) may include a trajectory that moves the movement point in a straight line. The movement trajectory (1610) may include a start point (910) and an end point (920). For example, if a specific object includes an animal or a person but does not include a face, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify the center of the object as the start point and the center of the image as the end point. In this case, a passing point is not identified, and the movement trajectory may be generated as a straight line.

[0173] FIG. 17 is a diagram illustrating a method for an electronic device (100) to identify movement trajectories (1751, 1752, 1753, 1754) when a plurality of specific objects (1710, 1720, 1730, 1740) are included in an image (1700) according to one embodiment of the present disclosure.

[0174] In one embodiment, when the image (1700) includes a plurality of specific objects (1710, 1720, 1730, 1740), the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to identify the leftmost specific object (1710) as a starting point (1711) and the rightmost specific object (1740) as an ending point (1741). In this case, the passing points (1721, 1731) may include specific objects (1720, 1730) located between the starting point (1711) and the ending point (1711).

[0175] In one embodiment, the movement trajectories (1751, 1752, 1753, 1754) may include a trajectory that moves along a curve through at least one movement point (1711, 1721, 1731, 1741). The movement trajectories (1751, 1752, 1753, 1754) may include a start point (1711), an end point (1741), and passing points (1721, 1731). The movement trajectories (1751, 1752, 1753, 1754) may include curves or straight lines.

[0176] In one embodiment, the generation of a movement trajectory (e.g., a curve) may be limited to cases where the number of movement points is greater than or equal to a certain number. For example, only when there are at least three movement points, instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to generate a movement trajectory including a curve using the movement points.

[0177] In one embodiment, the movement path may be a straight line, as the specific object is a single image without facial information and has only two movement points. In this case, zooming in and out techniques can be used to capture the specific object.

[0178] FIG. 18 is a diagram showing viewpoints (1821, 1822, 1823, 1824, 1825) of a virtual camera (250) when an electronic device (100) according to one embodiment of the present disclosure captures a specific object (410) of an image (400) along a movement trajectory (1810).

[0179] In one embodiment, the movement trajectory (1810) may include points in time (1821, 1822, 1823, 1824, 1825) when the virtual camera (250) photographs a specific object (410) in a 3D modeling environment. Points in time (1821, 1822, 1823, 1824, 1825) when the virtual camera (250) photographs a specific object (410) in a 3D modeling environment may always be directed toward the specific object (410).

[0180] In one embodiment, the movement trajectory (1810) may include directions (1821, 1822, 1823, 1824, 1825) in which the virtual camera (250) photographs a specific object (410) in a 3D modeling environment. The directions (1821, 1822, 1823, 1824, 1825) in which the virtual camera (250) photographs a specific object (410) in the 3D modeling environment may be fixed to always face the specific object (410).

[0181] In one embodiment, after the movement trajectory (1810) is generated, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), can cause the electronic device (100) to control the viewpoint or viewpoint direction that the virtual camera (250) views. If the virtual camera (250) moves with the viewpoint or viewpoint direction fixed in one direction rather than facing the object, the virtual camera (250) can capture the outer part of the image as a 3D video. Accordingly, the viewpoint or viewpoint direction of the virtual camera (250) can be adjusted to be centered on a specific object (410).

[0182] For example, a movement trajectory (1810) may include a starting point (1811), a first passing point (1812), a second passing point (1813), a third passing point (1814), and an ending point (1815). When moving from the starting point (1811) to the first passing point (1812), the viewpoint direction of the virtual camera (250) is directed toward the first passing point (1812), and when passing the first passing point (1812) and moving to the second point (1813), the viewpoint direction of the virtual camera (250) may also change to target the second point (1813).

[0183] In one embodiment, when an image includes a plurality of specific objects, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to set the viewpoint direction of the virtual camera (250) so that when moving between specific objects, the viewpoint direction of the virtual camera (250) looks at the next moving point (e.g., a passing point).

[0184] In one embodiment, even if an image includes multiple specific objects, the start and end points can exist within the image, just as if the image includes one specific object. Accordingly, the viewpoint of the virtual camera (250) can be controlled to look at each specific object. If the virtual camera (250) moves while keeping the viewpoint or viewpoint direction fixed in one direction rather than facing the object, the virtual camera (250) can capture the outer part of the image as a 3D image. Accordingly, the viewpoint or viewpoint direction of the virtual camera (250) can be adjusted to center each specific object corresponding to the moving point.

[0185] FIG. 19 is a diagram schematically showing the movement time of a virtual camera (250) between moving points according to one embodiment of the present disclosure.

[0186] In one embodiment, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to make the movement times between movement points (1911, 1912, 1913, 1914, 1915) of the virtual camera (250) the same or linear.

[0187] In one embodiment, instructions stored in memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to differentially distribute movement times between movement points (1911, 1912, 1913, 1914, 1915) of the virtual camera (250).

[0188] In one embodiment, after the movement trajectory and viewpoint of the virtual camera (250) are generated, by controlling the time interval between movement points of the virtual camera (250), the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), can cause the electronic device (100) to generate a 3D image by giving a slow or fast effect to the generated image.

[0189] For example, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), cause the electronic device (100) to cause the movement time of the virtual camera (250) between the starting point (1911) and the first passing point (1912) to be 0.05 (unit, e.g., second), the movement time of the virtual camera (250) between the first passing point (1912) and the second passing point (1913) to be 0.5 (unit, e.g., second), the movement time of the virtual camera (250) between the second passing point (1913) and the third passing point (1914) to be 0.52 (unit, e.g., second), the movement time of the virtual camera (250) between the third passing point (1914) and the end point (1915) to be 0.92 (unit, e.g., second), and the start at the end point (1915) The movement time of the virtual camera (250) between points (1911) can be distributed as 1 (unit, e.g., second). At this time, when the electronic device (100) captures a 3D image of a specific object, the 3D image can include a fast or slow effect due to the time difference in moving to each moving point. When the electronic device (100) captures a 3D image of a specific object, the 3D image can include a glambot shooting effect due to the time difference in moving to each moving point.

[0190] FIG. 20 is a drawing showing a method of capturing a 3D image by applying a glambot shooting effect to a specific object (2100) included in an image (2000) by an electronic device (100) according to one embodiment of the present disclosure.

[0191] In one embodiment, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to capture a 3D image by having the virtual camera (250) first capture the entire screen (2200) and then capture a specific object (2100) while moving in the following order: a start point (2010), a first pass point (2020), a second pass point (2030), a third pass point (2040), and an end point (2050). At this time, the zoom size for a specific object (2100) can be determined in the order of the full screen (2200), starting point (2010), first passing point (2020), second passing point (2030), third passing point (2040), and end point (2050), and the zoom size can be gradually reduced in the order of the full screen (2200), starting point (2010), first passing point (2020), second passing point (2030), third passing point (2040), and end point (2050) to capture the specific object (2100).

[0192] For example, a glambot shooting effect can quickly zoom in on a specific object (2100) from a remote location (e.g., full screen (2200)) around the face (2300) of the specific object (2100), approach in a curved manner, and then move the virtual camera (250) in slow motion to film the scene by increasing the movement time between moving points (e.g., the first passing point (2020) and the second passing point (2030)) near the face of the specific object (2100), and then move the virtual camera (250) to an end point (2050) after another zoom-in approach between moving points (e.g., the second passing point (2030) and the third passing point (2040)) to highlight the specific object (2100) (e.g., the face).

[0193] In one embodiment, to implement a glambot shooting effect, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to recognize an object (2100) included in an image (2000) by distinguishing it into a first specific object (e.g., a face), a second specific object (e.g., an upper body), and a third specific object (e.g., a full body).

[0194] In one embodiment, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to capture a 3D image in slow motion by slowing down the movement time of the virtual camera (250) between movement points while moving from a specific object of low importance (e.g., a third specific object) to a specific object of high importance (e.g., a first specific object).

[0195] In one embodiment, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to move the virtual camera (250) from a movement point corresponding to a third specific object (e.g., a full body) (e.g., a full screen (2200)) to a movement point corresponding to a second specific object (e.g., an upper body) (e.g., a starting point (2010), a first passing point (2020)), and then move the virtual camera (250) from a movement point corresponding to the second specific object (e.g., an upper body) (e.g., a starting point (2010), a first passing point (2020)) to a movement point corresponding to a first specific object (e.g., a face) (e.g., a second passing point (2030)) to capture a 3D image.

[0196] In one embodiment, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to capture a 3D image including a slow motion effect by lengthening the movement time of the virtual camera (250) when moving to the most important object (e.g., a first specific object).

[0197] In one embodiment, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to designate important objects and capture a 3D image including a slow motion effect on the most important object. The electronic device (100) of the present invention may capture a 3D image to which various shooting effects, such as a glambot shooting effect, zoom-in, fast motion, and tilt roll, are applied corresponding to various objects according to a method of selecting the priority of important objects in an image, such as animals, objects, and landscapes.

[0198] FIG. 21 is a diagram illustrating a user interface in which the position movement and zoom effect of a moving point can be changed according to user input according to one embodiment of the present disclosure.

[0199] According to one embodiment, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to display a user interface (2110) on the display (140) regarding position change that allows the position of the moving point to be changed by user input (2500).

[0200] According to one embodiment, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to display a user interface (2110) on the display (140) regarding position changes in which the order of movement points can be changed by user input.

[0201] In one embodiment, a user interface (2110) for changing positions may correspond to a starting point (2010), a first passing point (2020), a second passing point (2030), a third passing point (2040), and an end point (2050) of FIGS. 20 and 21. A user interface (2110) for changing positions may include a starting point (2010), a first passing point (2020), a second passing point (2030), a third passing point (2040), and an end point (2050) of FIGS. 20 and 21.

[0202] According to one embodiment, the instructions stored in the memory (120), when individually or collectively executed by at least one processor (110), may cause the electronic device (100) to display a user interface (2120) regarding zoom, in which the zoom is changed when capturing a specific object from a moving point by a user input, on the display (140). The user input that can change the size of the user interface (2120) regarding zoom may include a pinch zoom in / out or a press input.

[0203] The size (e.g., the size of a circle) of a user interface (2120) regarding zoom may be changed by a user input (2500). When the electronic device (100) captures a 3D image of a specific object (2100) using a virtual camera (250), the electronic device (100) may capture the image by enlarging it in proportion to the size of the user interface (2120) regarding zoom. The user interface (2120) regarding zoom may correspond to the starting point (2010), the first passing point (2020), the second passing point (2030), the third passing point (2040), and the end point (2050) of FIGS. 20 and 21. A user interface (2120) for zoom may include a start point (2010), a first pass point (2020), a second pass point (2030), a third pass point (2040), and an end point (2050) of FIGS. 20 and 21.

[0204] In one embodiment, the electronic device (100) includes a display (140), at least one processor (110), and a memory (120) storing instructions, which, when individually or collectively executed by the processor (110), may cause the electronic device (100) to identify a specific object in an image, identify at least one movement point of a virtual camera (250) based on a location of the specific object, identify a movement trajectory based on the at least one movement point, capture an image based on the movement trajectory, and display the image on the display (140) or store the image in the memory (120).

[0205] In one embodiment, the image comprises a three-dimensional (3D) image, and the instructions, when executed by the processor (110), may cause the electronic device (100) to identify a specific object in the image using at least one of a segmentation engine (210), a depth heat map (220), or an attention learning model (230).

[0206] In one embodiment, the instructions, when individually or collectively executed by the processor (110), may cause the electronic device (100) to identify a face and gaze in a particular object.

[0207] In one embodiment, the instructions, when individually or collectively executed by the processor (110), may cause the electronic device (100) to identify at least one movement point, including a start point, an end point, and a pass point, based on a face and gaze identified in a particular object.

[0208] In one embodiment, the instructions, when individually or collectively executed by the processor (110), may cause the electronic device (100) to identify a midpoint between a start point and an end point as a passing point.

[0209] In one embodiment, the instructions, when individually or collectively executed by the processor (110), may cause the electronic device (100) to generate a motion trajectory that draws a curved trajectory in 3D space for an image and passes through a start point, an end point, and a pass point.

[0210] In one embodiment, the instructions, when individually or collectively executed by the processor (110), may cause the electronic device (100) to generate a curve trajectory based on a Bezier curve or a Cardinal Spline.

[0211] In one embodiment, the instructions, when individually or collectively executed by the processor (110), may cause the electronic device (100) to move the virtual camera (250) along a movement trajectory while fixing the direction of the virtual camera (250) toward a particular object.

[0212] In one embodiment, the instructions, when executed individually or collectively by the processor (110), may cause the electronic device (100) to photograph a particular object in 3D space along a movement trajectory, varying the photographing time for each starting point, ending point, and passing point.

[0213] In one embodiment, the instructions, when individually or collectively executed by the processor (110), may cause the electronic device (100) to identify a plurality of pass points based on a plurality of objects in the image.

[0214] In one embodiment, a method for displaying a 3D image of an electronic device (100) may include an operation of identifying a specific object in an image, an operation of identifying at least one movement point of a virtual camera (250) based on a location of the specific object, an operation of identifying a movement trajectory based on at least one movement point, an operation of capturing an image based on the movement trajectory, and an operation of displaying the image on a display (140) or storing the image in a memory (120).

[0215] In one embodiment, the image includes a three-dimensional (3D) image, and in one embodiment, the method for displaying a 3D image of the electronic device (100) may further include an operation of identifying a specific object in the image using at least one of a segmentation engine (210), a depth heat map (220), or an attention learning model (230).

[0216] In one embodiment, the method for displaying a 3D image of an electronic device (100) may further include an operation of identifying a face and gaze in a specific object.

[0217] In one embodiment, the method for displaying a 3D image of an electronic device (100) may further include an operation of identifying at least one movement point including a start point, an end point, and a passing point based on a face and gaze identified in a specific object.

[0218] In one embodiment, the method for displaying a 3D image of an electronic device (100) may further include an operation of identifying a midpoint between a start point and an end point as a passing point.

[0219] In one embodiment, the method for displaying a 3D image of an electronic device (100) may further include an operation of generating a movement trajectory that draws a curve trajectory in a 3D space for the image and passes through a start point, an end point, and a passing point.

[0220] In one embodiment, the method for displaying a 3D image of an electronic device (100) may further include an operation of generating a curve trajectory based on a Bezier curve or a Cardinal Spline.

[0221] In one embodiment, a method of displaying a 3D image of an electronic device (100) may include an operation of moving a virtual camera (250) along a movement trajectory while fixing the direction of the virtual camera (250) toward a specific object.

[0222] In one embodiment, the method for displaying a 3D image of an electronic device (100) may further include an operation of varying the shooting time for each starting point, ending point, and passing point when shooting a specific object in 3D space according to a movement trajectory.

[0223] In one embodiment, the method for displaying a 3D image of an electronic device (100) may further include an operation of confirming a plurality of passing points based on a plurality of objects when there are a plurality of objects in the image.

[0224] An electronic device according to an embodiment disclosed in this document may take various forms. The electronic device may include, for example, a portable communication device (e.g., a smartphone), a computer device, a portable multimedia device, a portable medical device, a camera, a wearable device, or a home appliance. The electronic device according to an embodiment of this document is not limited to the aforementioned devices.

[0225] It should be understood that the embodiments of this document and the terminology used herein are not intended to limit the technical features described in this document to specific embodiments, but include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of the items, unless the context clearly indicates otherwise. In this document, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" can include any one of the items listed together in the corresponding phrase among those phrases, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish one component from another, and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as "coupled" or "connected" to another (e.g., a second component), with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0226] The term "module" used in one embodiment of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integral component, or a minimum unit or part of such a component that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0227] An embodiment of the present document may be implemented as software (e.g., a program) including one or more instructions stored in a storage medium (e.g., built-in memory or external memory) readable by a machine (e.g., an electronic device (100)). For example, a processor (e.g., processor (110)) of the machine (e.g., electronic device (100)) may call at least one instruction among the one or more instructions stored from the storage medium and execute it. This enables the machine to operate to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' simply means that the storage medium is a tangible device and does not contain signals (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently or temporarily on the storage medium.

[0228] According to one embodiment, the method according to one embodiment disclosed in the present document may be provided as a computer program product. The computer program product may be traded between sellers and buyers as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or may be provided through an application store (e.g., Play Store). TM ) or directly between two user devices (e.g., smart phones), online distribution (e.g., downloading or uploading). In the case of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily created in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0229] According to one embodiment, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separated and placed in other components. According to one embodiment, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to one embodiment, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

Claims

1. In an electronic device (100), display (140); At least one processor (110); and It includes at least one memory (120) for storing instructions, The above instructions, when individually or collectively executed by the processor (110), cause the electronic device (100) to: Identify specific objects in an image, At least one movement point of the virtual camera (250) is identified based on the location of the specific object, Check the movement trajectory based on at least one of the above movement points, To take a video based on the above movement trajectory, An electronic device that displays the image on the display (140) and / or stores the image in at least one memory (120).

2. In paragraph 1, The above image includes a 3D (three-dimensional) image, The above instructions, when executed by the at least one processor (110), cause the electronic device (100) to: An electronic device that identifies a specific object in the image using at least one of a segmentation engine (210), a depth heat map (220), or an attention learning model (230).

3. In paragraph 1, The above instructions, when individually or collectively executed by the at least one processor (110), cause the electronic device (100) to: An electronic device that identifies at least one face or gaze in the above specific object.

4. In paragraph 3, The above instructions, when individually or collectively executed by the at least one processor (110), cause the electronic device (100) to: An electronic device that identifies at least one movement point including a start point, an end point, and a passing point based on at least one face or gaze identified in the specific object.

5. In paragraph 4, The above instructions, when individually or collectively executed by the at least one processor (110), cause the electronic device (100) to: An electronic device that identifies the midpoint between the above starting point and the above ending point as the above passing point.

6. In paragraph 4, The above instructions, when individually or collectively executed by the at least one processor (110), cause the electronic device (100) to: In the 3D space for the above image, a curve trajectory is drawn and a movement trajectory is generated that passes through the start point, the end point, and the passing point, Generate the above curve trajectory based on a Bezier Curve or Cardinal Spline, While moving the virtual camera (250) along the above movement trajectory, the direction of the virtual camera (250) is directed toward the specific object, An electronic device that, when photographing the specific object in the 3D space according to the movement trajectory, sets different photographing times for each of the starting point, the ending point, and the passing point.

7. In paragraph 3, The above instructions, when individually or collectively executed by the at least one processor (110), cause the electronic device (100) to: An electronic device that identifies multiple passing points based on the multiple objects in the image.

8. In the method of displaying a 3D image of an electronic device (100) The action of identifying a specific object in an image; An action of identifying at least one movement point of a virtual camera (250) based on the location of the specific object; An action of checking a movement trajectory based on at least one of the above movement points; An action of taking a video based on the above movement trajectory; and A method comprising the action of displaying the image on the display (140) and / or storing the image in at least one memory (120).

9. In paragraph 8, The above image includes a 3D (three-dimensional) image, A method further comprising an action of identifying the specific object in the image using at least one of a segmentation engine (210), a depth heat map (220), or an attention learning model (230).

10. In paragraph 8, A method further comprising an action of identifying at least one face or gaze in said specific object.

11. In paragraph 10, A method further comprising an action of identifying at least one movement point including a start point, an end point, and a passing point based on at least one of a face or gaze identified in the specific object.

12. In paragraph 11, A method further comprising an action of identifying a midpoint between the above starting point and the above ending point as the passing point.

13. In paragraph 11, An action of drawing a curve trajectory in 3D space for the image and generating the movement trajectory passing through the start point, the end point, and the passing point; An operation of generating the curve trajectory based on a Bezier curve or a Cardinal Spline; and A method further comprising an action of moving the virtual camera (250) along the movement trajectory and directing the direction of the virtual camera (250) toward the specific object.

14. In paragraph 13, A method further comprising an action of differentiating the shooting time for each of the start point, the end point, and the passing point when shooting the specific object in the 3D space according to the movement trajectory.

15. In paragraph 10, A method further comprising an action of identifying a plurality of passing points based on the plurality of objects based on the plurality of objects in the image.

Images