Method and apparatus for image composition, device, medium, and program product

Abstract

Provided in the embodiments of the present disclosure are a method and apparatus for image composition, a device, a medium, and a program product. The method comprises: determining a composition requirement for a reference object; determining at least one reference point of the reference object on the basis of the composition requirement, the at least one reference point comprising at least a first reference point; on the basis that a first projection point of the first reference point on a camera rendering plane is set at a first predetermined location, determining a first camera location and a camera rotation axis of a camera acquisition point corresponding to the camera rendering plane, wherein the rotation of the camera acquisition point around the camera rotation axis from the first camera location enables the first projection point to remain at the first predetermined location; determining a second camera location and a camera orientation parameter obtained after the camera acquisition point rotates to a preset camera pitch angle from the first camera location, wherein said rotation occurs around the rotation axis using the first reference point as the center point; and generating an image of at least one object in a virtual scene on the basis of the second camera location and the camera orientation parameter.

Description

Method, device, equipment, medium and program product for image construction

[0001] The present application claims priority to the Chinese patent application No. 202411303485.1, filed on September 18, 2024, entitled “Method, device, equipment, medium and program product for image construction”, the whole content of which is incorporated herein by reference. TECHNICAL FIELD

[0002] The example embodiments of the present disclosure generally relate to the field of computer, and in particular, to a method, device, equipment, computer readable storage medium and computer program product for image construction. BACKGROUND

[0003] With the development of hardware technology and image processing technology, the visual effect of virtual scenes formed by virtualization technology is more and more real and delicate. Some virtual scenes are provided with virtual cameras, and the images of virtual objects (such as virtual characters, virtual items, virtual environments, etc.) can be constructed by using virtual cameras. For example, in a game scene, virtual cameras can be used to take pictures of virtual characters, pets, items and other virtual objects, which can increase the interactivity of the game. Also for example, in a virtual live scene, virtual cameras can be used to construct streaming media data of virtual objects for live streaming. However, the picture composition quality of the traditional virtual camera still needs to be improved. SUMMARY

[0004] In a first aspect of the present disclosure, a method for image construction is provided. The method comprises: determining a composition requirement for a reference object, the composition requirement indicating a picture layout of the reference object in an image to be generated; determining at least one reference point of the reference object based on the composition requirement, the at least one reference point comprising at least a first reference point; determining a first camera position and a camera rotation axis of a camera capture point corresponding to a camera rendering plane based on the first reference point being set at a first predetermined position at a first projection point of the camera rendering plane, wherein the camera capture point rotates from the first camera position around the camera rotation axis to keep the first projection point at the first predetermined position; determining a second camera position and camera pose parameters of the camera capture point after rotating the camera capture point at the first camera position around the camera rotation axis to a preset camera pitch angle with the first reference point as the center; and generating an image of at least one object in a virtual scene based on the second camera position and the camera pose parameters, the at least one object being of the same type as the reference object.

[0005] In a second aspect of the present disclosure, an apparatus for image construction is provided. The apparatus comprises: a composition requirement determination module configured to determine a composition requirement for a reference object, the composition requirement indicating a picture layout of the reference object in an image to be generated; a reference point determination module configured to determine at least one reference point of the reference object based on the composition requirement, the at least one reference point comprising at least a first reference point; a first position determination module configured to determine a first camera position and a camera rotation axis of a camera capture point corresponding to a camera rendering plane based on a first projection point of the first reference point being set at a first predetermined position, wherein the camera capture point rotates around the camera rotation axis from the first camera position to enable the first projection point to remain at the first predetermined position; a second position determination module configured to determine a second camera position and camera pose parameters of the camera capture point after the camera capture point rotates around the camera rotation axis from the first camera position with the first reference point as a center to a preset camera pitch angle; and an image generation module configured to generate an image of at least one object in a virtual scene based on the second camera position and the camera pose parameters, the at least one object being of a same type as the reference object.

[0006] In a third aspect of the present disclosure, an electronic device is provided. The device includes at least one processor; and at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor. The instructions, when executed by the at least one processor, cause the electronic device to perform the method of the first aspect.

[0007] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided. The medium has stored thereon computer-executable instructions that, when executed by a processor, implement the method of the first aspect.

[0008] In a fifth aspect of the present disclosure, a computer program product is provided, comprising computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the method according to the first aspect of the present disclosure.

[0009] It should be understood that nothing in this section is intended to limit the key or critical features of the embodiments of the present disclosure or limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0010] The above and other features, advantages and aspects of embodiments of the present disclosure will become more apparent by describing in detail some embodiments thereof with reference to the annexed drawings in which:

[0011] FIG. 1 shows a schematic diagram of an example environment in which embodiments of the present disclosure can be implemented;

[0012] FIG. 2 illustrates a flowchart of a process for image construction, according to some embodiments of the present disclosure;

[0013] FIG. 3 illustrates a schematic diagram of an example of a reference object, according to some embodiments of the present disclosure;

[0014] FIG. 4 illustrates a schematic diagram of a geometric representation for image construction, according to some embodiments of the present disclosure;

[0015] FIG. 5 illustrates a schematic diagram of an example of a reference object, according to some embodiments of the present disclosure;

[0016] FIGS. 6A and 6B respectively illustrate schematic diagrams of an example of an image presentation interface, according to some embodiments of the present disclosure;

[0017] FIG. 7 illustrates a schematic structural block diagram of an apparatus for image construction, according to some embodiments of the present disclosure; and

[0018] FIG. 8 illustrates a block diagram of an electronic device that can implement one or more embodiments of the present disclosure. DETAILED DESCRIPTION

[0019] Embodiments of the present disclosure will be described in more detail with reference to the drawings. While certain embodiments of the present disclosure are illustrated in the drawings, it is understood that the present disclosure can be embodied in various forms and should not be interpreted in a limited sense as illustrated in the drawings. Rather, the embodiments are provided so that the present disclosure can be more thoroughly and completely understood. It should be understood that the drawings and embodiments of the present disclosure are only for illustrative purposes and are not intended to limit the scope of protection of the present disclosure.

[0020] It should be noted that the titles of any sections / subsections provided herein are not limiting. Various embodiments are described throughout this document, and any type of embodiment can be included under any section / subsection. Furthermore, embodiments described in any section / subsection can be combined with any other embodiment described in the same section / subsection and / or a different section / subsection in any manner.

[0021] In the description of embodiments of the present disclosure, the term "includes" and its derivatives, are not intended to be limiting. The term "based on" is intended to be further to "based, at least in part, on." The term "one embodiment" or "an embodiment" are intended to be interpreted as "at least one embodiment." The term "some embodiments" are intended to be interpreted as "at least some embodiments." Other explicit or implicit definitions can also be included below. The terms "first," "second," etc. can refer to different or same objects. Other explicit or implicit definitions can also be included below.

[0022] The data of the user, the acquisition and / or use of the data, etc. can be involved in the embodiments of the present disclosure. These aspects all comply with the corresponding laws and regulations and relevant provisions. In the embodiments of the present disclosure, the collection, acquisition, processing, processing, forwarding, use, etc. of all data are performed on the premise that the user is aware of and confirms. Accordingly, when implementing the embodiments of the present disclosure, the type, use range, use scenario, etc. of the data or information that can be involved should be informed to the user and the authorization of the user should be obtained through appropriate means according to the relevant laws and regulations. The specific informing and / or authorization manner can vary according to the actual situation and application scenario, and the scope of the present disclosure is not limited in this aspect.

[0023] In the present specification and embodiments, if personal information processing is involved, it will be processed on the premise of legality (for example, obtaining the consent of the subject of personal information, or being necessary for the performance of a contract, etc.), and only within the prescribed or agreed range. The user refuses to process personal information other than the necessary information required for the basic function, which does not affect the user's use of the basic function.

[0024] FIG. 1 shows a schematic diagram 100 of an example scenario according to some embodiments of the present disclosure. As shown in FIG. 1, in some virtual scenarios 120 such as games, simulations, movies, etc., the scene image 150 of the virtual scenario 120 is usually obtained or generated by controlling the parameters of the camera (or virtual camera) 130. Such a scene image 150 can include, for example, static images and / or dynamic images (e.g., videos).

[0025] Generally, the parameters of the camera 130 can include, for example, the position parameters, attitude parameters and field of view (FOV) parameters of the camera 130, etc. Exemplarily, the position parameters can be represented as the spatial coordinates of the camera 130, for example, three coordinate components of x, y and z.

[0026] The attitude parameters can be described by Euler angles, i.e., yaw / pitch / roll, denoted as α, β and γ, respectively. The field of view parameters can include, for example, the FOV range of the camera 130, which can be represented as θ, for example.

[0027] Thus, in the process of determining the scene image 150, it can be necessary to determine the above parameters, which can also be referred to as composition parameters in the present disclosure. In some scenarios, some parameters can be known, also referred to as known composition parameters; some parameters can be unknown, also referred to as unknown composition parameters or to-be-determined composition parameters.

[0028] In some embodiments, a set of composition parameters 140 can be determined or given by the electronic device 110, after which a scene image 150 can be generated using the set of composition parameters 140. Alternatively or additionally, the determined set of composition parameters 140 can be used to generate a scene image 150 of the scene 120 by the electronic device 110 or other suitable electronic device.

[0029] In some embodiments, the electronic device 110 can be any type of mobile terminal, fixed terminal, or portable terminal including a mobile handset, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media player, a multimedia tablet, a palmtop computer, a portable gaming terminal, a VR / AR device, a Personal Communication System (PCS) terminal, a personal navigation device, a Personal Digital Assistant (PDA), an audio / video player, a digital camera / camcorder, a positioning device, a television receiver, a radio broadcast receiver, an electronic book device, a game device, or any combination thereof, including an apparatus and peripherals or peripherals thereof. In some embodiments, the electronic device 110 can also include a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, and the like.

[0030] It should be understood that the structure and function of the environment 100 are described for illustrative purposes only, and do not imply any limitation on the scope of the present disclosure.

[0031] As mentioned previously, with the development of hardware technology and image processing technology, the visual effect of a virtual scene formed using virtualization technology is increasingly realistic and delicate. Some virtual scenes are provided with virtual cameras, and images of virtual objects (e.g., virtual characters, virtual items, virtual environments, and the like) can be constructed using the virtual cameras. For example, in a game scene, virtual characters, pets, items, and other virtual objects can be photographed using virtual cameras, which can increase the interactivity of the game. For another example, in a virtual live streaming scene, stream media data of virtual objects can be constructed using virtual cameras for live streaming.

[0032] Traditionally, the composition parameters of a virtual camera are usually manually given for different characters, scenes, and expression intentions. Some other requirements are to pre-construct multiple virtual cameras, and configure different composition parameters for different virtual cameras, and select different virtual cameras for different characters or scenes. These traditional configuration methods of the composition parameters of virtual cameras all require human involvement, resulting in low efficiency of the configuration of virtual cameras. Moreover, the composition parameters configured for an object are usually not applicable to different objects, and have poor flexibility.

[0033] In view of this, the embodiments of the present disclosure provide an improved requirement for image construction. In the requirement, a composition requirement for a reference object is determined, the composition requirement indicating a picture layout of the reference object in an image to be generated. At least one reference point of the reference object is determined based on the composition requirement, the at least one reference point including at least a first reference point. A first camera position and a camera rotation axis of a camera capture point corresponding to a camera rendering plane are determined based on the first reference point being set at a first predetermined position at a first projection point of the camera rendering plane, wherein the camera capture point rotates from the first camera position around the camera rotation axis to keep the first projection point at the first predetermined position. A second camera position and camera pose parameters of the camera capture point are determined after the camera capture point rotates around the camera rotation axis at the first camera position with the first reference point as the center to a preset camera pitch angle. Then, an image of at least one object in the virtual scene is generated based on the second camera position and the camera pose parameters, the at least one object being of the same type as the reference object.

[0034] According to the embodiments of the present disclosure, for different types of reference objects, camera positions and camera pose parameters (i.e., composition parameters) that meet specific composition requirements can be automatically determined. Using the determined camera positions and camera pose parameters, images of the reference objects or objects of the same type as the reference objects in the virtual scene can be generated. In this way, not only the configuration efficiency of the virtual camera can be improved, but also the applicable range of the configured composition parameters can be improved to improve the flexibility of the virtual camera.

[0035] Some example embodiments of the present disclosure will be described in detail below with reference to examples of the accompanying drawings.

[0036] FIG. 2 shows a flowchart of a process 200 for image construction according to some embodiments of the present disclosure. The process 200 can be implemented by the electronic device 110, which will be described below in conjunction with FIG. 1 for the process 200 shown in FIG. 2.

[0037] At block 210 of the process 200, the electronic device 110 determines a composition requirement for a reference object. The reference object here can include any object in the virtual scene 120. For example, in a game scene, the reference object can be a virtual character, a virtual creature, a virtual building, a virtual landscape, etc. in the game. Also for example, in a virtual live streaming scene, the reference object can be a virtual host, a virtual guest, a virtual product, etc.

[0038] Alternatively or additionally, the electronic device 110 can determine the composition requirement based on the type of the reference object. For example, the type of the reference object can indicate that the reference object belongs to a character, an animal, a natural landscape, a building, a micro object, etc. In actual applications, the type of the reference object can be divided in multiple dimensions according to actual needs.

[0039] Alternatively or additionally, the electronic device 110 can also acquire the composition requirement indicated by the composition instruction in response to receiving the composition instruction for the reference object. Illustratively, a plurality of composition requirements can be pre-constructed. The user can trigger the composition operation for the reference object by using the electronic device 110 or an attached device of the electronic device 110, and can select the composition requirement for the reference object according to actual needs. The electronic device 110 can generate the composition instruction based on the selected composition requirement in response to the selection operation of the composition requirement.

[0040] The composition requirement indicates the screen layout of the reference object in the image to be generated. Alternatively or additionally, the composition requirement can indicate the shape, size, aspect ratio, etc. of the image itself. The composition requirement can also indicate the part of the reference object displayed in the image, and the shape, size, aspect ratio, layout direction in the image, position in the image, etc. of the part. Alternatively or additionally, the composition requirement can indicate the relative positional relationship between the part of the reference object displayed in the image and at least one point, axis or region in the image. Alternatively or additionally, the composition requirement can also include at least part of the known composition parameters, such as the camera pitch angle, camera focal length, camera sensor size, camera aperture, etc.

[0041] At block 220 of the process 200, the electronic device 110 determines at least one reference point of the reference object based on the composition requirement, the at least one reference point including at least a first reference point. Alternatively or additionally, the at least one reference point can be a point on the reference object, such as a skeletal point of the reference object, a boundary point or a bounding box of the reference object. The at least one reference point can also have a corresponding relationship with at least one point on the reference object.

[0042] In some embodiments, the electronic device 110 can determine the at least one reference point of the reference object based on the screen layout of the reference object in the image to be generated and the type of the reference object. For example, the reference object can include a virtual character. In the case where the composition requirement indicates to take a full-body shot of the virtual character (i.e. the full body of the virtual character is present in the image), a point on the head can be selected as a reference point, and a point on the leg or foot can also be selected as a reference point. For another example, the reference object can include an animal (such as a cat or a dog), and the composition requirement can indicate that the screen layout direction of the animal in the image is horizontal. In this case, a point on the head, a point on the shoulder blade, a point on the rear hip and a point on the tail of the animal can be selected as reference points, respectively.

[0043] In some embodiments, the electronic device 110 determines at least one key point located on the reference object based on the composition requirement. Based on the layout direction of the picture layout, a reference axis matching the layout direction is determined. At least one projection point of the at least one key point on the reference axis is determined as at least one reference point. Alternatively or additionally, the at least one key point can include at least one of a skeleton point of the reference object, or a boundary point or a bounding box of the reference object. The electronic device 110 can determine at least one skeleton point or a boundary point of the reference object as at least one key point of the reference object based on the composition requirement. For example, for a reference object having a skeleton point such as a person, an animal, etc., at least one skeleton point of the reference object can be selected as a key point. For a reference object such as a building, a natural landscape, a stationary object (e.g., furniture, home appliances, kitchenware, small commodities, etc.), a bounding box of the reference object can be determined, and then at least one boundary point can be selected from the bounding box as a key point.

[0044] Alternatively or additionally, the composition requirement can indicate a portion of the reference object to be displayed in the image to be generated, and a relative positional relationship between the portion and the image to be generated. The electronic device 110 can determine at least one key point of the reference object based on the portion of the reference object to be displayed in the image to be generated, and the relative positional relationship between the portion and the image to be generated.

[0045] For example, FIG. 3 shows a schematic diagram of an example 300 of a reference object according to some embodiments of the present disclosure. In the example 300, it is assumed that an image of a virtual person 310 in a virtual scene is expected to be generated. The composition requirement can indicate that a page layout of the image to be generated is landscape, and indicate that an upper body (e.g., from the head to the chest) of the virtual person 310 is to be displayed in the image to be generated. The electronic device 110 can select a chin of the virtual person 310 as a key point 330 based on the composition requirement. Alternatively, the electronic device 110 can also select a glabella and a suprasternal notch as key points 340 and 350, respectively.

[0046] Alternatively or additionally, the composition requirement can also include a camera yaw angle. The camera yaw angle generally refers to a rotation angle of the camera 120 relative to the y-axis in the camera coordinate system. The camera yaw angle can be used to determine an orientation of the camera 120 in a circumferential direction of the reference object. The electronic device 110 can determine at least one key point located on the reference object based on the picture layout of the reference object in the image to be generated and the camera yaw angle.

[0047] Exemplarily, as shown in FIG. 3, if it is determined according to the composition requirement that the upper body of the virtual character 310 is displayed in the image to be generated, and the camera 120 is located in front of the virtual character, at least one part of the virtual character 310, such as the center of the eyebrows, the chin, and the upper chest, can be determined as the key point 340, the key point 330, or the key point 350. If it is determined according to the camera yaw angle that the camera 120 is located at the side of the virtual character 310, the ear, the shoulder, or the like of the virtual character 310 can be selected as the key point. If it is determined according to the camera yaw angle that the camera 120 is located at the back of the virtual character 310, the back of the head, the neck, the scapula, or the like of the virtual character 310 can be selected as the key point.

[0048] Alternatively or additionally, the composition requirement can also indicate a positional relationship between at least one part of the reference object displayed in the image to be generated and at least one reference line of the image. At this time, the electronic device 110 can divide the at least one part indicated by the composition requirement into the key points. Exemplarily, as shown in FIG. 3, the composition requirement corresponding to the virtual character 310 determined by the electronic device 110 can indicate a relative positional relationship between the chin of the virtual character 310 and the reference line 320 (for example, the vertical center line of the image) of the image. For example, the composition requirement can indicate that the key point 330 is located at or close to the middle of the reference line 320. In this case, the electronic device 110 can determine the chin of the virtual character 310 as the key point 330.

[0049] It can be understood that the above-mentioned key point selection method is only exemplary, and should not be understood as being limited to the method of selecting the key point as shown above. In actual application, different key point selection requirements can be determined according to actual needs for different reference objects.

[0050] The layout direction of the picture layout herein can include a page layout direction of the image, for example, the image itself is horizontally laid out or vertically laid out. The layout direction of the picture layout can also include a layout direction of the reference object in the image, for example, the part of the reference object displayed in the image is horizontally laid out or vertically laid out.

[0051] In some embodiments, the electronic device 110 can determine the reference axis based on the page layout direction of the image to be generated. For example, if the composition requirement indicates that the page layout direction of the image to be generated is vertical layout, an axis corresponding to the vertical center line of the image can be determined as the reference axis.

[0052] In some embodiments, the electronic device 110 can also determine the reference axis based on the layout direction of the reference object in the image to be generated. Exemplarily, as shown in FIG. 3, the virtual character 310 is partially and wholly arranged in the vertical direction in the image, and an axis corresponding to the reference line 320 can be determined as the reference axis.

[0053] In some embodiments, the electronic device 110 can determine at least one key point of the reference object based on the layout direction of the picture layout. Based on the at least one key point, a reference axis matching the layout direction of the picture layout is determined. Exemplarily, as shown in FIG. 4, FIG. 4 shows a schematic diagram of a geometric representation 400 for image construction according to some embodiments of the present disclosure. In the several representations 400, the electronic device 110 can determine a key point A and a key point B according to the composition requirement, for example, select the key point A and the key point B along the vertical arrangement on the reference object. The electronic device 110 can construct a world coordinate system having a specific relative positional relationship with the key point A and the key point B according to the key point A and the key point B. In the world coordinate system, a straight line matching the layout direction of the picture layout is selected as a reference axis 410, for example, a straight line passing through the key point A and the key point B or another straight line parallel to the straight line can be selected as the reference axis 410. Then, the projection point ProjA of the key point A on the reference axis 410 and the projection point ProjB of the key point B on the reference axis 410 are respectively taken as reference points. For example, the projection point ProjA can be determined as a first reference point, and the projection point ProjB can be determined as a second reference point.

[0054] At block 230 of the process 200, the electronic device 110 determines a first camera position and a camera rotation axis of a camera capture point corresponding to the camera rendering plane based on the first reference point being set at a first predetermined position on the first projection point of the camera rendering plane. The camera capture point here can be a point position at which the simulated camera 120 performs image capture in the virtual scene 120. When generating an image, the simulated camera 120 performs image capture at the camera capture point in the virtual scene 120 to generate a scene image 150 in the virtual scene 120. The camera rendering plane can be a virtual plane to which the camera 120 aligns when performing image rendering at the camera capture point. The camera rotation axis can enable the camera capture point to rotate from the first camera position around the camera rotation axis, and the first projection point remains at the first predetermined position of the camera rendering plane.

[0055] Alternatively or additionally, the first predetermined position can be a position having a predetermined proportional relationship with the camera rendering plane. Optionally, the camera rendering plane can have a reference line matching the layout direction of the picture layout. The first predetermined position can be a position on the reference line having a predetermined proportional relationship with the reference line. For example, as shown in FIG. 4, the vertical center line of the rendering plane 420 can be determined as a reference line. The composition requirement can indicate that the first predetermined position is located at a position having a predetermined proportional relationship on the reference line (for example, located at 1 / 5, 1 / 4, 1 / 3 or 1 / 2 close to the top end of the reference line). The electronic device 110 can determine the predetermined position PredA on the camera rendering plane as the first predetermined position based on the composition requirement.

[0056] It can be understood that the first predetermined position described above is only exemplary, and in actual application, any position of the camera rendering plane can be selected as the first predetermined position according to actual needs. The first predetermined position can be a fixed point or a region. For example, the first predetermined position can be a position 1 / 3 of the length of the reference line from the top end of the reference line downward, or a region close to the position.

[0057] In some embodiments, the electronic device 110 can determine that the center point of the camera rendering plane is at a third projection point of the reference axis. Based on the camera projection matrix, a camera field of view angle in the extension direction of the reference axis is determined. Based on the camera field of view angle, it is determined that the two ends of the camera rendering plane in the extension direction of the reference axis are at a fourth projection point and a fifth projection point of the reference axis. Then, the electronic device 110 can determine the first camera position based on the positional relationship between the at least one reference point, the third projection point, the fourth projection point, the fifth projection point and the first predetermined position.

[0058] Exemplarily, as shown in FIG. 4, the electronic device 110 can determine the center point C of the camera rendering plane 410, and determine the projection point ProjC of the center point C on the reference axis 410. In the case where the reference axis 410 extends vertically, the electronic device 110 can determine the camera vertical field of view angle (Vertical FOV) based on the camera projection matrix. Of course, in the case where the reference axis extends horizontally (or laterally), the electronic device 110 can also determine the camera horizontal field of view angle (Horizontal FOV) based on the camera projection matrix. The electronic device 110 can determine the projection point ProjMax and the projection point ProjMin of the top end and the low end of the camera rendering plane 420 on the reference axis 410 according to the triangle similarity, the projection characteristics, the camera vertical field of view angle, and the predetermined positional relationship between the predetermined position PredA and the camera rendering plane 420. Then, the electronic device 110 can determine the camera position LocCam1 of the camera 120 in the world coordinate system based on the projection point ProjA, the projection point ProjC, the projection point ProjMax, the projection point ProjMin and the predetermined position PredA according to the triangle similarity theorem. Of course, the electronic device 110 can also determine the camera pose parameter RotCam1 of the camera 120 at the camera position LocCam1.

[0059] It can be understood that the determination method of the first camera position described above is only exemplary, and should not be understood as being limited to determining the first camera position by the above method. For example, in the case where the projection point ProjA, the projection point ProjC and the predetermined position PredA are determined, and the initial pitch angle of the camera 120 is given, the first camera position can also be determined by using, for example, a camera model.

[0060] In some embodiments, the electronic device 110 can determine the camera rotation axis based on at least one vector from the third projection point to at least one reference point, and a vector from the third projection point to the first camera location. For example, as shown in FIG. 4, the electronic device 110 can determine a vector ProjCToProjA from the projection point ProjC to the projection point ProjA, a vector ProjCToProjB from the projection point ProjC to the projection point ProjB, and a vector ProjCToCam1 from the projection point ProjC to the camera location LocCam1. Based on the vector ProjCToProjA, the vector ProjCToProjB, and the vector ProjCToCam1, the electronic device 110 can determine the camera rotation axis AxisPitch, for example, by determining a horizontal axis passing through the projection point ProjA as the camera rotation axis AxisPitch. Of course, the camera rotation axis AxisPitch can also be other axis as long as the projection point ProjA can remain at the predetermined position PredA on the camera rendering plane 420 when the camera 120 is rotated around the camera rotation axis AxisPitch with the projection point ProjA as the center point.

[0061] At block 240 of the process 200, the electronic device 110 determines a second camera location and a camera pose parameter of the camera capture point at the first camera location with the first reference point as the center point, and with the camera rotation axis rotated to the preset camera pitch angle. The second camera location can indicate a relative position relationship between the camera 120 and the reference object, and the camera pose parameter can indicate a relative pose relationship between the camera 120 and the reference object. For example, the second camera location can be configured to identify a relative position relationship between the camera 120 and at least one reference point of the reference object in the world coordinate system. The camera pose parameter can be configured to identify a relative pose relationship between the camera 120 and at least one reference point of the reference object in the world coordinate system.

[0062] Alternatively or additionally, the composition requirement can include the camera pitch angle AngelPitch. The electronic device 110 can extract the camera pitch angle from the composition requirement. Alternatively or additionally, the user can also specify the camera pitch angle. The electronic device 110 can also extract the camera pitch angle from the user input. For example, the electronic device 110 can determine a camera location LocCam2 and a camera pose parameter RotCam2 of the camera 120 from the camera location LocCam1 with the projection point ProjA as the center point, and with the camera rotation axis AxisPitch rotated to the preset camera pitch angle AngelPitch. It can be understood that the composition requirement can also preset a camera rotation angle that can enable the camera 120 to rotate from the camera location LocCam1 to the camera location LocCam2.

[0063] At block 250 of process 200, electronic device 110 generates an image of at least one object in virtual scene 120 based on the second camera position and the camera pose parameter, the at least one object being of the same type as the reference object. In the case where the at least one reference point includes the first reference point, the second camera position and the camera pose parameter can be used to generate the image of the at least one object in virtual scene 120 as part of the composition parameters 140. It can be appreciated that the image can include a still image and / or a dynamic image (e.g., a video).

[0064] In some embodiments, electronic device 110 can set a relative positional relationship between camera 120 and the at least one object based on the second camera position. Electronic device 110 can also set a relative pose relationship between camera 120 and the at least one object based on the camera pose parameter. Electronic device 110 can simulate a photographing of the at least one object by camera 120 at the spatial pose indicated by the second camera position and the camera pose parameter, and render an image of the at least one object on a camera rendering plane of camera 120 to generate the image of the at least one object in the virtual scene. It can be appreciated that in actual applications, camera 120 can not be required to be placed in virtual scene 120, and electronic device 110 can only determine the relative positional relationship and the relative pose relationship between the at least one object and the camera rendering plane using the second camera position and the camera pose parameter. Further, a projection relationship between the at least one object and the camera rendering plane is determined, and an image of the at least one object is simulated to be rendered on the camera rendering plane to generate the image of the at least one object.

[0065] In some embodiments, the object for which the determined parameters are used to generate an image can include the reference object, or other objects of the same type as the reference object.

[0066] Exemplarily, as shown in FIG. 3 and FIG. 5, FIG. 5 shows a schematic diagram of an example 500 of a reference object according to some embodiments of the present disclosure. The composition requirement can indicate a relative position relationship between the chin of the virtual person 310 in the image to be generated and the reference line 320 (e.g. the vertical center line of the image), for example, the composition requirement can be that the chin of the virtual person 310 is located at 1 / 2 of the reference line 320. The electronic device 110 can generate an image of the virtual person 310 in the virtual scene 120 using the second camera position and camera pose parameters determined based on the composition requirement, which can enable the chin of the virtual person 310 to be located at 1 / 2 of the vertical center line of the image or close to 1 / 2 of the vertical center line. The electronic device 110 can also generate an image of the virtual person 510 shown in the example 500 using the determined second camera position and camera pose parameters, which can also enable the chin of the virtual person 510 to be located at 1 / 2 of the vertical center line of the image or close to 1 / 2 of the vertical center line.

[0067] As shown in FIG. 6A and FIG. 6B, FIG. 6A and FIG. 6B respectively show schematic diagrams of an example 600A and an example 600B of an image presentation interface according to some embodiments of the present disclosure. The example 600A presents one image of the virtual person 510 generated by the electronic device 110 through the image presentation region 620 of the interface 610, and the example 600B presents another image of the virtual person 510 generated by the electronic device 110 through the interface presentation region 620 of the interface 610, and the chin of the virtual person 510 in both images can be kept at or close to 1 / 2 of the vertical center line of the image in a similar manner.

[0068] In addition, as shown in FIG. 6A and FIG. 6B, when the menu 630 is displayed on the left side of the interface 610, causing the size and proportion relationship of the image presentation region 620 to change, the image of the virtual person 510 generated by the electronic device 110 based on the second camera position and camera pose data will also adaptively change, and the chin of the virtual person 510 presented in the changed image presentation region can still be kept at or close to 1 / 2 of the vertical center line of the image presentation region. That is, because the second camera position and camera pose data indicate the relative position relationship and the relative pose relationship between the camera 120 and the reference object, when the size or proportion of the image changes, the electronic device 110 can also adaptively adjust and generate an image of at least one object that meets the composition requirement.

[0069] In some embodiments, if multiple reference points are selected for the reference object, for example, a second reference point is also included. After determining the second camera position and the first reference point based on the first reference point, the electronic device 110 can determine a target translation line based on the second camera position and the first reference point. The target translation line can enable the camera capture point to keep the camera pose parameters unchanged during the translation along the target translation line. Based on the second projection point of the second reference point being set at the second predetermined position on the camera rendering plane, a third camera position on the target translation line is determined. Then, based on the third camera position and the camera pose parameters, an image of at least one object in the virtual scene is generated. In this way, the screen layout of the reference object in the image to be generated can be calibrated based on two reference points, and the accuracy of the composition parameters can be further improved.

[0070] In some embodiments, the electronic device 110 can determine a first vector from the second reference point to the first camera position, and a second vector by rotating the first vector about the camera rotation axis to the camera pitch angle with the first reference point as the center. Then, based on the relative positional relationship between the second vector, the first reference point and the second reference point, and the vector from the first reference point to the second camera position, a third camera position on the target translation line is determined.

[0071] For example, as shown in FIG. 4, after determining the projection point ProjB of the key point B on the reference axis 410 and the camera position LocCam1, the electronic device 110 can determine a vector ProjBToLocCam1 from the projection point ProjB to the camera position LocCam1. When the camera 120 is centered on the projection point ProjA and rotates about the camera rotation axis AxisPitch, the vector ProjBToLocCam1 is also centered on the projection point ProjA and forms a vector ProjBToLocCam2 about the camera rotation axis AxisPitch. Then, the electronic device 110 can determine a target translation line passing through the projection point ProjA and the camera position LocCam2 (i.e., a straight line on which the vector ProjAToLocCam2 from the projection point ProjA to the camera position LocCam2 is located).

[0072] The electronic device 110 can determine the camera position LocCam3 based on the positional relationship between the vector PorjAToProjB between the projection point ProjA and the projection point ProjB, the vector ProjAToLocCam2 between the projection point ProjA and the camera position LocCam2, and the vector ProjBToLocCam2 according to the law of cosines. The camera 120 translates along the target translation line without changing the camera tilt angle, which can ensure that the projection point of the projection point ProjA in the camera rendering plane remains at the predetermined position PredA. When the camera 120 is translated to the camera position LocCam3, the projection point of the projection point ProjB in the camera rendering plane 420 can also remain at the predetermined position PredB. The image generated based on the camera position LocCam3 can ensure that the key point A and the key point B meet the picture layout (for example, the positional relationship) of the reference object in the image indicated by the composition requirement.

[0073] It can be understood that for the reference object, the number of selected reference points is not limited to one reference point or two reference points, and a plurality of reference points can be selected according to actual needs. Embodiments of the present disclosure are not limited in this respect. In the case of selecting more than two reference points, for the third reference point, the camera position and the corresponding camera pose can also be adjusted according to the similar adjustment mode described above for the second reference point. It should be noted that in the case of selecting multiple reference points, there can be a case where there is no solution for the camera position, that is, there is no camera position that can make multiple reference points respectively located at the predetermined positions in the camera rendering image. At this time, the reference points can be corrected or selected in a way close to the position.

[0074] In summary, according to embodiments of the present disclosure, for different types of reference objects, the camera position and the camera pose parameters (that is, the composition parameters) that meet the specific composition requirement can be automatically determined. Using the determined camera position and camera pose parameters, an image of the reference object or the same type of object of the reference object in the virtual scene can be generated. In this way, not only the configuration efficiency of the virtual camera can be improved, but also the applicable range of the configured composition parameters can be improved to improve the flexibility of the virtual camera.

[0075] Embodiments of the present disclosure also provide a corresponding device for implementing the above method or process. FIG. 7 shows a schematic structural block diagram of a device 700 for image construction according to some embodiments of the present disclosure. The device 700 can be implemented in or included in the electronic device 110, for example. Various modules / components in the device 700 can be implemented by hardware, software, firmware, or any combination thereof.

[0076] As shown, the apparatus 700 can include a composition requirement determining module 710, a reference point determining module 720, a first position determining module 730, a second position determining module 740, and an image generating module 750. The composition requirement determining module 710 is configured to determine a composition requirement for a reference object, the composition requirement indicating a picture layout of the reference object in an image to be generated. The reference point determining module 720 is configured to determine at least one reference point of the reference object based on the composition requirement, the at least one reference point including at least a first reference point. The first position determining module 730 is configured to determine a first camera position and a camera rotation axis of a camera capture point corresponding to a camera rendering plane based on the first reference point being set at a first predetermined position at a first projection point of the camera rendering plane, wherein the camera capture point rotates around the camera rotation axis from the first camera position to keep the first projection point at the first predetermined position. The second position determining module 740 is configured to determine a second camera position and camera pose parameters of the camera capture point after the camera capture point rotates to a preset camera pitch angle with the first reference point as a center at the first camera position and with the camera rotation axis. The image generating module 750 is configured to generate an image of at least one object in a virtual scene based on the second camera position and the camera pose parameters, the at least one object being of a same type as the reference object.

[0077] In some embodiments, the at least one reference point further includes a second reference point; and the image generating module 750 is further configured to: determine a target translation line based on the second camera position and the first reference point, wherein the camera capture point translates along the target translation line to keep the camera pose parameters unchanged; determine a third camera position on the target translation line based on a second projection point of the second reference point being set at a second predetermined position of the camera rendering plane; and generate the image of the at least one object in the virtual scene based on the third camera position and the camera pose parameters.

[0078] In some embodiments, the image generating module 750 is further configured to: determine a first vector from the second reference point to the first camera position; determine a second vector after the first vector rotates to the camera pitch angle with the first reference point as a center and with the camera rotation axis; and determine the third camera position on the target translation line based on a relative positional relationship between the second vector, the first reference point, and the second reference point, and a vector from the first reference point to the second camera position.

[0079] In some embodiments, the reference point determining module 720 is further configured to: determine at least one key point on the reference object based on the composition requirement; determine a reference axis matching a layout direction of the picture layout based on the layout direction; and determine at least one projection point of the at least one key point on the reference axis as the at least one reference point.

[0080] In some embodiments, the composition requirement further includes a camera yaw angle; the reference point determination module 720 is further configured to determine at least one key point located on the reference object based on the screen layout of the reference object in the image to be generated and the camera yaw angle.

[0081] In some embodiments, the at least one key point includes at least one of a skeleton point of the reference object, or a boundary point or a bounding box of the reference object.

[0082] In some embodiments, the first position determination module 730 is further configured to determine a center point of the camera rendering plane at a third projection point of a reference axis on which the at least one reference point is located, an extension direction of the reference axis matching a layout direction of the screen layout; determine a camera field of view angle in the extension direction of the reference axis based on the camera projection matrix; determine two ends of the camera rendering plane in the extension direction of the reference axis at a fourth projection point and a fifth projection point of the reference axis based on the camera field of view angle; and determine the first camera position based on a positional relationship between the at least one reference point, the third projection point, the fourth projection point, the fifth projection point and the first predetermined position.

[0083] In some embodiments, the first position determination module 730 is further configured to determine the camera rotation axis based on at least one vector from the third projection point to the at least one reference point, and a vector from the third projection point to the first camera position.

[0084] In some embodiments, the first predetermined position is a position having a predetermined proportional relationship with the camera rendering plane.

[0085] The units and / or modules included in the apparatus 700 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units and / or modules can be implemented using software and / or firmware, e.g., machine executable instructions stored on a storage medium. In addition to or alternatively, some or all of the units and / or modules in the apparatus 700 can be implemented at least partially by one or more hardware logic components. As an example and not by way of limitation, example types of hardware logic components that can be used include Field-programmable Gate Arrays (FPGAs), Application-specific Integrated Circuits (ASICs), Application-specific Standard Products (ASSPs), System-on-a-chip systems (SOCs), Complex Programmable Logic Devices (CPLDs), etc.

[0086] FIG. 8 shows a block diagram of an electronic device 800 in which one or more embodiments of the present disclosure can be implemented. It should be understood that the electronic device 800 illustrated in FIG. 8 is merely an example and should not be construed as limiting the functionality and scope of the embodiments described herein. The electronic device 800 illustrated in FIG. 8 can include or be implemented as the electronic device of FIG. 1, or the apparatus 700 of FIG. 7.

[0087] As shown in FIG. 8, electronic device 800 is in the form of a general electronic device. Components of electronic device 800 can include, but are not limited to, one or more processors or processing units 810, memory 820, storage 830, one or more communication units 840, one or more input devices 850, and one or more output devices 860. Processor 810 can be a real or virtual processor and is capable of executing various processing in accordance with computer-executable instructions stored in memory 820. In a multiprocessor system, multiple processors execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 800.

[0088] Electronic device 800 typically includes a plurality of computer storage media. Such media can be removable and / or non-removable, volatile and / or non-volatile. Memory 820 can be volatile (such as registers, cache, random access memory (RAM)), non-volatile (such as read-only memory (ROM), electrically erasable programmable read only memory (EEPROM), flash memory), or some combination thereof. Storage 830 can be removable or non-removable and can include machine-readable media, such as a flash drive, a magnetic disk drive, or any other media capable of storing information and / or data and accessible by electronic device 800.

[0089] Electronic device 800 can further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG. 8, a disk drive or other computer-readable media drive can be provided for reading from or writing to a removable, non- volatile magnetic disk (e.g., a "hard drive"), and a disk drive or other computer-readable media drive can be provided for reading from or writing to a removable, non-volatile optical disk (such as a CD-ROM or other optical medium). In these instances, each drive can be connected to the bus (not shown) by one or more data media interfaces. Memory 820 can include a computer program product 825 having one or more program modules configured to carry out the various methods or actions of the various embodiments of the present disclosure.

[0090] Communication unit 840 enables communication with other electronic devices over communication media. Additionally, functionality of components of electronic device 800 can be implemented in a single computing cluster or a plurality of computer machines capable of communicating over a communication connection. As such, electronic device 800 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network nodes in a distributed computing environment.

[0091] Input device 850 can be one or more input devices, such as a mouse, a keyboard, a trackball, etc. Output device 860 can be one or more output devices, such as a display, a speaker, a printer, etc. Electronic device 800 can also communicate with one or more external devices (not shown), such as a storage device, a display device, etc., through communication unit 840, as desired, in order to communicate with one or more devices that enable a user to interact with electronic device 800, or to communicate with any device (e.g., a network card, a modem, etc.) that enables electronic device 800 to communicate with one or more other electronic devices. Such communication can be carried out via an input / output (I / O) interface (not shown).

[0092] According to an example implementation of the present disclosure, a computer readable storage medium is provided having computer executable instructions stored thereon, where the computer executable instructions are executed by a processor to implement the method described above. According to an example implementation of the present disclosure, a computer program product is also provided that is tangibly stored on a non-transitory computer readable medium and includes computer executable instructions, where the computer executable instructions are executed by a processor to implement the method described above.

[0093] The computer executable instructions can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer executable instructions can also be stored in a computer readable storage medium that can include a non-transitory computer readable storage medium that can direct a computer, a programmable data processing apparatus, and / or other devices to function in a particular manner, such that the computer readable storage medium having instructions stored

[0094] The computer executable instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0095] The computer executable instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0096] The computer program product of the present disclosure can be a computer program product, which is a machine-readable medium (media) having instances of the software embodied thereon, such as computer software, firmware, wireless application protocol (WAP), middleware or microcode. For example, a computer program product can be a floppy disk, a CD-ROM, a DVD, a Blu-ray Disc™, a flash drive, a memory stick, a magnetic tape, or a hard disk drive. The computer program product can also be a downloaded file, such as a file downloaded from the Internet or another computer network. Of course, many modifications can be made by those skilled in the art to the inventive concept described herein, which can be practiced in various embodiments and over a variety of applications, and that the scope of the application is limited only by the following claims. For example, a computer program product can be a downloaded file, such as a file downloaded from the Internet or another computer network. Of course, many modifications can be made by those skilled in the art to the inventive concept described herein, which can be practiced in various embodiments and over a variety of applications, and that the scope of the application is limited only by the following claims.

[0097] The implementations of the disclosure have been described above with the intent to be illustrative rather than limiting. Although the implementations described above have particular applications in the medical field, it should be recognized that the implementations of the disclosure have broad applicability to other fields. Numerous modifications and variations will be apparent to those skilled in the art in light of the above teachings. For example, the above-described implementations can be used in a variety of medical applications, such as in the diagnosis of medical conditions, in the administration of medical treatment, and in the administration of medical care. Any or all of the individual features or operations described above can be used separately or in any combination. By way of non-limiting example, features described above can be used in a medical device, a medical system, a medical method, a medical apparatus, a medical instrument, a medical computer program, a medical computer program product, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program distribution medium, a medical computer program

Claims

1. A method for image construction, comprising: determining a composition requirement for a reference object, the composition requirement indicating a layout of the reference object in an image to be generated; determining at least one reference point of the reference object based on the composition requirement, the at least one reference point comprising at least a first reference point; determining a first camera position and a camera rotation axis of a camera capture point corresponding to a camera rendering plane based on a first projection point of the first reference point being set at a first predetermined position on the camera rendering plane, wherein the camera capture point rotates around the camera rotation axis from the first camera position to keep the first projection point at the first predetermined position; determining a second camera position and camera pose parameters of the camera capture point at the first camera position with the first reference point as a center and with the camera rotation axis rotated to a preset camera pitch angle; and generating an image of at least one object in a virtual scene based on the second camera position and the camera pose parameters, the at least one object being of the same type as the reference object. 2.The method of claim 1, wherein the at least one reference point further comprises a second reference point; and generating an image of at least one object in a virtual scene based on the second camera position and the camera pose parameters comprises: determining a target translation line based on the second camera position and the first reference point, wherein the camera capture point translates along the target translation line to keep the camera pose parameters unchanged; determining a third camera position on the target translation line based on a second projection point of the second reference point being set at a second predetermined position on the camera rendering plane; and generating an image of at least one object in a virtual scene based on the third camera position and the camera pose parameters. 3.The method of claim 2, wherein determining the third camera position on the target translation line comprises: determining a first vector from the second reference point to the first camera position; determining a second vector from the first vector with the first reference point as a center and with the camera rotation axis rotated to the camera pitch angle; and determining the third camera position on the target translation line based on a relative position relationship between the second vector, the first reference point and the second reference point, and a vector from the first reference point to the second camera position. 4.The method of claim 1, wherein determining the at least one reference point based on the composition requirement comprises: determining at least one key point on the reference object based on the composition requirement; determining a reference axis matching a layout direction of the layout based on the layout direction; and determining at least one projection point of the at least one key point on the reference axis as the at least one reference point. 5.The method of claim 4, wherein the composition requirement further comprises a camera yaw angle; and determining at least one key point on the reference object comprises: ​ determine at least one key point on the reference object based on the picture layout of the reference object in the image to be generated and the camera yaw angle.

6. The method of claim 4, wherein the at least one key point comprises at least one of: a skeletal point of the reference object, or a boundary point or a bounding box of the reference object.

7. The method of claim 1, wherein determining the first camera position comprises: determining a third projection point of a center point of the camera rendering plane on a reference axis on which the at least one reference point is located, an extension direction of the reference axis matching a layout direction of the picture layout; determining a camera field of view angle in the extension direction of the reference axis based on a camera projection matrix; determining fourth and fifth projection points of two ends of the camera rendering plane in the extension direction of the reference axis based on the camera field of view angle; and determining the first camera position based on a positional relationship between the at least one reference point, the third projection point, the fourth projection point, the fifth projection point and the first predetermined position.

8. The method of claim 7, wherein determining the camera rotation axis comprises: determining the camera rotation axis based on at least one vector from the third projection point to the at least one reference point, and a vector from the third projection point to the first camera position.

9. The method of claim 1, wherein the first predetermined position is a position having a predetermined proportional relationship with the camera rendering plane.

10. An apparatus for image construction, comprising: a composition requirement determination module configured to determine a composition requirement for a reference object, the composition requirement indicating a picture layout of the reference object in an image to be generated; a reference point determination module configured to determine at least one reference point of the reference object based on the composition requirement, the at least one reference point comprising at least a first reference point; a first position determination module configured to determine a first camera position and a camera rotation axis of a camera capture point corresponding to a camera rendering plane based on the first reference point being set at a first projection point of the camera rendering plane at a first predetermined position, wherein the camera capture point rotates around the camera rotation axis from the first camera position to keep the first projection point at the first predetermined position; a second position determination module configured to determine a second camera position and camera pose parameters of the camera capture point after rotating the camera capture point around the camera rotation axis at the first camera position with the first reference point as a center to a preset camera pitch angle; and an image generation module configured to generate an image of at least one object in a virtual scene based on the second camera position and the camera pose parameters, the at least one object being of a same type as the reference object.

11. An electronic device, comprising: at least one processor; and ​ at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor, the instructions, when executed by the at least one processor, cause the electronic device to perform the method according to any one of claims 1 to 9.

12. A computer-readable storage medium having computer-executable instructions stored thereon that are executable by a processor to implement the method according to any one of claims 1 to 9.

13. A computer program product comprising computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the method according to any one of claims 1 to 9.

Images