Image presentation method and apparatus, image generation method and apparatus, presentation picture generation method and apparatus, and device and storage medium

Abstract

The present disclosure relates to the technical field of image processing, and particularly relates to an image presentation method and apparatus, an image generation method and apparatus, a presentation picture generation method and apparatus, and a device and a storage medium. The image presentation method comprises: presenting a preview object on a display interface, wherein the preview object comprises a three-dimensional model of an object to be presented and a scenario to be presented, and the three-dimensional model of said object is generated on the basis of a planar image of said object; in response to an adjustment operation performed on the preview object, presenting a target preview object on the display interface, wherein the target preview object is the preview object which has been adjusted on the basis of the adjustment operation; and in response to a rendering trigger operation performed on the target preview object, presenting a target rendered image of the target preview object on the display interface.

Description

Image display method, generation method, display image generation method and its device, equipment, and storage medium Technical Field

[0001] The present disclosure relates to the field of image processing technology, and in particular to an image display method, a generation method, a display graph generation method, and a device, equipment, and storage medium thereof. Background Art

[0002] On a product introduction page, it is usually necessary to display detailed images of the product (or commodity) to facilitate users to quickly obtain relevant information. However, how to improve the display effect of the product is a hot issue that needs to be solved urgently.

[0003] Summary of the Invention

[0004] A first aspect of an embodiment of the present disclosure provides an image display method, comprising: displaying a preview object on a display interface, the preview object comprising a three-dimensional model of an object to be presented and a scene to be presented, wherein the three-dimensional model of the object to be presented is generated based on a planar image of the object to be presented; in response to an adjustment operation on the preview object, displaying a target preview object on the display interface, the target preview object being the preview object adjusted based on the adjustment operation; and in response to a rendering trigger operation on the target preview object, displaying a target rendered image of the target preview object on the display interface.

[0005] A second aspect of an embodiment of the present disclosure provides an image display device, comprising: a first display unit, configured to display a preview object on a display interface, the preview object comprising a three-dimensional model of an object to be presented and a scene to be presented, wherein the three-dimensional model of the object to be presented is generated based on a planar image of the object to be presented; a second display unit, configured to display a target preview object on the display interface in response to an adjustment operation on the preview object, the target preview object being the preview object adjusted based on the adjustment operation; and a third display unit, configured to display a target rendered image of the target preview object on the display interface in response to a rendering trigger operation on the target preview object.

[0006] A third aspect of an embodiment of the present disclosure provides a method for generating a display image, comprising: in response to a first selection operation on a target object and a target background, displaying a target model in a first area of ​​a display interface, and displaying a background image of the target background at the bottom layer of the target model in the first area, wherein the target model is a three-dimensional model of the target object; in response to a rendering operation, displaying at least one display image on the display interface, wherein the display image in at least one display image is a fusion of a first sub-image and a second sub-image located at the bottom layer of the first sub-image, and the first sub-image is an image of the target object obtained by rendering the target model based on the selected target light, and the second sub-image is an image obtained by generating a model using an AI image and based on the target light, the background image and the target model.

[0007] A fourth aspect of an embodiment of the present disclosure provides a display image generating device, comprising: a fourth display unit, for displaying a target model in a first area of ​​a display interface in response to a first selection operation on a target object and a target background, and displaying a background image of the target background at the bottom layer of the target model in the first area, wherein the target model is a three-dimensional model of the target object; a fifth display unit, for displaying at least one display image on a display interface in response to a rendering operation, wherein the display image in at least one display image is a fusion of a first sub-image and a second sub-image located at the bottom layer of the first sub-image, and the first sub-image is an image of the target object obtained by rendering the target model based on the selected target light, and the second sub-image is an image generated by using an AI image generation model and based on the target light, the background image and the target model.

[0008] A fifth aspect of an embodiment of the present disclosure provides an image generation method, comprising: in a case where it is determined that a wireframe image of a foreground image of a target object and a target background image are displayed in a current operation area, in response to a first image generation operation, displaying an initial fusion effect image; the initial fusion effect image is obtained by fusing the foreground image of the target object with the wireframe image of the target background image; in response to a second image generation operation, displaying a target fusion effect image; wherein, the target fusion effect image is obtained by performing image processing on the initial fusion effect image using image effect description parameters, and is used to represent a simulated effect image after the target object and the target background image are fused.

[0009] A sixth aspect of an embodiment of the present disclosure provides an image generating device, comprising: a processing unit, for obtaining an initial fusion effect diagram in response to a first image generating operation when it is determined that a wireframe diagram of a foreground image of a target object and a target background image are displayed in a current operating area; the initial fusion effect diagram is obtained by fusing the foreground image of the target object with the wireframe diagram of the target background image; a display unit, for displaying the initial fusion effect diagram; the processing unit is also used to obtain a target fusion effect diagram in response to a second image generating operation; wherein the target fusion effect diagram is a simulated effect diagram obtained by performing image processing on the initial fusion effect diagram using image effect description parameters, and is used to represent the fusion of the target object and the target background image; the display unit is also used to display the target fusion effect diagram.

[0010] The seventh aspect of the embodiments of the present disclosure provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor performs the steps of the method provided in any aspect of the embodiments of the present disclosure.

[0011] An eighth aspect of the embodiments of the present disclosure provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute the steps of the method provided in any aspect of the embodiments of the present disclosure.

[0012] A ninth aspect of the embodiments of the present disclosure provides a computer program product, comprising a computer program, which implements the steps of the method provided in any aspect of the embodiments of the present disclosure when executed by a processor.

[0013] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the solutions in the present disclosure, a brief introduction is given below to the drawings required for use in describing the embodiments of the present disclosure. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0015] FIG1 is a schematic structural diagram of a system applying the image display method according to an embodiment of the present disclosure.

[0016] FIG2 is a schematic diagram of an image display method provided according to an embodiment of the present disclosure.

[0017] FIG3 is a schematic diagram of an image display method provided according to another embodiment of the present disclosure.

[0018] FIG4 is a schematic diagram of an image display device according to an embodiment of the present disclosure.

[0019] FIG5 is a structural diagram of a system of an application display diagram generation method provided by an embodiment of the present disclosure.

[0020] FIG6 is a flowchart of a method for generating a display diagram according to an embodiment of the present disclosure.

[0021] 7-a to 7-c are operation flow charts of the display interface of the display image generation method provided in one embodiment of the present disclosure.

[0022] FIG8 is a flowchart of a method for generating a display diagram provided by another embodiment of the present disclosure.

[0023] FIG9 is a schematic block diagram of a display image generating device provided in an embodiment of the present disclosure.

[0024] FIG10 is a schematic flowchart 1 of an image generating method according to an embodiment of the present disclosure.

[0025] FIG11 is a schematic diagram of an interface of an image generation method in a specific example according to an embodiment of the present disclosure.

[0026] FIG12 is a second schematic flowchart of an image generation method according to an embodiment of the present disclosure.

[0027] FIG13 is a third schematic flowchart of an image generation method according to an embodiment of the present disclosure.

[0028] Figure 14-a is a schematic flowchart 4 of the image generation method according to an embodiment of the present disclosure.

[0029] Figure 14-b is a schematic diagram of a parameter configuration interface according to an embodiment of the present disclosure.

[0030] FIG15 is a schematic diagram of a process implementation of an image generation method in an example according to an embodiment of the present disclosure.

[0031] FIG16 is a schematic structural diagram of an image generating device according to an embodiment of the present disclosure.

[0032] FIG17 is a structural block diagram of an electronic device for an image display method, a display image generation method, or an image generation method provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0033] Unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art in the art to which this disclosure belongs. The terms used in the specification disclosed herein are for the purpose of describing specific embodiments only and are not intended to limit this disclosure. The terms "including" and "having" and any variations thereof in the specification and claims of this disclosure and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this disclosure or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0034] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present disclosure. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0035] In order to enable those skilled in the art to better understand the solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0036] The first aspect of the present disclosure is described as follows:

[0037] Product introduction pages typically display detailed images of products or merchandise, allowing users to quickly access relevant information about the product. To enhance the product's presentation, it's often necessary to place the product in a suitable shooting scene and capture the product image.

[0038] The embodiments of the present disclosure provide an image display method, device, electronic device and storage medium. Specifically, the image display method of the embodiments of the present disclosure can be executed by an electronic device, wherein the electronic device can be a terminal or a server and other devices. The terminal can be a smart phone, a tablet computer, a laptop computer, an intelligent voice interaction device, a smart home appliance, a wearable smart device, an aircraft, an intelligent vehicle terminal and other devices. The terminal can also include a client, which can be an audio client, a video client, a browser client, an instant messaging client or a mini-program, etc. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and basic cloud computing services such as big data and artificial intelligence platforms.

[0039] Related technologies mainly rely on manual photography of product images, and the manual photography process includes the following main steps:

[0040] 1. Determine the product type and quantity: First, you need to determine the type and quantity of products to be photographed. Based on the characteristics of the products and market demand, select the appropriate products to be photographed and determine the number of photos required.

[0041] 2. Design the composition and scene: After determining the product type and quantity, you need to design the composition and shooting scene, choose a suitable shooting background and pose, and consider appropriate lighting settings to highlight the characteristics and advantages of the product.

[0042] 3. Prepare shooting equipment and accessories: After designing the composition and shooting scene, you need to prepare appropriate shooting equipment and accessories, such as cameras, lenses, tripods, lights, etc., as well as some auxiliary props, such as background boards, props, etc.

[0043] 4. Shoot and Verify: After preparing the equipment, shoot and verify to ensure that the captured images meet the expected requirements. Verification includes checking the captured images for color, focus, clarity, etc.

[0044] 5. Post-processing: After shooting is completed, post-processing is required, including image color adjustment, cropping, beautification, etc. According to the characteristics of the product and market demand, choose the appropriate post-processing method to improve the quality of the images to be displayed.

[0045] 6. Export and listing: After completing post-processing, export the images to be displayed into a suitable format and upload them to e-commerce platforms for display, such as putting products on shelves for sale.

[0046] However, the above manual shooting process mainly includes the following disadvantages:

[0047] 1. High time cost: Manual shooting requires a lot of time to prepare the scene, lighting, placement, shooting, etc.

[0048] 2. High cost: Manual photography requires hiring professional photographers and staff, purchasing professional cameras and equipment, etc., which is relatively costly.

[0049] 3. Requires actual scenes: Manual shooting needs to be carried out in actual scenes, and the influence of environmental factors such as light and weather needs to be taken into account, which limits the flexibility of shooting.

[0050] 4. Complex post-processing: After manual shooting is completed, post-processing is required, including color adjustment, photo modification, etc., which requires a lot of time and energy.

[0051] 5. Limited accuracy: The accuracy of manual photography is subject to the limitations of the photographer's skills and equipment, and there may be some errors and deviations in the shooting results.

[0052] To address at least one of the aforementioned issues, embodiments of the present disclosure provide an image display method, apparatus, device, and storage medium. The method comprises displaying a preview object on a display interface, the preview object comprising a three-dimensional model of the object to be presented and a scene to be presented, wherein the three-dimensional model of the object to be presented is generated based on a two-dimensional image of the object to be presented. In response to an adjustment operation on the preview object, a target preview object is displayed on the display interface, the target preview object being the preview object adjusted based on the adjustment operation. In response to a rendering trigger operation on the target preview object, a target rendered image of the target preview object is displayed on the display interface. When a rendered image of the object to be presented needs to be generated, the user can adjust the object to be presented and the scene to be presented through the display interface, eliminating the need to manually construct a shooting scene or manually capture an image, thereby reducing the cost and time of obtaining product display images.

[0053] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0054] FIG1 is a schematic diagram of a system for applying the image display method according to an embodiment of the present disclosure. Referring to FIG1 , the system includes a terminal 110 and a server 120 . The terminal 110 and the server 120 are connected via a network, such as a wired or wireless network.

[0055] Among them, the terminal 110 can be used to display a graphical user interface. Among them, the terminal is used to interact with the user through the graphical user interface, for example, by downloading and installing the corresponding client and running it through the terminal, for example, by calling the corresponding applet and running it, for example, by logging into the website to present the corresponding graphical user interface, etc. In an embodiment of the present disclosure, the terminal 110 can be installed with an image processing application, and through the application, a preview object is displayed on the display interface, the preview object includes a three-dimensional model of the object to be presented and a scene to be presented, wherein the three-dimensional model of the object to be presented is generated based on the plane image of the object to be presented; in response to an adjustment operation on the preview object, a target preview object is displayed on the display interface, and the target preview object is the preview object adjusted based on the adjustment operation; in response to a rendering trigger operation on the target preview object, a target rendered image of the target preview object is displayed on the display interface. The server 120 can be used to generate a target rendered image based on the target preview object, and then send the target rendered image to the terminal 110 to display the target rendered image on the terminal.

[0056] It should be noted that this embodiment uses the example of server 120 generating a target rendered image based on a target preview object. In other embodiments, a terminal may also generate a target rendered image based on a target preview object. Furthermore, the application may be an application installed on a desktop computer, an application installed on a mobile terminal, or a mini-program embedded within an application.

[0057] It should be noted that the above application scenarios are only shown to facilitate understanding of the spirit and principles of the present disclosure, and the embodiments of the present disclosure are not limited in this respect. On the contrary, the embodiments of the present disclosure can be applied to any applicable scenario.

[0058] It should be noted that the order in which the following embodiments are described does not limit the priority order of the embodiments.

[0059] FIG2 is a schematic diagram of an image display method according to an embodiment of the present disclosure. Referring to FIG2 , the present disclosure embodiment provides an image display method 200 , comprising the following steps S201 to S203 .

[0060] Step S201 : displaying a preview object on a display interface. The preview object includes a three-dimensional model of the object to be presented and a scene to be presented. The three-dimensional model of the object to be presented is generated based on a planar image of the object to be presented.

[0061] Step S202 : In response to the adjustment operation on the preview object, displaying a target preview object on the display interface, where the target preview object is the preview object adjusted based on the adjustment operation.

[0062] Step S203 : In response to the rendering triggering operation on the target preview object, a target rendered image of the target preview object is displayed on the display interface.

[0063] The display interface may be a display interface of a terminal, and the terminal may be a mobile phone, computer, tablet computer or other device.

[0064] The display interface can display a preview object, which may include a three-dimensional model of the object to be presented and a scene to be presented.

[0065] In step S201 , a three-dimensional model of the scene to be presented and the object to be presented may be displayed on a display interface.

[0066] It is understood that the object to be presented may be a product to be presented, etc., and the three-dimensional model of the object to be presented may be a three-dimensional model generated based on a two-dimensional image of the object to be presented. Specifically, a plurality of two-dimensional images of the object to be presented may be used to generate a corresponding three-dimensional model of the object to be presented. For example, a planar front view, top view, and side view of the image to be presented may be used to generate a corresponding three-dimensional model of the object to be presented.

[0067] The scene to be presented can be the background of the object to be presented, and can be a two-dimensional or three-dimensional scene, etc., and can match the usage scenario of the object to be presented. For example, if the object to be presented is kitchenware, the scene to be presented can be an indoor kitchen scene. If the object to be presented is a sofa, the scene to be presented can be an indoor living room scene. If the object to be presented is a tent, the scene to be presented can be an outdoor natural scene, etc.

[0068] In step S202 , the user may adjust the scene to be presented and / or the object to be presented through adjustment operations.

[0069] It is understood that the adjustment operation may be applied only to the scene to be presented, i.e., adjusting the angle, position, texture, etc. of the scene to be presented. Alternatively, the adjustment operation may be applied only to the 3D model of the object to be presented, such as adjusting the display angle, size, texture, etc. of the 3D model. Alternatively, the adjustment operation may include adjustments to both the scene to be presented and the 3D model of the object to be presented.

[0070] Depending on the parameters to be adjusted, the adjustment operation may include dragging, selecting, clicking, and other operations, or a combination of various operations.

[0071] Through the adjustment operation, the display state of the three-dimensional model of the scene to be presented and the object to be presented can be adjusted to a display state that meets the user's needs (i.e., the product presentation requirements), that is, the adjusted preview object is displayed on the current display interface, and the adjusted preview object is the target preview object. It can be understood that the display state of the target preview object can better present the state of the object to be presented, that is, the display state of the object to be presented that the user wants to present. Before obtaining the target preview object, the user can repeatedly perform the adjustment operation so that the final display effect meets the product presentation requirements.

[0072] In step S203, if a rendering trigger operation is detected for the currently adjusted target preview object, such as the target preview object being displayed on the current display interface and a click on a render button, a rendered image of the target preview object, i.e., the target rendered image, can be displayed on the current display interface. The target rendered image can be an image obtained by processing the target preview object through the rendering operation. Its display resolution and clarity can be higher, resulting in a better presentation than the target preview object displayed on the interface. The target rendered image can be displayed as a product display image on a product introduction page.

[0073] It is understood that the target rendered image can be a product display image that is ultimately intended to be displayed on the product details page. After obtaining the target rendered image, the target rendered image can also be provided for download. After downloading the target rendered image, the user can upload the target rendered image, for example, to an e-commerce platform, thereby displaying the product.

[0074] In this embodiment, by displaying the three-dimensional model of the object to be presented and the scene to be presented on the display interface, and adjusting the three-dimensional model of the object to be presented and the scene to be presented to the state required by the user through user adjustment operations, and then generating the target rendering image of the object to be presented, the automatic generation and display of the product display picture can be realized, without spending a lot of time preparing the scene, lighting, placement, shooting, etc., thus saving time costs.

[0075] This eliminates the need to hire professional photographers and staff, purchase specialized cameras and equipment, and reduces the cost of creating product display images. Furthermore, the presentation scene is not restricted by real-world environmental factors such as lighting and weather, offering high flexibility. Users can adjust parameters such as lighting, background, and material through the display interface, further controlling the display effect.

[0076] Furthermore, since rendered images can be generated directly, post-processing such as color adjustment and photo retouching can be reduced, further saving time and effort. Furthermore, when rendering the target preview object to obtain the target rendered image, various physical environments and scenes can be simulated by the computer, avoiding some of the physical limitations of manual photography, such as gravity and air resistance, making the product display images more realistic.

[0077] In addition, in related technologies, since the accuracy of manual shooting is subject to the limitations of the photographer's skills and equipment, there may be some errors and deviations in the shooting results. The image display method provided in this embodiment does not require the participation of the photographer, and the target rendered image finally presented on the display interface is the final shooting result, with higher presentation accuracy.

[0078] In some embodiments, displaying the preview object on the display interface in step S201 may include: displaying the scene to be presented on the display interface in response to a first selection operation on the scene to be presented; and displaying a three-dimensional model of the object to be presented on the display interface in response to a second selection operation on the object to be presented.

[0079] It can be understood that the first selection operation can be an operation such as clicking on the scene to be presented (for example, clicking on a presentation scene to be presented from multiple presentation scenes, or directly clicking on the scene to be presented), dragging (for example, dragging the scene to be presented directly to the current display interface, etc.).

[0080] In some embodiments, the display interface may also display a list of presentation scenarios. For example, by clicking a presentation scenario drop-down button, a list of pre-stored presentation scenarios may be displayed. The presentation scenario list may display multiple selectable presentation scenarios, which may be pre-stored in the terminal or server. The scene to be presented may be a presentation scenario selected by the user from the presentation scenario list.

[0081] Taking the home furnishing product as an example, the scenes to be presented may include various indoor and outdoor scenes. Indoor scenes may also include kitchens, living rooms, bedrooms, etc. The first selection operation may be a click operation on the scene to be presented in the presentation scene list. It is understood that after the user selects the scene to be presented, the scene to be presented may be displayed on the display interface.

[0082] Similarly, the second selection operation can be clicking on the object to be presented (for example, clicking on a presentation object you want to present from multiple presentation objects, or directly clicking on the object to be presented) or dragging (for example, dragging the object to be presented directly to the current display interface, etc.).

[0083] In some embodiments, the display interface may also display a presentation object list. For example, by clicking a presentation object drop-down button, multiple pre-stored presentation objects may be displayed in a list. The presentation object list may display multiple selectable presentation objects, which may be pre-stored in the terminal or server. The object to be presented may be a presentation object selected by the user from the presentation object list.

[0084] It can be understood that after a three-dimensional model is generated based on the planar image of the object to be presented, the three-dimensional model of the object to be presented can be stored in a terminal or a server and added to a presentation object list.

[0085] When the user needs to generate a target rendering image of an object to be presented, he or she can select it from the presentation object list, thereby meeting the situation where a product display image in multiple different presentation scenarios is required for a certain product, or where multiple products need to be displayed in a certain presentation scenario.

[0086] By pre-storing the objects to be presented, users can select the objects to be presented according to different product presentation requirements, which makes it more convenient to use.

[0087] In addition, by setting up a presentation scene list, users can select scenes from a preset pool to preview the product's presentation effect, choosing the scene that best highlights the product's characteristics for rendering. This reduces time costs and increases the efficiency of obtaining product display images. In contrast, manually shooting and setting up different backgrounds requires higher costs and time.

[0088] In some embodiments, displaying the preview object on the display interface in step S201 may include: displaying the preview object in a first area of ​​the display interface.

[0089] Displaying the target preview object on the display interface in response to the adjustment operation on the preview object in step S202 may include: displaying the target preview object in a first area in response to the adjustment operation on the preview object, wherein the first area is at least a portion of the display area in the display interface.

[0090] In this embodiment, the display interface may include a first area, and the first area may be at least a portion of the display interface, for example, it may be a middle area of ​​the display interface.

[0091] The preview object can be displayed in the first area, and when the adjustment operation is obtained, the preview object can be adjusted in real time in the first area, that is, the adjusted preview object is updated in real time, so that the first area can display the adjustment of the preview object in real time, which is convenient for users to view the adjustment of the preview object in time, thereby facilitating users to judge whether the adjusted preview object meets the product presentation requirements.

[0092] Of course, in other embodiments, the preview object and the target preview object may be displayed in different areas of the display interface, so that the user can compare the objects to be presented and the scenes to be presented before and after the adjustment operation.

[0093] In some embodiments, in response to an adjustment operation on a preview object, displaying a target preview object in a first area may include: in response to a first adjustment operation on scene data of a scene to be presented, displaying a target scene to be presented in the first area, the target preview object including the target scene to be presented, and the target scene to be presented is obtained after adjusting the scene data of the scene to be presented based on the first adjustment operation.

[0094] Alternatively, in response to an adjustment operation on the preview object, displaying the target preview object in the first area may include: in response to a second adjustment operation on the model data of the three-dimensional model of the object to be presented, displaying the target three-dimensional model of the object to be presented in the first area, the target preview object including the target three-dimensional model of the object to be presented, and the target three-dimensional model being obtained after adjusting the model data of the three-dimensional model of the object to be presented based on the second adjustment operation.

[0095] Alternatively, displaying the target preview object in the first area in response to an adjustment operation on the preview object may include: displaying the target scene to be presented in the first area in response to a first adjustment operation on the scene data of the scene to be presented; and displaying the target three-dimensional model of the object to be presented in the first area in response to a second adjustment operation on the model data of the three-dimensional model of the object to be presented.

[0096] In this embodiment, the adjustment operation may include a first adjustment operation on scene data of the scene to be rendered, or the adjustment operation may include a second adjustment operation on model data of a three-dimensional model of the object to be rendered. Alternatively, the adjustment operation may include both a first adjustment operation on scene parameters of the scene to be rendered and a second adjustment operation on model data of the three-dimensional model of the object to be rendered.

[0097] Taking the adjustment operation including the first adjustment operation and the second adjustment operation as an example, the three-dimensional model after the second adjustment operation can be the target three-dimensional model, and the scene to be presented after the first adjustment operation can be the target scene to be presented.

[0098] In some embodiments, the scene data may include at least one of: interior scene model information, exterior scene model information, lighting information, and camera information.

[0099] The interior scene model information represents the model information of the indoor scene where the 3D model of the object to be rendered resides. The exterior scene model information represents the display information of the outdoor scene outside the indoor scene. The lighting information represents the parameters of the lighting that illuminates the 3D model of the object to be rendered. The camera information represents the parameters of the camera used to capture the 3D model of the object to be rendered.

[0100] It can be understood that the scene data can be used to adjust the display state of the scene to be presented, and the scene to be presented can include at least one of an indoor scene model and an outdoor scene model.

[0101] The interior scene model can be an indoor model, such as a kitchen interior layout model. By adjusting the interior scene model information, the display state of the indoor scene can be adjusted, such as the angle, texture, display size, etc.

[0102] The exterior scene model can be an outdoor model. For example, if the exterior scene is visible through the transparent glass window of the interior scene, the exterior scene can be displayed using the exterior scene model. The exterior scene model information can be used to adjust the exterior scene display state, such as angle, texture, display size, etc. Of course, if the product is an outdoor product, the scene to be presented can also only include the exterior scene model.

[0103] Lighting information can set parameters for the lights in the scene to be presented, such as the position of the lights, the number of lights, the type of lights (electric light source or surface light source, etc.), the brightness of the lights, the color temperature of the lights (warm or cool, etc.), etc.

[0104] Camera information may include parameter settings for the virtual camera used to capture the target preview object, such as exposure time, focal length, and camera position. It should be understood that the virtual camera here is not a physical camera in the true sense, but rather a virtual module in the system that simulates camera operation. Capturing the target preview object with the virtual camera involves capturing an image of the current presentation state of the target preview object, similar to how a physical camera would take a photograph of the target preview object.

[0105] By adjusting the above parameters, the object to be presented can be placed in a presentation scene that meets the product presentation requirements, and at the same time, the diversity and authenticity of the scene can be improved.

[0106] In some embodiments, the model data may include at least one of position information and material information.

[0107] The position information is used to represent the position information of the three-dimensional model of the object to be presented; the material information is used to represent the material mapping information of the three-dimensional model of the object to be presented.

[0108] The position information can be used to adjust the placement position and placement angle of the object to be presented, etc. The material information can be used to add material texture mapping to the three-dimensional model of the object to be presented, etc.

[0109] Through position information and material information, the display effect of the three-dimensional model of the object to be presented in the scene to be presented can better meet user needs, improve the display effect of the final target rendered image, and make it closer to the real scene and product presentation requirements.

[0110] In this embodiment, by adjusting the scene data and / or model data, the scene can better highlight the characteristics of the product, and the final display effect of the product can be better controlled, saving time and manpower.

[0111] In some embodiments, method 200 may further include: displaying a reference preview object in a second area of ​​the display interface, where the reference preview object is a preview object adjusted based on the adjustment operation, and display parameters of the target preview object are lower than display parameters of the reference preview object; the second area is at least a portion of the display area in the display interface.

[0112] It can be understood that the second area can be a different area from the first area, or the two can at least partially overlap, for example, the second area can be displayed suspended above the first area.

[0113] The display content of the reference preview object and the target preview object is the same, and both are preview objects adjusted according to the adjustment operation, but the display parameters of the reference preview object and the target preview object can be different.

[0114] The display parameters may refer to the display quality of the picture, for example, parameters such as resolution, etc. If the display parameters of the reference preview object are higher than those of the target preview object, that is, the display effect and picture quality of the reference preview object are better.

[0115] It's understood that the target preview object can be a real-time display of the 3D model of the current object to be presented and the scene to be presented, based on the adjustment operation. However, since the current image also needs to be rendered in real time based on the adjustment operation, to allow users to quickly see the results of the adjustment operation, the display parameters can be appropriately relaxed. Specifically, the resolution and other display parameters of the target preview object displayed in the first area can be lowered, thereby reducing image rendering time and ensuring real-time performance.

[0116] At the same time, in order to facilitate users to see images that are closer to the final rendering results, a reference preview object with higher display parameters can be displayed in the second area. It can be understood that since the picture quality requirements of the reference preview object are higher, its display can have a small delay.

[0117] It is understood that after detecting an adjustment operation, the target preview object can be displayed in the first area, and the reference preview object can be displayed in the second area. That is, both the target preview object and the reference preview object can be responses to the adjustment operation. In other embodiments, after detecting an adjustment operation, the target preview object can be displayed in the first area. At the same time, after further detecting an operation to display the reference preview object, the reference preview object can be displayed in the second area. In other words, the display of the reference preview object and the target preview object can be triggered by different operations.

[0118] In this embodiment, by displaying the target preview object and the reference preview object, the user can not only see the result of the adjustment operation in real time, but also see a display screen that is relatively close to the final target rendered image.

[0119] In some embodiments, the area of ​​the first region is larger than the area of ​​the second region; in response to a rendering trigger operation on the target preview object, displaying the target rendering image on the display interface may include: in response to a rendering trigger operation on the target preview object, displaying the target rendering image in the first region.

[0120] The first area may occupy most of the display interface, and the second area may occupy a small part of the display interface.

[0121] After the rendering trigger operation is detected, the target rendered image may also be displayed in the first area, so that the user can intuitively observe whether the target rendered image meets the requirements.

[0122] The above is an explanation of the display interface. The following will explain in detail the process of generating the target rendered image.

[0123] In some embodiments, in response to an adjustment operation on a preview object, displaying a target preview object in a first area may include: in response to the adjustment operation on the preview object, determining incremental data of the preview object corresponding to the adjustment operation; generating a target preview object based on the incremental data; and displaying the target preview object in the first area.

[0124] It is understood that when displaying a preview object, the preview object can be displayed based on the first data of the preview object. The first data can be data related to the preview object, and the preview object can be displayed based on the first data. For example, the first data can be used to render a display screen of the current first area, i.e., the first preview object.

[0125] After detecting an adjustment operation on a preview object, incremental data corresponding to the adjustment operation can be obtained in real time. The incremental data can be data related to the change in the preview object caused by the adjustment operation. For example, taking the adjustment operation as an example of adjusting the angle of the 3D model of the object to be presented, assuming that before the adjustment operation, the display angle (first data) of the 3D model of the object to be presented is 30 degrees. The adjustment operation is to rotate by dragging the mouse, and the incremental data can be detected in real time as a clockwise rotation of 30 degrees.

[0126] When obtaining incremental data, the first data and the incremental data can be combined to obtain the second data of the target preview object. For example, the current display angle is 30 degrees + 30 degrees = 60 degrees. The second data can then be used to render the current display screen, that is, the display image of the target preview object on the display interface.

[0127] It is understood that the incremental data can be detected in real time, and the display content of the first area can be adjusted in real time based on the incremental data. That is, the terminal can obtain incremental update data in real time based on the user's operation, update the viewport and render it, ensuring that the preview effect of the display is consistent with the edited content, so that the user can see the results of the adjustment operation in real time.

[0128] In some embodiments, displaying a reference preview object in a second area of ​​a display interface may include: sending incremental data of the preview object to a server; wherein the incremental data of the preview object corresponds to an adjustment operation; receiving a reference preview object sent by the server; wherein the reference preview object is generated by the server based on the incremental data; and displaying the reference preview object in the second area.

[0129] It can be understood that in this embodiment, after obtaining the incremental data, the terminal can send the incremental data to the server. The server can obtain the relevant data of the reference preview object based on the incremental data and the first data of the preview object, thereby generating a reference preview object, and then send the reference preview object to the terminal so that the second area of ​​the terminal can display the reference preview object.

[0130] It can be understood that since the display parameters of the reference preview object have high requirements, in order to reduce the processing pressure of the terminal, the server can render the display screen of the reference preview object based on the incremental data, and then the terminal will display it so that the terminal can run smoothly.

[0131] Based on the above embodiment, in response to the rendering trigger operation on the target preview object, displaying the target rendered image of the target preview object on the display interface in step S203 includes: sending the target preview object to the server in response to the rendering trigger operation on the target preview object; receiving the target rendered image sent by the server; wherein the target rendered image is generated by the server based on the target preview object; and displaying the target rendered image on the display interface.

[0132] In this embodiment, the generation of the target rendered image can also be achieved by the server. For example, after the terminal generates the target preview object, the relevant data of the target preview object can be sent to the server, and the server renders according to the data to obtain the target rendered image.

[0133] Specifically, this embodiment uses the server's cloud rendering technology to execute the rendering task of the current target preview object, and after the task is completed, the target rendered image is sent to the terminal, so that the user can obtain the product display image (target rendered image).

[0134] It is understandable that since the target rendered image has high image quality requirements, generating the target rendered image by rendering the target preview object through the server can reduce the processing pressure of the terminal, improve the rendering speed, and the smoothness of the terminal operation.

[0135] In some implementations, before displaying the preview object on the display interface in step S201, method 200 may include: obtaining a planar image of the object to be presented, the planar image including planar front views of the object to be presented at multiple angles; and generating a three-dimensional model of the object to be presented based on the planar image.

[0136] It can be understood that the planar image can be three views (planar front views, such as a front view, a side view, and a top view) of the product taken by the user, and of course can also include other views.

[0137] The terminal can generate a three-dimensional model of the object to be presented based on the planar view. It can be understood that there are many methods for generating a three-dimensional model of the object to be presented from a planar image.

[0138] In some embodiments, generating a three-dimensional model of the object to be presented based on the planar image may include the following steps 1 to 3.

[0139] Step 1: Based on the plane image, determine the two-dimensional corner points and the two-dimensional boundary lines of the object to be presented.

[0140] Step 2: Based on the two-dimensional corner points and the two-dimensional boundary lines, determine the three-dimensional corner points and the three-dimensional boundary lines of the object to be presented.

[0141] Step three: Generate a 3D model of the object to be presented based on the 3D corner points and 3D boundary lines.

[0142] For example, based on a planar image, image recognition technology can be used to obtain two-dimensional corner points and two-dimensional boundary lines of an object to be presented in the image.

[0143] Three-dimensional corner points and three-dimensional boundary lines can be obtained based on the two-dimensional corner points and two-dimensional boundary lines. This step can be processed by relying on a trained neural network model.

[0144] After obtaining the three-dimensional corner points and three-dimensional boundary lines, the three-dimensional model of the object to be presented can be reconstructed, realizing the conversion from a plane image to a three-dimensional model and obtaining the model file of the product.

[0145] In addition to the method of generating a 3D model from a planar image provided in this embodiment, other methods are also possible. For example, 2D corner points in a planar image are used to generate 3D candidate corner points, 3D candidate edges are then derived from the 3D candidate corner points, candidate faces are constructed from the 3D candidate edges located on the same surface, and then a 3D object (3D model) is constructed from the candidate faces.

[0146] In other embodiments, reconstructed data (two-dimensional geometric elements, such as two-dimensional corner points and two-dimensional line segments) can be obtained by preprocessing the data in the planar image; a three-dimensional wireframe consisting of candidate corner points and candidate edges can be generated based on the two-dimensional geometric elements; three-dimensional candidate faces can be searched in the three-dimensional wireframe; and a possible solid three-dimensional model can be obtained based on the three-dimensional candidate faces.

[0147] It can be understood that in this embodiment, a three-dimensional model of the object to be presented is generated by the user shooting a plane image, which can facilitate the user to directly obtain a product display image (target rendering image) in the virtual scene to be presented. Compared with setting up a physical shooting scene, it can save manpower and material costs.

[0148] It is understood that in one possible embodiment, taking the display interface as a user's terminal interface (e.g., a mobile phone interface), the user can directly capture and obtain a two-dimensional image of the object to be presented through the terminal, and then the terminal can generate a three-dimensional model of the object to be presented based on the two-dimensional image. After the three-dimensional model of the object to be presented is generated, the terminal can also display the three-dimensional model on the terminal interface and simultaneously display the scene to be presented on the terminal interface, that is, display a preview object on the terminal interface.

[0149] At the same time, the user can adjust the preview object. After detecting the user's adjustment operation on the preview object, the terminal will display the target preview object on the terminal interface. And when the terminal detects the user's rendering trigger operation on the target preview object, it can display the target rendered image of the target preview object on the terminal interface.

[0150] The target rendered image can be generated by rendering by a terminal or a server.

[0151] In this embodiment, the user can quickly obtain the target rendered image of the object to be presented in a snap-and-use manner.

[0152] In another possible embodiment, a user terminal may obtain a two-dimensional image of the object to be presented. The two-dimensional image may be directly captured by a camera device of the user terminal, or may be an image captured by another device and uploaded to the user terminal. The terminal may then generate a three-dimensional model of the object to be presented based on the two-dimensional image. The terminal may then send the three-dimensional model of the object to be presented to a server, which then stores the three-dimensional model.

[0153] When a user wants to generate a rendering, they can select the object to be rendered from the terminal's rendering object list (a list of all rendering object names stored in the display server). The user can then adjust the preview object. After detecting the user's adjustment operation on the preview object, the terminal displays the target preview object on the terminal interface. Furthermore, when the terminal detects the user triggering a rendering operation on the target preview object, it can display the target rendered image of the target preview object on the display interface. The target rendered image can be generated by rendering on the terminal or the server.

[0154] In this embodiment, when generating a three-dimensional model of an object to be presented, the three-dimensional model can be stored in the server first. When the user wants to generate a rendering image, the three-dimensional model of the object to be presented in the server can be called in the terminal, so that multiple product display images for the object to be presented can be generated, or multiple objects to be presented can be displayed in one product display image, and it will not take up too much terminal storage space, which is conducive to the rapid operation of the terminal.

[0155] In some embodiments, after generating a three-dimensional model of the object to be presented based on the plane image, method 200 further includes: sending the three-dimensional model of the object to be presented to a server; wherein the server is used to parse the three-dimensional model of the object to be presented into a three-dimensional model in a preset format and store the three-dimensional model in the preset format.

[0156] It can be understood that after obtaining the three-dimensional model of the object to be presented, the obtained three-dimensional model file can be uploaded to the server through the terminal for parsing. The server will uniformly parse it into a model file compatible with rendering on both ends of the terminal and the server (including the model's size, material information, etc.), that is, a three-dimensional model in a preset format, according to the type of the three-dimensional model file, and store it, for example, in the server's presentation object pool.

[0157] By storing the three-dimensional model, subsequent users can conveniently select the product for which to generate a product display picture directly from the presentation object list (a list showing the name information of all presentation objects in the presentation object pool), thereby generating multiple product display pictures for the object to be presented, or displaying multiple objects to be presented in the same product display picture.

[0158] Figure 3 is a schematic diagram of an image display method provided according to another embodiment of the present disclosure; in a specific embodiment, the image display method 300 can be jointly implemented by the client (terminal) and the cloud (server), and the method 300 can include the following steps S301 to S307.

[0159] In step S301, the user photographs the product (the object to be presented) to obtain three views (plane images), and obtains the three-dimensional model file of the product (the three-dimensional model of the object to be presented) through three-view modeling, for example, by exporting the model file of the product through a trained algorithm model.

[0160] In step S302, the user uploads the obtained 3D model file (the 3D model of the object to be presented) to the cloud through the client for parsing. The cloud parses the model file into a model file compatible with both the client and the cloud for rendering (including the 3D model in a preset format such as the model's size and material information) according to the type of the model file, and stores it in the database.

[0161] In step S303, the user selects a template scene (scene to be presented) for "shooting" the product in the client template library (presentation scene list), and selects the product (object to be presented) to be "shot" in the uploaded model list (presentation object list).

[0162] In step S304, the client obtains scene data (model information within the scene (interior scene model information), lighting information, scene exterior setting information (exterior scene model information), preset camera (camera information), etc.) and model data (material mapping information (material information), product preset position (position information), etc.) based on the template scene and product selected by the user, and renders them in real time through the WebGL (Web Graphics Library, web page drawing protocol) technology engine, thereby constructing a visual three-dimensional scene on the client to display the preview effect (preview object).

[0163] In step S305, the user adjusts the three-dimensional scene (preview object) in the client interactive viewport (display interface), such as moving the camera's perspective, editing the location and material of the scene model, editing lighting parameters, setting the scene exterior, editing the product location, angle, size, and material, and other editing operations to find the best "shooting" angle (find the target preview object).

[0164] In step S306, the client obtains incremental update data (incremental data) in real time according to the user's operation (adjustment operation), and updates the viewport rendering (real-time update of the preview effect) to ensure that the displayed preview effect is consistent with the edited content. The user selects a final desired "shooting" effect (the presentation effect of the target preview object) during the process and clicks the render button (rendering trigger operation) on the client to initiate a rendering request.

[0165] In step S307, the rendering task of the current 3D scene information (target preview object) snapshot is executed through the cloud rendering technology. After the task is completed, the picture (target rendered image) is sent to the client, so that the user can obtain the rendering image of the displayed product.

[0166] The “shooting” in this embodiment refers to the process of obtaining a display image of a product (ie, a target rendered image) using a virtual camera, and is not shooting using a physical camera.

[0167] This embodiment provides a method for generating product display images using image 3D modeling technology and cloud rendering technology, which has the following advantages:

[0168] 1. Cost savings: Cloud rendering eliminates the need to purchase equipment and rent a venue, significantly reducing costs. In contrast, manual photography requires preparing cameras, lenses, lighting, and other equipment, as well as renting a venue, which is relatively expensive.

[0169] 2. High time efficiency: Users can preview product presentations by selecting scenes from a pool of pre-set scenes, then choose the scene that best highlights the product's features for "shooting." In comparison, manually shooting and setting up different backgrounds is more expensive and time-consuming.

[0170] 3. Better control over the effect: Users can adjust parameters such as lighting, background, and material through the client to better control the effect. Manual photography is often limited by factors such as lighting and environment, making it difficult to fully control the effect.

[0171] 4. Avoid physical limitations: Cloud rendering can simulate various physical environments and scenes through computers, avoiding some physical limitations of manual photography, such as gravity and air resistance, and making the product display images more realistic.

[0172] FIG4 is a schematic diagram of an image display device according to an embodiment of the present disclosure. Referring to FIG4 , an embodiment of the present disclosure provides an image display device 400 , comprising the following units.

[0173] The first display unit 401 is used to display a preview object on the display interface. The preview object includes a three-dimensional model of the object to be presented and a scene to be presented. The three-dimensional model of the object to be presented is generated based on a planar image of the object to be presented.

[0174] The second display unit 402 is configured to display a target preview object on the display interface in response to an adjustment operation on the preview object, where the target preview object is the preview object adjusted based on the adjustment operation.

[0175] The third display unit 403 displays a target rendered image of the target preview object on the display interface in response to a rendering triggering operation on the target preview object.

[0176] In some embodiments, the first display unit 401 is further used to: display the scene to be presented on the display interface in response to a first selection operation on the scene to be presented; and display the three-dimensional model of the object to be presented on the display interface in response to a second selection operation on the object to be presented.

[0177] In some embodiments, the first display unit 401 is further used to: display a preview object in a first area of ​​the display interface; the second display unit 402 is further used to: display a target preview object in the first area in response to an adjustment operation on the preview object, wherein the first area is at least a portion of the display area in the display interface.

[0178] In some embodiments, the second display unit 402 is further used to: in response to a first adjustment operation on the scene data of the scene to be presented, display the target scene to be presented in the first area, the target preview object includes the target scene to be presented, and the target scene to be presented is obtained by adjusting the scene data of the scene to be presented based on the first adjustment operation; and / or, in response to a second adjustment operation on the model data of the three-dimensional model of the object to be presented, display the target three-dimensional model of the object to be presented in the first area, the target preview object includes the target three-dimensional model of the object to be presented, and the target three-dimensional model is obtained by adjusting the model data of the three-dimensional model of the object to be presented based on the second adjustment operation.

[0179] In some embodiments, the device 400 also includes: a fourth display unit, used to display a reference preview object in the second area of ​​the display interface, the reference preview object is a preview object adjusted based on the adjustment operation, and the display parameters of the target preview object are lower than the display parameters of the reference preview object; the second area is at least a portion of the display area in the display interface.

[0180] In some embodiments, the area of ​​the first region is larger than that of the second region; the third display unit 403 is further configured to: display the target rendered image in the first region in response to a rendering triggering operation on the target preview object.

[0181] In some embodiments, the second display unit 402 is further configured to: in response to an adjustment operation on the preview object, determine incremental data of the preview object corresponding to the adjustment operation; generate a target preview object based on the incremental data; and display the target preview object in the first area.

[0182] In some embodiments, the second display unit 402 is further used to: send incremental data of the preview object to the server; wherein the incremental data of the preview object corresponds to the adjustment operation; receive a reference preview object sent by the server; wherein the reference preview object is generated by the server based on the incremental data; and display the reference preview object in the second area.

[0183] In some embodiments, the third display unit 403 is further used to: send the target preview object to the server in response to a rendering trigger operation on the target preview object; receive a target rendered image sent by the server; wherein the target rendered image is generated by the server based on the target preview object; and display the target rendered image on the display interface.

[0184] In some embodiments, the device 400 further includes: a generating unit for acquiring a planar image of the object to be presented, the planar image including planar front views of the object to be presented at multiple angles; and generating a three-dimensional model of the object to be presented based on the planar image.

[0185] In some embodiments, the generation unit is also used to: determine the two-dimensional corner points of the object to be presented and the two-dimensional boundary lines of the object to be presented based on the plane image; determine the three-dimensional corner points of the object to be presented and the three-dimensional boundary lines of the object to be presented based on the two-dimensional corner points and the two-dimensional boundary lines; and generate a three-dimensional model of the object to be presented based on the three-dimensional corner points and the three-dimensional boundary lines.

[0186] In some embodiments, the generating unit is further configured to: send the three-dimensional model of the object to be presented to a server; wherein the server is configured to parse the three-dimensional model of the object to be presented into a three-dimensional model in a preset format and store the three-dimensional model in the preset format.

[0187] In some embodiments, the scene data includes: at least one of interior scene model information, exterior scene model information, lighting information, and camera information; the interior scene model information is used to represent the model information of the indoor scene where the three-dimensional model of the object to be presented is located; the exterior scene model information is used to represent the display information of the outdoor scene outside the indoor scene; the lighting information is used to represent the parameter information of the light irradiated to the three-dimensional model of the object to be presented; and the camera information is used to represent the parameter information of the camera used to capture the three-dimensional model of the object to be presented.

[0188] In some embodiments, the model data includes: at least one of position information and material information; the position information is used to represent the position information of the three-dimensional model of the object to be presented; the material information is used to represent the material mapping information of the three-dimensional model of the object to be presented.

[0189] For the description of specific functions and examples of each unit of the device in the embodiment of the present disclosure, please refer to the relevant description of the corresponding steps in the above-mentioned image display method embodiment, which will not be repeated here.

[0190] The second aspect of the present disclosure is described as follows:

[0191] Product introduction pages often require detailed product or merchandise images to help users quickly and easily access relevant product information. Therefore, how to quickly and easily provide effective product or merchandise display images has become a hot topic of research.

[0192] The embodiments of the present disclosure provide a method, device, electronic device and storage medium for generating a display image. Specifically, the display image generation method of the embodiments of the present disclosure can be executed by an electronic device, wherein the electronic device can be a terminal or a server or other device. The terminal can be a smart phone, a tablet computer, a laptop computer, an intelligent voice interaction device, a smart home appliance, a wearable smart device, an aircraft, an intelligent vehicle-mounted terminal or other device. The terminal can also include a client, which can be an audio client, a video client, a browser client, an instant messaging client or a mini-program, etc. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0193] In related technologies, when generating a display image of an item such as a product or commodity, a three-dimensional model of the item can be obtained, and then a background is added to the three-dimensional model to obtain the display image of the item. However, the fusion effect of the item and the background in the display image, especially the light and shadow effect, is poor, and the display effect is not good.

[0194] In order to solve at least one of the above problems, the embodiments of the present disclosure provide a method for generating a display image, comprising: in response to a first selection operation of a target object and a target background, displaying a target model in a first area of ​​a display interface, and displaying a background image of a target background at the bottom layer of the target model in the first area, wherein the target model is a three-dimensional model of the target object; in response to a rendering operation, displaying at least one display image on the display interface, wherein the display image in at least one display image is a fusion of a first sub-image and a second sub-image located at the bottom layer of the first sub-image, and the first sub-image is an image of the target object obtained by rendering the target model based on the selected target light, and the second sub-image is an image obtained by using an AI image generation model and based on the target light, the background image and the target model. In the display image generation method, apparatus, device and storage medium provided by the embodiments of the present disclosure, since the first sub-image and the second sub-image are both obtained based on the target light, the light and shadow effects of the target object in the display image can be better integrated with the light and shadow effects of the background, thereby improving the quality and display effect of the generated display image.

[0195] The solution of the present disclosure is described below with reference to the accompanying drawings.

[0196] Figure 5 is a structural diagram of a system for an application display diagram generation method provided by an embodiment of the present disclosure; please refer to Figure 5, the system includes a terminal 510 and a server 520, etc.; the terminal 510 and the server 520 are connected via a network, for example, via a wired or wireless network connection, etc.

[0197] Among them, the terminal 510 can be used to display a graphical user interface. Among them, the terminal is used to interact with the user through the graphical user interface, for example, by downloading and installing the corresponding client and running it through the terminal, for example, by calling the corresponding applet and running it, for example, by logging into the website to present the corresponding graphical user interface, etc. In an embodiment of the present disclosure, the terminal 510 displays the target model in the first area of ​​the display interface in response to a first selection operation of the target object and the target background, and displays the background image of the target background at the bottom layer of the target model in the first area, wherein the target model is a three-dimensional model of the target object; in response to a rendering operation, at least one display image is displayed on the display interface, wherein the display image in the at least one display image is a fusion of a first sub-image and a second sub-image located at the bottom layer of the first sub-image, and the first sub-image is an image of the target object rendered based on the selected target light for the target model, and the second sub-image is an image obtained by using an AI image generation model and based on the target light, background image, and target model. The server 520 can be used to render the target model based on the target light to obtain the first sub-image, and use the AI ​​image generation model to obtain the second sub-image based on the target light, background image, and target model.

[0198] It should be noted that, although the display interface is an application page as an example, the display interface may also be other pages such as a web page. In addition, the application may be an application installed on a desktop computer, an application installed on a mobile terminal, or a small program embedded in an application.

[0199] It should be noted that the above application scenarios are only shown to facilitate understanding of the spirit and principles of the present disclosure, and the embodiments of the present disclosure are not limited in this respect. On the contrary, the embodiments of the present disclosure can be applied to any applicable scenario.

[0200] It should be noted that the order in which the following embodiments are described does not limit the priority order of the embodiments.

[0201] FIG6 is a flow chart of a method for generating a display image provided by another embodiment of the present disclosure. Referring to FIG6 , an embodiment of the present disclosure provides a method 600 for generating a display image, comprising steps S601 to S602 .

[0202] Step S601: In response to a first selection operation on a target object and a target background, a target model is displayed in a first area of ​​a display interface, and a background image of the target background is displayed below the target model in the first area, wherein the target model is a three-dimensional model of the target object;

[0203] Step S602: In response to the rendering operation, at least one display image is displayed on the display interface, wherein the display image in the at least one display image is a fusion of a first sub-image and a second sub-image located at the bottom layer of the first sub-image, and the first sub-image is an image of the target object obtained by rendering the target model based on the selected target light, and the second sub-image is an image obtained by using the AI ​​image generation model and based on the target light, background image and target model.

[0204] The target object may be an item to be displayed, such as a commodity or product, etc. Of course, the target object may also be a person, etc.

[0205] It can be understood that the display interface can provide an entry to a model library of objects to be displayed, and the user can open the model library and select one as a target object.

[0206] In one embodiment, a two-dimensional image of the object to be displayed can be captured, and then a three-dimensional model of the object to be displayed can be generated based on the two-dimensional image and stored in a model library. When a user needs to generate a display image of a certain object to be displayed, the user can select the object to be displayed, i.e., the target object, from the model library through a first selection operation, so that the three-dimensional model of the target object, i.e., the target model, can be displayed in the first area of ​​the display interface. In addition, the model library can be stored in a terminal or a server.

[0207] Similarly, the display interface may also provide a plurality of preset backgrounds to choose from. The user may select one of them as the target background through a first selection operation. The background image corresponding to the target background may serve as the display background of the target model. The background image of the target background may also be displayed in the first area. It is understood that the background image may be a color background image, or the background image may be a line drawing or a grayscale image.

[0208] The first area may be at least a partial area of ​​the display interface, for example, a partial area located at the center of the display interface.

[0209] The first area may have two canvases or layers, the bottom layer may display a background image of the target background, for example, the background image may occupy the entire first area, and the top layer may display an image of the target model.

[0210] In addition, the display interface can also provide an entrance to the lighting template library. Users can open the lighting template library through the display interface and select a target light from it. The target light is a virtual light that shines on the target model, which can change the light and shadow effects on the surface of the target model.

[0211] Of course, the user can also change the background image by reselecting the target background. In some embodiments, in response to a first adjustment operation on the target model in the first area, the target model displayed in the first area is updated based on the first adjustment operation. The user can also change the position of the 3D model in the background image, the display angle of the 3D model, etc. by rotating, translating, or scaling the 3D model (first adjustment operation).

[0212] When a rendering operation is detected, such as a click operation on an AI (Artificial Intelligence) image generation control, at least one display image can be displayed on the display interface. Each display image can be fused by a first sub-image at the top layer and a second sub-image at the bottom layer. The first sub-image can be obtained by rendering the target model based on the current target light, and the second sub-image can be an image generated by using an AI image generation model based on the current target light, the current background image, and the current target model. The AI ​​image generation model can be an AI output model provided in the relevant technology, such as Stable Diffusion (an open source AI image generation model).

[0213] The first sub-image can be superimposed on the target area of ​​the second sub-image to obtain a display image, and the target area corresponds to the area of ​​the target model in the background image, that is, in the first area, the position of the target model in the background image can be used as the target area. Since the second sub-image is obtained by the AI ​​image generation model, the items in the target area of ​​the second sub-image may change. Taking the target object as a camera as an example, the shape or details of the camera in the target area of ​​the second sub-image may be different from the target object, and may even become other types of objects. The first sub-image superimposed on the target area can enable the target object in the first sub-image to cover the items in the target area of ​​the second sub-image, so that the target object displayed in the display image is the item that the user actually wants to display.

[0214] It can be understood that the first sub-image can be the target object (such as an object) part in the display image, and the second sub-image serves as the final background of the target object. Since the target model in the first sub-image is rendered based on the target light, and the underlying second sub-image is also generated based on the target light, the light and shadow effects in the first sub-image and the second sub-image are basically the same. When the first sub-image and the second sub-image are superimposed and fused together, the overall light and shadow effects of the display image are better integrated, which improves the image quality and the display effect of the target object.

[0215] Figures 7a through 7c illustrate the operational flow of the display interface of the display image generation method provided in one embodiment of the present disclosure. Referring to Figure 7a, the display interface may display a display image generation page 700, with controls such as "Item," "Background," and "Lighting" displayed on the left. Clicking "Item" displays selectable objects from the model library of the object to be displayed on the right, such as Item 1, Item 2, Item 3, and Item 4 in the image. The user can select one of these objects as the target object.

[0216] Similarly, clicking "Background" displays previews of preset backgrounds in the background library on the right, allowing users to select a target background. Clicking "Lighting" displays lighting templates in the lighting template library on the right, allowing users to select a target light. Figure 7-a only shows the state diagram when clicking "Item."

[0217] After selecting the target object and target background, the first area 710 displays a target model 711 of the target object and a background image 712 of the target background. As can be seen, the target model 711 is displayed on top of the background image 712. The display position and angle of the target model 711 can be changed by rotating or translating it. It should be understood that the target light selected by the user may not be displayed in the first area 710.

[0218] As shown in Figure 7-c, when the preview effect in the first area 710 meets the requirements, by clicking the "AI Image Generation" control 730, the generated result, namely display image 741, can be displayed on the display interface. It can be understood that there can be multiple display images 741, each of which can be obtained by using the AI ​​image generation model once. Display image 741 can be displayed full screen or in the third area 740 of the display interface. The specific display location can be set according to the situation.

[0219] In some embodiments, the background image is a line drawing of the target background. It will be understood that in this embodiment, the original image of the optional preset background can be a color background image, which can be converted into a line drawing by preprocessing, such as using lineart (line drawing) preprocessing. The line drawing is a black and white or grayscale wireframe drawing, that is, a black and white (or grayish white) line drawing that only shows the shape outline of the object in the image without coloring. As shown in Figure 7-a, background image 712. By removing details such as color in the background image, when generating the second sub-image using the AI ​​image generation model, it is not limited to the color of the original background, thereby facilitating the generation of more diverse display images, or facilitating users to customize the style of the display image.

[0220] In some embodiments, step S601, in response to a first selection operation on a target object and a target background, displays a target model in a first area of ​​a display interface and displays a background image of the target background below the target model in the first area, which may include:

[0221] In response to a third selection operation on the target object, displaying a target model in the first area;

[0222] In response to the fourth selection operation on the target background, the original image corresponding to the target background is processed to obtain a line drawing of the target background, and the line drawing is displayed as a background image on the bottom layer of the target model.

[0223] After the user selects a target object, the corresponding target model can be displayed in the first area. If the target background is a color image, the original image of the target background (i.e., the color image) can be obtained and then processed. For example, lineart preprocessing can be used to obtain the corresponding line drawing. The line drawing can be displayed as the background image at the bottom layer of the target model, such as background image 712 in Figure 7-a.

[0224] Through the method of this embodiment, a line drawing of the target background can be obtained, and the color and other details in the background image can be removed from the line drawing. When the second sub-image is generated by using the AI ​​image generation model, it is not limited to the color of the original preset background, thereby facilitating the generation of more diverse display images, or facilitating users to customize the style of the display image.

[0225] In some embodiments, method 600 also includes: in response to a second selection operation on the target light, displaying a preview effect image in a second area of ​​the display interface, the preview effect image being an image of the target object obtained by rendering the target model based on the target light, and the image parameters of the first sub-image are higher than the image parameters of the preview effect image.

[0226] As shown in FIG. 7 - a , the second area 720 may display a partial area in the interface, which may partially overlap with the first area 710 , or may be located outside the first area 710 .

[0227] The second area can display a preview effect image, that is, a preview effect image obtained by rendering the target model and the target light. It can be understood that the preview effect image can only display the light and shadow effects of the target model without involving the display of the target background.

[0228] Image parameters can include display quality or resolution, among other things. The image parameters of the preview image can be set lower, thereby reducing rendering time and enabling a quick display of the lighting effects of the target model. It is understood that both the first sub-image and the preview image are images rendered based on the target light and the target object. The lighting effects of the target object in both images are the same, but the image parameters are different. The first sub-image is the final display image, and its image parameters can be higher, thereby providing a high-quality display image.

[0229] The preview rendering can be used to preview the light and shadow effects of the target model in real time, so as to avoid the need to regenerate the display diagram when the light and shadow effects are not suitable after the display diagram is generated, thereby improving the generation speed of the display diagram.

[0230] In some embodiments, the method 600 further includes: in response to an adjustment operation on the target light and / or the target model, updating the preview effect image based on the adjustment operation.

[0231] It is understood that the target lighting can be reset using the lighting template, and the lighting in the preview effect image can be updated in real time. When the position and angle of the target model in the first area are adjusted, the target model in the first area is updated in real time, and the preview effect image in the second area is also updated based on the target model adjustment. By updating the preview effect image in real time, users can directly view the lighting and shadow effects of the first sub-image, thereby promptly understanding whether the lighting and shadow effects of the target object in the display image meet the requirements, so as to quickly adjust them.

[0232] In some embodiments, the display interface also has an information input area, which is used to provide the AI ​​image generation model with image description information that can generate a display image.

[0233] As shown in Figure 7-a, the display interface also displays an information input area 750. The information input area 750 is an area for users to input image description information. Through this area, users can input some relevant descriptions (keywords or custom descriptions, etc.) about the display image to be generated, such as the description of the target object, display style, color, space, etc. These image description information can be used as input for the AI ​​image generation model, so that the background part of the display image can better meet the needs.

[0234] Of course, the information input area 750 can also provide some style scene selections. For example, clicking the "Expand" control can open Figure 7-b to expand the information input area 750. The area can include a first sub-area 751 and a second sub-area 752. The first sub-area 751 can display some optional styles (such as modern, simple, Japanese, European, etc.) and optional scenes (such as bedroom, living room, kitchen, dining room, etc.) for users to choose from. The second sub-area 752 can display a text input window, and users can enter keywords and custom descriptions by themselves. For example, the object to be displayed is a camera, the style is natural, and so on.

[0235] After selecting a scene style and adding a description, the user can click the "AI Image Generation" control to display Figure 7-c. Information input area 750 allows users to add some image description information for the generated presentation image, which helps the generated presentation image better meet user needs.

[0236] As shown in Figures 7-a and 7-c, in some embodiments, the second area 720 is a floating area of ​​the display interface, and at least one presentation image is displayed in the third area 740 of the display interface. The floating area can be freely dragged on the display interface and placed on the top display. The third area can be located on the right side of the display interface, and by clicking on one of the presentation images, it can be enlarged or displayed in full screen.

[0237] In this embodiment, the preview effect image, the display image, the background image and the target model can be displayed simultaneously on the same display interface, which is beneficial to the convenience of user use and the friendliness of the interface.

[0238] In some embodiments, step S602 displays at least one display image on a display interface in response to a rendering operation, including:

[0239] In response to the rendering operation, the target model is rendered based on the target light to obtain a first sub-image;

[0240] Fusing the target model and the background image to obtain a fused image;

[0241] Input the preset light description information of the target light and the fused image into the AI ​​image generation model to obtain the second sub-image;

[0242] The first sub-image is superimposed on the target area of ​​the second sub-image to obtain a display image, where the display image is one display image in the at least one display image, and the target area corresponds to the area of ​​the target model in the background image.

[0243] When a rendering operation is detected, an image of the target model under the target light can be rendered according to the target light and the target model selected by the user to obtain a first sub-image. It is understood that the first sub-image only contains the target object and does not have the surrounding background.

[0244] At the same time, the target model and the background image in the first region can be fused into a fused image. It will be appreciated that the target model and the background image in the first region are layered and not a single, integrated image, and the target model can be moved and rotated within the image. Fusion can be performed based on the current position of the target model within the background image to fuse the two into a single fused image.

[0245] Additionally, the lights in the lighting template can be configured with corresponding preset lighting descriptions. This information can include light type (point source, parallel light, ring light, etc.), color temperature, position, brightness, and more. The preset lighting descriptions can be determined based on the selected target lighting. This preset lighting description information and the fused image can be input into the AI ​​image generation model to generate the second sub-image.

[0246] Then the first sub-image can be superimposed on the target area of ​​the second sub-image to achieve fusion of the two. It can be understood that in the fused image, the target model can be located at the first position of the background image. After the AI ​​image generates the model, the first position can be used as the target area of ​​the second sub-image. The first sub-image is superimposed on the area to cover the objects generated according to the target model in the fused image. It can be understood that, for example, if the target object is a camera, after the AI ​​image generates the second sub-image, the original camera shape in the fused image may change, that is, it may be quite different from the actual structure of the target object, and may even become something other than a camera. Therefore, the original structure of the target object can be retained by superimposing the first sub-image on the second sub-image. At the same time, since the second sub-image is generated based on the fused image and the preset lighting description information of the target light, its lighting and shadow effects will be consistent with the first sub-image. For example, in the first sub-image, the target light illuminates the target model from the left, so the left side of the first sub-image is brighter, and there will be a corresponding shadow on the right side of the target area in the second sub-image. When the two are fused into a display image, the shadow in the second sub-image can be used as the shadow of the target object, thereby achieving consistency in lighting and shadow effects. The display effect and quality of the fused display image are better.

[0247] In some embodiments, the method 600 further includes:

[0248] Obtain image description information for generating display images;

[0249] Input the preset light description information of the target light and the fused image into the AI ​​image generation model to obtain the second sub-image, including:

[0250] The preset light description information, image description information and fused image of the target light are input into the AI ​​image generation model to obtain the second sub-image.

[0251] As shown in Figure 7-b, after the user sets the image description information by selecting or entering in the information input area, the image description information, preset lighting description information and fused image can be input into the AI ​​image generation model to generate a display image that can meet the user's image description information.

[0252] Of course, users can also select other information such as the target model's material and use it as input to the AI ​​image generation model. For example, the material information, preset lighting description information, and image description information can be combined as prompt information for the AI ​​image generation model, and then the prompt information and the fused image can be input into the AI ​​image generation model to obtain a display image.

[0253] In some embodiments, rendering the target model based on the target light to obtain a first sub-image includes:

[0254] Sending parameter information of the target light and position information of the target model to the server, so that the server renders the target model to obtain a first sub-image;

[0255] Receive the first sub-image rendered by the server;

[0256] Input the preset light description information of the target light and the fused image into the AI ​​image generation model to obtain the second sub-image, including:

[0257] Sending the preset light description information and the fused image to the server, so that the server uses the AI ​​image generation model to obtain a second sub-image based on the preset light description information and the fused image;

[0258] Receive the second sub-image sent by the server.

[0259] It can be understood that in this embodiment, the display interface can be a display interface of the terminal, which is mainly used to display various images and interface interactions, while tasks with high processor requirements such as image rendering and generation can be performed by the server.

[0260] The terminal may send parameter information of the target light (eg, light type, color temperature, position, brightness, etc. of the target light) to the server, and the server may render the first sub-image based on the information and send the first sub-image to the terminal.

[0261] Similarly, the terminal can send the preset lighting description information and the fused image to the server. The AI ​​image generation model in the server generates a second sub-image and sends it to the terminal. The terminal can receive the first and second sub-images and fuse and overlay them to obtain a display image.

[0262] In this embodiment, the image rendering and AI image generation model processing are implemented by the server, which can reduce the processing workload of the terminal and improve the processing speed.

[0263] Of course, in other embodiments, the superposition of the first sub-image and the second sub-image, or the generation of the preview effect image, etc. can also be implemented by the server. Of course, in some embodiments, all the display image generation steps can also be executed by the terminal.

[0264] FIG8 is a flowchart of a method for generating a display image provided by another embodiment of the present disclosure. Referring to FIG8 , an embodiment of the present disclosure provides a method 800 for generating a display image, comprising steps S801 to S807 .

[0265] In step S801, the user uploads the model (3D model of the object to be displayed) file (including but not limited to max, fbx, skp, glb, 3dm and other file formats) through the client (terminal) to the server (cloud or server) for parsing. The server parses the model file into a model file compatible with both the client and server rendering (including the model's size, material information, etc.) according to the type of the model file, and stores it in the model list (the model library of the object to be displayed).

[0266] In step S802, the user selects the product (target object) to be photographed from the uploaded model list, selects a background image (the background image of the target background, which can be a background wireframe image) from the background template list, and selects a lighting template (target lighting) from the lighting template list.

[0267] In step S803, the client renders through a browser (the display interface can be a browser interface) to display a preview effect (the target model and background image are displayed in the first area), and at the same time opens a small window to display the actual rendering effect (preview effect image). For example, the client creates two canvases in the browser, stacks them one on top of the other, uses the lower canvas as a 2D (two-dimensional) operation canvas, and places the background wireframe (background image) into the 2D canvas; uses the upper canvas as a 3D (three-dimensional) operation canvas, places the selected 3D product (target model) into the 3D canvas, and draws a low-precision model for preview based on the product's material and geometric data. At the same time, a small window (second area) is opened to display the actual rendering effect (preview effect image) of the 3D model (target model) under the current lighting template (target lighting) for confirming the final rendering effect.

[0268] In step S804, the user moves, rotates, or scales the product in the client's interactive viewport, or switches lighting template effects. The client monitors mouse events on the canvas, allowing the user to move, rotate, or scale the main product (target model) to better blend in with the background. The user can also change the lighting effects by reselecting a lighting template from the lighting template list.

[0269] In step S805, the small window updates the rendering effect (preview effect picture) of the product under the light in real time (adjustment operation) according to the user operation for the user's reference.

[0270] In step S806, the user selects output parameters to control the final output and initiates AI image generation. The user selects prompts such as style, environment, and color scheme, or enters prompts (image descriptions) as positive or negative incantations (prompts) for the final Stable Diffusion (AI image generation model), and then initiates AI image generation.

[0271] Step S807: Generate a picture (display picture) by using Stable Diffusion and image synthesis technology. Step S807 may specifically include the following steps:

[0272] A. The client first initiates high-precision server-side rendering based on the selected product (target model), the product's current matrix information (movement, rotation, scaling) (i.e., the adjusted target model), and the selected lighting template (target light) to obtain the first sub-image.

[0273] B. Combine the 3D canvas and 2D canvas content to obtain a fused image of the 3D product and the 2D background line drawing.

[0274] C. Convert the material of the 3D model (target model) and the relative position, brightness, color, and other information of the light template and the model into a spell (preset light description information). Combine this with the user-selected output parameter spell (image description information) as the input for Stable Diffusion. Use the fused image from step B for image generation to obtain a second sub-image, thereby achieving deep fusion of the product, light template, and background.

[0275] D. Overlay the product rendering (transparent PNG image) (first sub-image) obtained in step A onto the AI ​​image (second sub-image) output by Stable Diffusion, and use image synthesis technology to process the synthesized image so that the product can better blend into the background.

[0276] This method allows for better control over the preview effect, allowing users to preview the final rendered lighting and shadow effects of the product in real time during operation. It also improves the quality of AI-generated images, achieving a better integration of the product and the background.

[0277] FIG9 is a schematic block diagram of a display image generating device provided by an embodiment of the present disclosure. Referring to FIG9 , the present disclosure provides a display image generating device, including the following units:

[0278] a fourth display unit 901 for displaying a target model in a first area of ​​the display interface in response to a first selection operation on the target object and the target background, and displaying a background image of the target background on a bottom layer of the target model in the first area, wherein the target model is a three-dimensional model of the target object;

[0279] The fifth display unit 902 is used to display at least one display image on the display interface in response to the rendering operation, wherein the display image in the at least one display image is a fusion of a first sub-image and a second sub-image located at the bottom layer of the first sub-image, and the first sub-image is an image of the target object obtained by rendering the target model based on the selected target light, and the second sub-image is an image obtained by using the AI ​​image generation model and based on the target light, background image and target model.

[0280] In some embodiments, the apparatus 900 further includes:

[0281] The sixth display unit is used to display a preview effect image in the second area of ​​the display interface in response to the second selection operation of the target light. The preview effect image is an image of the target object obtained by rendering the target model based on the target light, and the image parameters of the first sub-image are higher than the image parameters of the preview effect image.

[0282] In some embodiments, the background image is a line drawing of the target background.

[0283] In some embodiments, the apparatus 900 further includes:

[0284] The adjustment unit is configured to respond to an adjustment operation on the target light and / or the target model and update the preview effect image based on the adjustment operation.

[0285] In some embodiments, the display interface also has an information input area, which is used to provide the AI ​​image generation model with image description information that can generate a display image.

[0286] In some embodiments, the second area is a floating area of ​​the display interface, and the at least one display image is displayed in a third area of ​​the display interface.

[0287] In some embodiments, the fourth display unit 901 is further used to:

[0288] In response to a third selection operation on the target object, displaying a target model in the first area;

[0289] In response to the fourth selection operation on the target background, the original image corresponding to the target background is processed to obtain a line drawing of the target background, and the line drawing is displayed as a background image on the bottom layer of the target model.

[0290] In some embodiments, the fifth display unit 902 is further used to:

[0291] In response to the rendering operation, the target model is rendered based on the target light to obtain a first sub-image;

[0292] Fusing the target model and the background image to obtain a fused image;

[0293] Input the preset light description information of the target light and the fused image into the AI ​​image generation model to obtain the second sub-image;

[0294] The first sub-image is superimposed on the target area of ​​the second sub-image to obtain a display image, where the display image is one display image in the at least one display image, and the target area corresponds to the area of ​​the target model in the background image.

[0295] In some embodiments, the fifth display unit 902 is further used to:

[0296] Obtain image description information for generating display images;

[0297] The preset light description information, image description information and fused image of the target light are input into the AI ​​image generation model to obtain the second sub-image.

[0298] In some embodiments, the fifth display unit 902 is further used to:

[0299] Sending parameter information of the target light and position information of the target model to the server, so that the server renders the target model to obtain a first sub-image;

[0300] Receive the first sub-image rendered by the server;

[0301] Sending the preset light description information and the fused image to the server, so that the server uses the AI ​​image generation model to obtain a second sub-image based on the preset light description information and the fused image;

[0302] Receive the second sub-image sent by the server.

[0303] For the description of specific functions and examples of each unit of the device in the embodiment of the present disclosure, please refer to the relevant description of the corresponding steps in the above-mentioned embodiment of the display diagram generation method, which will not be repeated here.

[0304] The third aspect of the present disclosure is described as follows:

[0305] In related technologies, in order to meet the personalized needs of users, it is necessary to fuse the scene information specified by the user (such as the prompt words of the scene effect) with the product image specified by the user to form a fusion effect picture. However, the fusion effect picture generated by the existing method relying solely on the scene information may not meet the user's expectations, thereby reducing the user experience.

[0306] The disclosed solution provides an image generation method to fuse a specified product image with a background image, thereby obtaining an effect image that meets user expectations, thereby improving user experience.

[0307] Specifically, Figure 10 is a schematic flow chart 1 of an image generation method according to an embodiment of the present disclosure. The method can be optionally applied to electronic devices, such as personal computers, servers, server clusters, and other electronic devices.

[0308] Furthermore, the method includes at least part of the following contents. As shown in FIG10 , the image generation method includes:

[0309] Step S1001: When it is determined that a wireframe image of a foreground image and a background image of a target object are displayed in the current operation area, an initial fusion effect image is displayed in response to a first image generation operation.

[0310] Here, the initial fusion effect image is obtained by fusing the foreground image of the target object with the wireframe image of the target background image.

[0311] Step S1002: In response to the second image generation operation, a target fusion effect image is displayed.

[0312] Here, the target fusion effect image is obtained by performing image processing on the initial fusion effect image using image effect description parameters, and is used to represent a simulated effect image after the target object and the target background image are fused.

[0313] Furthermore, in a specific example, the target fusion effect diagram can be obtained by using the following two methods, which can specifically include one of the following two methods:

[0314] Mode 1: that is, in response to the second image generation operation, displaying the target fusion effect image (for example, step S1002 described above), specifically including:

[0315] Step S1002-1: In response to the second image generation operation, N candidate fusion effect images are displayed.

[0316] Here, each of the N candidate fusion effect images is obtained by performing image processing on the initial fusion effect image using image effect description parameters or adjusted image effect description parameters; and N is a positive integer greater than or equal to 1.

[0317] Furthermore, when N is greater than or equal to 2, the candidate fusion effect graphs in the N candidate fusion effect graphs are different from each other, so that it is convenient for the user to select a fusion effect graph that meets the expected needs.

[0318] Step S1002-2: in response to a selection operation on a candidate fusion effect graph among the N candidate fusion effect graphs, obtaining the target fusion effect graph.

[0319] Here, the target fusion effect graph is the candidate fusion effect graph selected by the selection operation.

[0320] For example, in one example, after the initial fusion effect image and image effect description parameters are determined, in response to a second image generation operation, such as a user clicking an image generation button, four candidate fusion effect images are obtained, as shown in Figure 11. These are displayed in areas other than the operation area of ​​the display interface, such as the fusion effect display area, for user selection. Furthermore, if the user selects Image 2, Image 2 can be selected as the target fusion effect image and displayed in the current operation area.

[0321] In this way, the disclosed solution provides a specific example of obtaining a target fusion effect diagram, namely, using image description effect parameters to perform image processing on the initial fusion effect diagram to obtain N candidate fusion effect diagrams, and then selecting the target fusion effect diagram from the N candidate fusion effect diagrams. In this way, it is convenient for users to quickly browse different fusion effect diagrams to increase the probability of users selecting a satisfactory fusion effect diagram, and further improve the user experience without increasing cumbersome operations.

[0322] Furthermore, in one example, a pre-trained model can be used to obtain N candidate fusion renderings. In this way, multiple candidate fusion renderings can be quickly obtained, making it easier for users to select a satisfactory target fusion rendering, reducing user waiting time, and further improving the user experience. Specifically, the above-mentioned display of N candidate fusion renderings in response to the second image generation operation (for example, step S1002-1 described above) specifically includes:

[0323] In response to the second image generation operation, the image effect description parameters and the initial fusion effect graph are input into the first model to obtain the N candidate fusion effect graphs.

[0324] Here, the first model is used to perform image processing on the initial fusion effect image based on the image effect description parameters or the adjusted image effect description parameters to obtain N candidate fusion effect images.

[0325] Furthermore, in one example, the first model is an image generation model with image generation capability, such as a stable diffusion model.

[0326] Mode 2: namely, in response to the second image generation operation, displaying the target fusion effect image (for example, step S1002 described above), specifically including:

[0327] In response to the second image generation operation, the image effect description parameters and the initial fusion effect graph are input into the second model to obtain the target fusion effect graph.

[0328] Here, the second model is used to perform image processing on the initial fusion effect image based on image effect description parameters to obtain a target fusion effect image.

[0329] Furthermore, in one example, the second model is an image generation model with image generation capability, such as a stable diffusion model.

[0330] In this way, after responding to the second image generation operation, the second model can be directly used to quickly obtain a simulated effect image that satisfies the user and is a fusion of the target object and the target background image, which reduces the user's waiting time and further improves the user experience.

[0331] In this way, the disclosed solution can utilize the foreground image of the target object and the wireframe image of the target background image to obtain an initial fusion effect image, and perform image processing on the initial fusion effect image based on the image effect description parameters to obtain a simulated effect image after the target object and the target background image are fused. In other words, the disclosed solution can make full use of the image effect description parameters and the wireframe image of the target background image configured by the user to better fuse the target object and the target background image, thereby obtaining a target fusion effect image that meets user needs, thereby greatly improving the user experience.

[0332] Furthermore, compared with the solutions in the related art that directly generate background images (or scene effects) based on prompt words, etc., since the solution disclosed herein not only uses the image effect description parameters configured by the user, but also adopts the wireframe diagram of the target background image specified by the user to limit the scene effects in the subsequently generated target fusion effect diagram, the solution disclosed herein can control the scene effects in the target fusion effect diagram so that the scene effects in the target fusion effect diagram meet the user's expectations, thereby meeting the user's personalized design needs and improving the user experience.

[0333] Figure 12 is a second schematic flow chart of an image generation method according to an embodiment of the present disclosure. This method can optionally be applied to electronic devices, such as personal computers, servers, and server clusters. It is understood that the relevant content of the method shown in Figure 10 above can also be applied to this example, and the relevant content will not be repeated in detail in this example.

[0334] Furthermore, the method includes at least part of the following contents. As shown in FIG12 , the image generation method includes:

[0335] Step S1201: When it is determined that a wireframe image of a foreground image and a background image of a target object is displayed in the current operation area, an initial fusion effect image is displayed in response to a first image generation operation.

[0336] Here, the initial fusion effect image is obtained by fusing the foreground image of the target object with the wireframe image of the target background image.

[0337] Step S1202: In response to the second image generation operation, a target fusion effect image is displayed.

[0338] Here, the target fusion effect image is obtained by performing image processing on the initial fusion effect image using image effect description parameters, and is used to represent a simulated effect image after the target object and the target background image are fused.

[0339] Here, regarding the specific method of generating the target fusion effect diagram, please refer to the above example and will not be repeated here.

[0340] Step S1203: In response to the third image generation operation, an enhanced fusion effect image is obtained.

[0341] Here, the enhanced fusion effect image is obtained by overlaying the foreground image of the target object on the area where the target object is located in the target fusion effect image.

[0342] That is to say, in this example, in order to further improve the fusion effect and ensure that the target object in the fusion effect image is clearer, after obtaining the target fusion effect image, further enhancement processing can be performed, for example, the foreground image of the target object is overlaid on the area where the target object is located in the target fusion effect image to replace the target object in the target fusion effect image, and then the processed target fusion effect image is obtained, that is, the enhanced fusion effect image.

[0343] For example, in one example, after displaying the target fusion effect diagram, if the user needs to further enhance the target object in the displayed target fusion effect diagram, the user can click the image enhancement button to cover the foreground image of the target object on the area where the target object is located in the target fusion effect diagram to obtain the processed target fusion effect diagram (that is, the enhanced fusion effect diagram described above).

[0344] In this way, the disclosed solution provides a specific example of enhancing the image effect of the target object in the target fusion rendering, thereby ensuring that the target object required by the user and the target background image can be perfectly combined to obtain a rendering that satisfies the user (such as an enhanced fusion rendering), thereby improving the user experience.

[0345] In a specific example of the disclosed solution, the foreground image of the target object may be obtained in the following manner. Specifically, before determining a wireframe image showing the foreground image of the target object and the target background image in the current operation area (for example, before step S1001 or step S1201 described above), the method further includes:

[0346] Displaying at least an initial image containing the target object in the current operation area;

[0347] In response to an object recognition operation on a target object in the initial image, a foreground image of the target object is obtained.

[0348] For example, in one example, in response to an object recognition operation on the target object in the initial image, target object extraction is performed on the initial image containing the target object to remove the background portion of the initial image and obtain a foreground portion containing the target object.

[0349] That is to say, in one example, after the user uploads the initial image containing the target object, it is necessary to perform object recognition on the target object in the initial image, such as clicking the smart cutout button to obtain the foreground image of the target object. In this way, the target object required by the user can be quickly obtained, laying the foundation for better integration of the target object with the target background image in the subsequent process.

[0350] Figure 13 is a third schematic flow chart of an image generation method according to an embodiment of the present disclosure. This method can optionally be applied to electronic devices, such as personal computers, servers, and server clusters. It is understood that the relevant content of the methods shown in Figures 10 and 12 above can also be applied to this example, and the relevant content will not be repeated in detail in this example.

[0351] Furthermore, the method includes at least part of the following contents. As shown in FIG13 , the image generation method includes:

[0352] Step S1301: displaying at least an initial image containing the target object in the current operation area.

[0353] Step S1302: In response to an object recognition operation on a target object in the initial image, a foreground image of the target object is obtained.

[0354] Step S1303: display at least the target background image in the current operation area.

[0355] At this time, the foreground image of the target object is also displayed in the current operation area.

[0356] Step S1304: In response to the wireframe extraction operation on the target background image, a wireframe image of the target background image is obtained.

[0357] That is to say, in one example, after the user uploads the target background image, it is necessary to perform a wireframe extraction operation on the uploaded target background image. For example, the user clicks the wireframe extraction button for the uploaded target background image to obtain the wireframe image of the target background image. In this way, the wireframe image of the target background image required by the user can be quickly obtained, which makes it easier for the user to control the scene effect required for the target object, so as to obtain the scene effect that meets the user's expectations, laying the foundation for better integration of the target object and the target background image in the future.

[0358] It should be noted that the execution order of the method of generating the foreground image of the target object (i.e., step S1301 and step S1302) and the method of generating the wireframe image of the target background image (i.e., step S1303 and step S1304) can be swapped or executed simultaneously, and the present disclosure does not limit this; for example, step S1303 and step S1304 are executed first, and then step S1301 and step S1302 are executed; or, step S1301 and step S1303 are executed first, that is, the initial image and the target background image are displayed in the current operation area, and then the above-mentioned processing is performed on the initial image and the target background image respectively.

[0359] Furthermore, in one example, the obtained wireframe image can be edited in the following manner, thereby obtaining a wireframe image of the target background image that satisfies the user, laying the foundation for subsequently obtaining a scene effect that meets the user's expectations. Specifically, after obtaining the wireframe image of the target background image in response to the wireframe extraction operation on the target background image (for example, after step S1304 described above), the following further steps are included:

[0360] In response to a wireframe editing operation on the wireframe image of the target background image, a wireframe image after the wireframe editing operation is obtained.

[0361] That is to say, in this example, if the user needs to make further adjustments to the wireframe diagram obtained in step S1304, the user can perform wireframe editing operations on the obtained wireframe diagram to obtain a wireframe diagram that satisfies the user, thereby achieving control over the scene effect in the target fusion rendering; for example, the user can use the erase function or the partial redraw function to edit the obtained wireframe diagram.

[0362] It should be noted that the wireframe editing operations in this example include but are not limited to erasing, partial redrawing and other editing operations.

[0363] Furthermore, it should be noted that if the user performs a wireframe editing operation on the wireframe diagram obtained in step S1304, then in the subsequent image generation process, processing will be performed based on the wireframe diagram after the wireframe editing operation. For example, steps S1001 and S1201 in the above example are both processed based on the wireframe diagram after the wireframe editing operation, so as to achieve control of the scene effect in the target fusion effect diagram.

[0364] Step S1305: When it is determined that the wireframe images of the foreground image and the background image of the target object are displayed in the current operation area, an initial fusion effect image is displayed in response to the first image generation operation.

[0365] Here, the initial fusion effect image is obtained by fusing the foreground image of the target object with the wireframe image of the target background image.

[0366] Step S1306: In response to the second image generation operation, a target fusion effect image is displayed.

[0367] Here, the target fusion effect image is obtained by performing image processing on the initial fusion effect image using image effect description parameters, and is used to represent a simulated effect image after the target object and the target background image are fused.

[0368] In this way, the disclosed solution provides a specific example of obtaining a foreground image and a wireframe image. In this example, a wireframe image can be extracted from a target background image input by a user. Moreover, when adjustment is required, the user can be supported to adjust the extracted wireframe image. In this way, the user can control the scene effect in the target fusion rendering, so that the scene effect in the target fusion rendering is more in line with the user's expectations.

[0369] In addition, since the disclosed solution uses the foreground image of the target object obtained after removing the background part of the initial image during the fusion processing, the interference elements in the initial image are removed, making it easier to fuse the target object with the target background image to obtain a target fusion effect image that satisfies the user.

[0370] Figure 14-a is a fourth schematic flow chart of an image generation method according to an embodiment of the present disclosure. This method can optionally be applied to electronic devices, such as personal computers, servers, and server clusters. It is understood that the relevant content of the methods shown in Figures 10, 12, and 13 above can also be applied to this example, and the relevant content will not be repeated in detail in this example.

[0371] Furthermore, the method includes at least part of the following contents. As shown in FIG14-a, the image generation method includes:

[0372] Step S1401: displaying at least an initial image containing the target object in the current operation area.

[0373] Step S1402: In response to an object recognition operation on a target object in the initial image, a foreground image of the target object is obtained.

[0374] Step S1403: display at least the target background image in the current operation area.

[0375] At this time, the foreground image of the target object is also displayed in the current operation area.

[0376] Step S1404: In response to the wireframe extraction operation on the target background image, a wireframe image of the target background image is obtained.

[0377] Here, regarding the method of generating the foreground image of the target object and the method of generating the wireframe image of the target background image, reference may be made to the above examples, which will not be described in detail here.

[0378] Here, regarding the execution order of steps S1401 to S1404, please refer to the relevant descriptions of steps S1301 to S1304 mentioned above, which will not be repeated here.

[0379] Step S1405: When it is determined that the wireframe images of the foreground image of the target object and the target background image are displayed in the current operation area, the positional relationship between the wireframe images of the foreground image of the target object and the target background image in the current operation area is adjusted by at least one of the following methods:

[0380] Here, the specific methods include:

[0381] Mode 1: In response to a layout adjustment operation on the foreground image of the target object, obtaining the foreground image after the layout adjustment operation;

[0382] Mode 2: In response to a layout adjustment operation on the wireframe image of the target background image, a wireframe image after the layout adjustment operation is obtained.

[0383] That is, in one example, the user may perform a layout adjustment operation on the foreground image of the target object so that the positional relationship between the foreground image after the layout adjustment operation and the wireframe image of the target background image meets the user's needs; or, in another example, the user may perform a layout adjustment operation on the wireframe image of the target background image so that the positional relationship between the wireframe image after the layout adjustment operation and the foreground image of the target object meets the user's needs; or, in yet another example, layout adjustment operations are performed on the foreground image of the target object and the wireframe image of the target background respectively so that the positional relationship between the foreground image after the layout adjustment operation and the wireframe image after the layout adjustment operation meets the user's needs.

[0384] It should be noted that the layout adjustment operations in this example include, but are not limited to, at least one of the following: scaling, rotating, moving, and other adjustment operations. Furthermore, in one example, after the layout adjustment operations, the size of the target object's foreground image matches the size of the target background's wireframe image, for example, the two are of equal size, to facilitate better fusion. For example, during the enhancement process of the resulting target fusion rendering, the equal size of the foreground image and wireframe image enables the target object's foreground image to better cover the target object's area in the target fusion rendering, thereby facilitating better fusion.

[0385] Furthermore, in this example, if the user performs a layout adjustment operation on the foreground image of the target object, the subsequent image generation process can be processed based on the foreground image after the layout adjustment operation. For example, steps S1001, S1201 and S1305 in the above example are processed based on the foreground image after the layout adjustment operation.

[0386] Alternatively, if the user performs a layout adjustment operation on the wireframe diagram of the target background, subsequent image generation processes can be processed based on the wireframe diagram after the layout adjustment operation. For example, steps S1001, S1201 and S1305 in the above example are processed based on the wireframe diagram after the layout adjustment operation.

[0387] Alternatively, if the user performs layout adjustment operations on the foreground image of the target object and the wireframe image of the target background respectively, the subsequent image generation process can be processed based on the foreground image after the layout adjustment operation and the wireframe image after the layout adjustment operation. For example, steps S1001, S1201 and S1305 in the above example are processed based on the foreground image after the layout adjustment operation and the wireframe image after the layout adjustment operation.

[0388] Step S1406: In response to the first image generation operation, an initial fusion effect image is displayed.

[0389] Here, the initial fusion effect image is obtained by fusing the foreground image of the target object with the wireframe image of the target background image.

[0390] Step S1407: In response to the second image generation operation, a target fusion effect image is displayed.

[0391] Here, the target fusion effect image is obtained by performing image processing on the initial fusion effect image using image effect description parameters, and is used to represent a simulated effect image after the target object and the target background image are fused.

[0392] Furthermore, in one example, the image effect description parameters may be obtained in the following manner so as to facilitate image processing using the image effect description parameters. Specifically, before displaying the target fusion effect image in response to the second image generation operation (for example, before step S1407 described above), the method further includes:

[0393] In response to the input operation, a parameter configuration interface is displayed, wherein the parameter configuration interface is used to input image effect description parameters; here, the image effect description parameters include but are not limited to at least one of the following: theme parameters, color parameters, and scene parameters. For example, as shown in FIG14-b, the parameter configuration interface includes three categories of parameters, namely theme, color, and scene. Each category of parameters includes multiple parameter setting values ​​for the user to select. In this way, the scene effect is configured to obtain a scene effect that meets the user's expectations. Here, FIG14-b is only an example. In actual application, it can be set according to actual conditions.

[0394] It should be pointed out that, in this example, the timing for obtaining the image effect description parameters may be before step S1401 (or step S1403), or may be after step S1405 and before step S1406, or may be after step S1406 and before step S1407. The disclosed solution does not impose any specific restrictions on this.

[0395] For example, in one example, first, in response to an input operation, such as a user clicking a parameter configuration button, a parameter configuration interface is displayed for the user to input image effect description parameters; secondly, after determining the image effect description parameters, and when the foreground image of the target object and the wireframe image of the target background that the user needs to fuse are displayed in the current operation area, in response to a layout adjustment operation for the foreground image and / or wireframe image, such as the user performing a layout adjustment operation on the selected foreground image to obtain a new positional relationship between the foreground image and the wireframe image; thirdly, after obtaining the new positional relationship, in response to a first image generation operation, such as the user clicking a first image generation button, an initial fusion effect image is obtained; finally, in response to a second image generation operation for the initial fusion effect image, such as the user clicking a second image generation button, at this time, the initial fusion effect image can be processed according to the image effect description parameters to obtain a target fusion effect image.

[0396] Alternatively, in another example, first, when the foreground image of the target object and the wireframe image of the target background that the user needs to fuse are displayed in the current operation area, in response to the layout adjustment operation for the foreground image and / or the wireframe image, such as the user performs a layout adjustment operation on the selected foreground image, a new positional relationship between the foreground image and the wireframe image is obtained; secondly, after obtaining the new positional relationship, in response to the input operation, such as the user clicking the parameter configuration button, a parameter configuration interface is displayed for the user to input the image effect description parameters; thirdly, after determining the image effect description parameters, in response to the first image generation operation, such as the user clicking the first image generation button, an initial fusion effect image is obtained; finally, in response to the second image generation operation for the initial fusion effect image, such as the user clicking the second image generation button, at this time, the initial fusion effect image can be processed according to the image effect description parameters to obtain the target fusion effect image.

[0397] Alternatively, in another example, first, when the foreground image of the target object and the wireframe image of the target background that the user needs to fuse are displayed in the current operation area, in response to the layout adjustment operation for the foreground image and / or the wireframe image, such as performing a layout adjustment operation on the selected foreground image, a new positional relationship between the foreground image and the wireframe image is obtained; secondly, after obtaining the new positional relationship, in response to the first image generation operation, such as the user clicking the first image generation button, an initial fusion effect image is obtained; thirdly, in response to the input operation, such as the user clicking the parameter configuration button, a parameter configuration interface is displayed for the user to input the image effect description parameters; finally, after determining the image effect description parameters, in response to the second image generation operation for the initial fusion effect image, such as the user clicking the second image generation button, at this time, the initial fusion effect image can be processed according to the image effect description parameters to obtain the target fusion effect image.

[0398] In this way, the disclosed solution provides a specific example of obtaining a foreground image after a layout adjustment operation and / or a wireframe image after a layout adjustment operation. In this way, the user can intuitively adjust the size, position, etc. of the target object to the expected scene to obtain a layout that meets the user's needs, thereby enabling the target object and the target background image to be better integrated, and obtaining a target fusion effect image that satisfies the user, meeting the user's personalized design needs, and improving the user experience.

[0399] The following further illustrates the disclosed solution with reference to specific examples. The disclosed solution proposes an image generation method that can better combine the product specified by the user with the required actual scene to obtain a product rendering after the two are fused.

[0400] Specifically, as shown in Figure 15, the core steps include:

[0401] Step 1: Obtain the main product image uploaded by the user (ie, the initial image corresponding to the target object mentioned above).

[0402] Step 2: Perform object recognition on the main product image to obtain the foreground image of the main product; for example, the user clicks the smart cutout button for the main product image to generate a transparent background image and place it on the canvas (i.e., corresponding to the operation area described above).

[0403] Step 3: Obtain the background image uploaded by the user (corresponding to the target background image mentioned above).

[0404] Step 4: Extract the wireframe of the background image to obtain a wireframe diagram of the background image; for example, when the user clicks a wireframe extraction button for the background image, a wireframe diagram is generated and placed on the canvas.

[0405] It should be noted that if the user needs to further adjust the extracted wireframe, the user can use the erase function or the partial redraw function to edit the obtained wireframe.

[0406] Step 5: Adjust the layout of the obtained foreground image and / or wireframe image, for example, the user scales, rotates, and moves the foreground image and / or wireframe image to obtain a layout that satisfies the user.

[0407] Step 6: Obtain the output parameters input by the user (ie, corresponding to the image effect description parameters described above), such as obtaining the output parameters such as theme, color, scene, etc. input by the user.

[0408] Step 7: Synthesize the images in the current canvas (i.e., the wireframe images of the foreground image and background image of the main product) to obtain a product-background fusion image of the same size (i.e., corresponding to the initial fusion effect image described above).

[0409] Step 8: Combine the output parameters and perform image processing on the product-background fusion image. For example, input the output parameters and the product-background fusion image into the image generation model (corresponding to the second model described above, such as the stable diffusion model) to obtain an artificial intelligence (AI) effect image (corresponding to the target fusion effect image described above).

[0410] Step 9: Use image synthesis technology to synthesize the foreground image of the main product and the AI ​​rendering to obtain the final product rendering (which corresponds to the enhanced fusion rendering described above).

[0411] In summary, compared with related technologies, the image generation method proposed in the present disclosure has the following advantages, including:

[0412] First, the scene effects are controllable. Compared to the solutions in related technologies that directly generate renderings based on scene information, the disclosed solution, when generating the scene effects in the target fusion rendering, not only needs to refer to the scene information input by the user (i.e., the image effect description parameters described above), but also needs to refer to the wireframe of the background image specified by the user. In this way, the user can control the scene effects in the target fusion rendering to obtain the scene effects that meet the user's expectations.

[0413] Second, it is highly editable. Compared to related art solutions that fuse user-specified scene information with user-specified product images, the disclosed solution provides a function for adjusting the positional relationship between images. For example, users can adjust the layout of the foreground image and / or background image wireframes of the product image to obtain a layout that meets user needs. In addition, users can directly edit the wireframe of the background image. This meets the user's personalized design needs and enables better integration of product images and background images.

[0414] Third, the user experience is better. The disclosed solution effectively integrates the product into the user's expected scene effect based on the user's actual needs, so as to obtain user-satisfied product renderings, thereby further improving the user experience.

[0415] The present disclosure further provides an image generating device, as shown in FIG16 , comprising:

[0416] Processing unit 1601 is configured to, upon determining that a wireframe image of a target object's foreground image and a target background image are displayed in a current operation area, generate an initial fused effect image in response to a first image generation operation; the initial fused effect image is obtained by fusing the wireframe image of the target object's foreground image and the target background image;

[0417] A display unit 1602 is used to display the initial fusion effect diagram;

[0418] The processing unit 1601 is further configured to obtain a target fusion effect image in response to the second image generation operation; wherein the target fusion effect image is obtained by performing image processing on the initial fusion effect image using image effect description parameters, and is used to represent a simulated effect image after the target object and the target background image are fused;

[0419] The display unit 1602 is also used to display the target fusion effect diagram.

[0420] In a specific example of the present disclosure,

[0421] The processing unit is specifically configured to obtain N candidate fusion effect images in response to the second image generation operation; each candidate fusion effect image in the N candidate fusion effect images is obtained by performing image processing on the initial fusion effect image using the image effect description parameter or the adjusted image effect description parameter; N is a positive integer greater than or equal to 1; and obtain the target fusion effect image in response to a selection operation on a candidate fusion effect image in the N candidate fusion effect images, wherein the target fusion effect image is the candidate fusion effect image selected by the selection operation;

[0422] The display unit is further used to display the N candidate fusion effect images.

[0423] In a specific example of the disclosed solution, the processing unit is specifically configured to:

[0424] In response to a second image generation operation, the image effect description parameter and the initial fusion effect graph are input into the first model to obtain the N candidate fusion effect graphs;

[0425] The first model is used to perform image processing on the initial fusion effect image based on the image effect description parameters or the adjusted image effect description parameters to obtain N candidate fusion effect images.

[0426] In a specific example of the disclosed solution, the processing unit is specifically configured to:

[0427] In response to a second image generation operation, the image effect description parameters and the initial fusion effect graph are input into a second model to obtain the target fusion effect graph;

[0428] The second model is used to perform image processing on the initial fusion effect image based on image effect description parameters to obtain a target fusion effect image.

[0429] In a specific example of the disclosed solution, the processing unit is further configured to:

[0430] In response to the third image generation operation, an enhanced fusion effect image is obtained; the enhanced fusion effect image is obtained by overlaying the foreground image of the target object on the area where the target object is located in the target fusion effect image;

[0431] The display unit is also used to display the enhanced fusion effect diagram.

[0432] In a specific example of the present disclosure,

[0433] The display unit is further configured to display at least an initial image containing the target object in the current operation area;

[0434] The processing unit is further configured to obtain a foreground image of the target object in response to an object recognition operation on the target object in the initial image;

[0435] The display unit is further configured to display a foreground image of the target object.

[0436] In a specific example of the present disclosure,

[0437] The display unit is further configured to display at least the target background image in the current operation area;

[0438] The processing unit is further configured to obtain a wireframe image of the target background image in response to a wireframe extraction operation on the target background image;

[0439] The display unit is further used to display the wireframe diagram of the target background image.

[0440] In a specific example of the present disclosure,

[0441] The processing unit is further configured to obtain a wireframe image after the wireframe editing operation is performed on the wireframe image of the target background image in response to the wireframe editing operation;

[0442] The display unit is also used to display the wireframe diagram after the wireframe editing operation.

[0443] In a specific example of the disclosed solution, the processing unit is further configured to:

[0444] The positional relationship between the foreground image of the target object and the wireframe image of the target background image in the current operation area is adjusted by at least one of the following methods:

[0445] In response to a layout adjustment operation on the foreground image of the target object, obtaining a foreground image after the layout adjustment operation;

[0446] In response to the layout adjustment operation on the wireframe image of the target background image, a wireframe image after the layout adjustment operation is obtained.

[0447] For the description of specific functions and examples of each unit of the device in the embodiment of the present disclosure, please refer to the relevant description of the corresponding steps in the embodiment of the image generation method, which will not be repeated here.

[0448] In the technical solutions disclosed herein, the acquisition, storage, and application of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0449] Figure 17 is a structural block diagram of an electronic device according to an embodiment of the present disclosure. As shown in Figure 17, the electronic device includes: a memory 1710 and a processor 1720, and the memory 1710 stores a computer program that can be run on the processor 1720. The number of memories 1710 and processors 1720 can be one or more. The memory 1710 can store one or more computer programs. When the one or more computer programs are executed by the electronic device, the electronic device executes the above-mentioned image display method or display image generation method or image generation method embodiment. The electronic device may also include: a communication interface 1730 for communicating with external devices and performing data exchange and transmission.

[0450] If the memory 1710, processor 1720, and communication interface 1730 are implemented independently, the memory 1710, processor 1720, and communication interface 1730 can be interconnected via a bus and communicate with each other. This bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. This bus can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, FIG17 shows only one thick line, but this does not mean that there is only one bus or only one type of bus.

[0451] Optionally, in a specific implementation, if the memory 1710, the processor 1720 and the communication interface 1730 are integrated on a chip, the memory 1710, the processor 1720 and the communication interface 1730 can communicate with each other through an internal interface.

[0452] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor that supports the Advanced RISC Machines (ARM) architecture.

[0453] Furthermore, optionally, the above-mentioned memory may include a read-only memory and a random access memory, and may also include a non-volatile random access memory. The memory may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may include a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may include a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available. For example, static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct memory bus random access memory (DR RAM).

[0454] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the process or function described in the embodiment of the present disclosure is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, data subscriber line (DSL)) or wireless (e.g., infrared, Bluetooth, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access, or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, or a magnetic tape), an optical medium (e.g., a digital versatile disc (DVD)), or a semiconductor medium (e.g., a solid-state drive (SSD)). It is worth noting that the computer-readable storage medium mentioned in the present disclosure may be a non-volatile storage medium, in other words, a non-transient storage medium.

[0455] Those skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or by a program to instruct the relevant hardware, and the program may be stored in a computer-readable storage medium, which may be a read-only memory, a disk, or an optical disk, etc.

[0456] In the description of the embodiments of the present disclosure, the reference terms "one embodiment," "some embodiments," "example," "specific example," or "some examples" mean that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. Moreover, the specific features, structures, materials, or characteristics described may be combined in any appropriate manner in any one or more embodiments or examples. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification, as well as features of different embodiments or examples, unless they are mutually inconsistent.

[0457] In the description of the embodiments of the present disclosure, unless otherwise specified, " / " means "or". For example, A / B can mean A or B. "And / or" in this document is only a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0458] In the description of the embodiments of the present disclosure, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present disclosure, unless otherwise specified, "plurality" means two or more.

[0459] The above description is merely an exemplary embodiment of the present disclosure and is not intended to limit the present disclosure. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present disclosure shall be included in the scope of protection of the present disclosure.

Claims

1. An image display method, comprising: Displaying a preview object on a display interface, the preview object including a three-dimensional model of the object to be presented and a scene to be presented, wherein the three-dimensional model of the object to be presented is generated based on a planar image of the object to be presented; In response to an adjustment operation on the preview object, displaying a target preview object on the display interface, the target preview object being the preview object adjusted based on the adjustment operation; In response to a rendering triggering operation on the target preview object, a target rendered image of the target preview object is displayed on the display interface.

2. The method according to claim 1, wherein: Display preview objects on the display interface, including: In response to a first selection operation on the scene to be presented, displaying the scene to be presented on the display interface; In response to a second selection operation on the object to be presented, a three-dimensional model of the object to be presented is displayed on the display interface.

3. The method according to claim 1 or 2, wherein: Displaying the preview object on the display interface includes: displaying the preview object in a first area of ​​the display interface; In response to the adjustment operation on the preview object, displaying the target preview object on the display interface includes: In response to an adjustment operation on the preview object, the target preview object is displayed in the first area, wherein the first area is at least a portion of a display area in the display interface.

4. The method according to claim 3, wherein: In response to the adjustment operation on the preview object, displaying the target preview object in the first area includes: In response to a first adjustment operation on the scene data of the scene to be presented, displaying a target scene to be presented in the first area, the target preview object including the target scene to be presented, the target scene to be presented being obtained by adjusting the scene data of the scene to be presented based on the first adjustment operation; and / or, In response to a second adjustment operation on the model data of the three-dimensional model of the object to be presented, a target three-dimensional model of the object to be presented is displayed in the first area, and the target preview object includes the target three-dimensional model of the object to be presented, and the target three-dimensional model is obtained after adjusting the model data of the three-dimensional model of the object to be presented based on the second adjustment operation.

5. The method according to claim 3 or 4, further comprising: A reference preview object is displayed in a second area of ​​the display interface, where the reference preview object is the preview object adjusted based on the adjustment operation, and display parameters of the target preview object are lower than display parameters of the reference preview object; the second area is at least a partial display area in the display interface.

6. The method according to claim 5, wherein: The area of ​​the first region is greater than the area of ​​the second region; In response to a rendering triggering operation on the target preview object, displaying a target rendering image on the display interface includes: In response to the rendering triggering operation on the target preview object, a target rendering image is displayed in the first area.

7. The method according to any one of claims 3 to 6, wherein: In response to the adjustment operation on the preview object, displaying the target preview object in the first area includes: In response to an adjustment operation on the preview object, determining incremental data of the preview object corresponding to the adjustment operation; Based on the incremental data, generating the target preview object; The target preview object is displayed in the first area.

8. The method according to claim 5 or 6, wherein: Displaying the reference preview object in the second area of ​​the display interface includes: Sending incremental data of the preview object to a server; wherein the incremental data of the preview object corresponds to the adjustment operation; Receiving the reference preview object sent by the server; wherein the reference preview object is generated by the server based on the incremental data; The reference preview object is displayed in the second area.

9. The method according to any one of claims 1 to 8, wherein: In response to a rendering triggering operation on the target preview object, displaying a target rendered image of the target preview object on the display interface includes: In response to a rendering triggering operation on the target preview object, sending the target preview object to a server; Receiving the target rendered image sent by the server; wherein the target rendered image is generated by the server based on the target preview object; The target rendered image is displayed on the display interface.

10. According to any one of claims 1 to 9, before the preview object is displayed on the display interface, the method further comprises: Acquire a planar image of the object to be presented, wherein the planar image includes planar elevation views of the object to be presented at multiple angles; Based on the planar image, a three-dimensional model of the object to be presented is generated.

11. The method according to claim 10, wherein: Generating a three-dimensional model of the object to be presented based on the planar image includes: Based on the plane image, determining the two-dimensional corner points of the object to be presented and the two-dimensional boundary line of the object to be presented; Determining the three-dimensional corner points of the object to be presented and the three-dimensional boundary line of the object to be presented based on the two-dimensional corner points and the two-dimensional boundary line; A three-dimensional model of the object to be presented is generated based on the three-dimensional corner points and the three-dimensional boundary lines.

12. The method according to claim 10, after generating the three-dimensional model of the object to be presented based on the planar image, the method further comprises: The three-dimensional model of the object to be presented is sent to a server; wherein the server is used to parse the three-dimensional model of the object to be presented into a three-dimensional model in a preset format, and store the three-dimensional model in the preset format.

13. The method according to claim 4, wherein: The scene data includes: at least one of: indoor scene model information, outdoor scene model information, lighting information and camera information; The interior scene model information is used to represent model information of the indoor scene where the three-dimensional model of the object to be presented is located; The outdoor scene model information is used to represent the display information of the outdoor scene outside the indoor scene; The lighting information is used to represent parameter information of the lighting irradiated to the three-dimensional model of the object to be presented; The camera information is used to represent parameter information of a camera used to capture the three-dimensional model of the object to be presented.

14. The method according to claim 4, wherein: The model data includes: at least one of position information and material information; The position information is used to represent the position information of the three-dimensional model of the object to be presented; The material information is used to represent the material mapping information of the three-dimensional model of the object to be presented.

15. An image display device, comprising: The first display unit is used to display the preview object on the display interface, and the preview object includes the object to be presented. A three-dimensional model of an object to be presented and a scene to be presented, wherein the three-dimensional model of the object to be presented is generated based on a planar image of the object to be presented; A second display unit, configured to display a target preview object on the display interface in response to an adjustment operation on the preview object, wherein the target preview object is the preview object adjusted based on the adjustment operation; A third display unit is configured to display a target rendered image of the target preview object on the display interface in response to a rendering triggering operation on the target preview object.

16. The device according to claim 15, wherein: The first display unit is also used for: In response to a first selection operation on the scene to be presented, displaying the scene to be presented on the display interface; In response to a second selection operation on the object to be presented, a three-dimensional model of the object to be presented is displayed on the display interface.

17. The device according to claim 15 or 16, wherein: The first display unit is further used to: display the preview object in the first area of ​​the display interface; The second display unit is also used for: In response to an adjustment operation on the preview object, the target preview object is displayed in the first area, wherein the first area is at least a portion of a display area in the display interface.

18. A method for generating a display graph, comprising: In response to a first selection operation on a target object and a target background, a target model is displayed in a first area of ​​a display interface, and a background image of the target background is displayed on a bottom layer of the target model in the first area, wherein the target model is a three-dimensional model of the target object; In response to the rendering operation, at least one display image is displayed on the display interface, wherein the display image in the at least one display image is a fusion of a first sub-image and a second sub-image located at the bottom layer of the first sub-image, and the first sub-image is an image of the target object rendered based on the selected target light to the target model, and the second sub-image is an image generated by using an AI image generation model and based on the target light, the background image and the target model.

19. The method according to claim 18, further comprising: In response to a second selection operation on the target light, a preview effect image is displayed in a second area of ​​the display interface. The preview effect image is an image of the target object obtained by rendering the target model based on the target light, and image parameters of the first sub-image are higher than image parameters of the preview effect image.

20. The method according to claim 19, wherein: The background image is a line drawing of the target background.

21. The method of claim 19, further comprising: In response to an adjustment operation on the target light and / or the target model, the preview effect image is updated based on the adjustment operation.

22. The method according to claim 18, wherein: The display interface also has an information input area, which is used to provide the AI ​​image generation model with image description information that can generate the display image.

23. The method according to claim 19, wherein: The second area is a floating area of ​​the display interface, and the at least one display image is displayed in a third area of ​​the display interface.

24. The method according to any one of claims 18 to 23, wherein: In response to a first selection operation on a target object and a target background, a target model is displayed in a first area of ​​a display interface, and a background image of the target background is displayed at a bottom layer of the target model in the first area, including: In response to a third selection operation on the target object, displaying a target model in the first area; In response to the fourth selection operation on the target background, the original image corresponding to the target background is processed to obtain a line drawing of the target background, and the line drawing is displayed as the background image on the bottom layer of the target model.

25. The method according to any one of claims 18 to 23, wherein: In response to the rendering operation, displaying at least one display image on the display interface includes: In response to a rendering operation, rendering the target model based on the target light to obtain the first sub-image; Fusing the target model and the background image to obtain a fused image; Inputting the preset light description information of the target light and the fused image into the AI ​​image generation model to obtain the second sub-image; The first sub-image is superimposed on the target area of ​​the second sub-image to obtain the display image, where the display image is one of the at least one display image, and the target area corresponds to the area of ​​the target model in the background image.

26. The method according to claim 25, further comprising: Obtaining image description information used to generate the display image; Inputting the preset light description information of the target light and the fused image into the AI ​​image generation model to obtain the second sub-image includes: The preset light description information of the target light, the image description information and the fused image are input into the AI ​​image generation model to obtain the second sub-image.

27. The method according to claim 25, wherein: Rendering the target model based on the target light to obtain the first sub-image includes: Sending the parameter information of the target light and the position information of the target model to a server, so that the server renders the target model to obtain the first sub-image; Receiving the first sub-image rendered by the server; Inputting the preset light description information of the target light and the fused image into the AI ​​image generation model to obtain the second sub-image includes: Sending the preset light description information and the fused image to the server, so that the server uses the AI ​​image generation model to obtain the second sub-image based on the preset light description information and the fused image; Receive the second sub-image sent by the server.

28. A display image generating device, comprising: a fourth display unit, configured to display a target model in a first area of ​​the display interface in response to a first selection operation on the target object and the target background, and to display a background image of the target background on a bottom layer of the target model in the first area, wherein the target model is a three-dimensional model of the target object; A fifth display unit is used to display at least one display image on the display interface in response to a rendering operation, wherein the display image in the at least one display image is a fusion of a first sub-image and a second sub-image located at the bottom layer of the first sub-image, and the first sub-image is an image of the target object rendered based on the selected target light to the target model, and the second sub-image is an image generated by using an AI image generation model and based on the target light, the background image and the target model.

29. The apparatus according to claim 28, further comprising: A sixth display unit is used to display a preview effect image in the second area of ​​the display interface in response to a second selection operation on the target light, wherein the preview effect image is an image of the target object obtained by rendering the target model based on the target light, and the image parameters of the first sub-image are higher than the image parameters of the preview effect image.

30. A method for generating an image, comprising: In the case where it is determined that the foreground image of the target object and the wireframe image of the target background image are displayed in the current operation area, in response to the first image generation operation, an initial fusion effect image is displayed; the initial fusion effect image is obtained by fusing the foreground image of the target object and the wireframe image of the target background image; In response to the second image generation operation, a target fusion effect diagram is displayed; wherein the target fusion effect diagram is obtained by performing image processing on the initial fusion effect diagram using image effect description parameters, and is used to represent a simulated effect diagram after the fusion of the target object and the target background image.

31. The method according to claim 30, wherein: The step of displaying a target fusion effect diagram in response to the second image generation operation includes: In response to the second image generation operation, N candidate fusion effect images are displayed; each of the N candidate fusion effect images is obtained by performing image processing on the initial fusion effect image using the image effect description parameter or the adjusted image effect description parameter; N is a positive integer greater than or equal to 1; In response to a selection operation on a candidate fusion effect graph among the N candidate fusion effect graphs, the target fusion effect graph is obtained, wherein the target fusion effect graph is the candidate fusion effect graph selected by the selection operation.

32. The method according to claim 31, wherein: In response to the second image generation operation, N candidate fusion effect images are displayed, including: In response to the second image generation operation, the image effect description parameter and the initial fusion effect graph are input into the first model to obtain the N candidate fusion effect graphs; The first model is used to perform image processing on the initial fusion effect image based on the image effect description parameters or the adjusted image effect description parameters to obtain N candidate fusion effect images.

33. The method of claim 30, wherein: The step of displaying a target fusion effect diagram in response to the second image generation operation includes: In response to a second image generation operation, the image effect description parameter and the initial fusion effect graph are input into a second model to obtain the target fusion effect graph; The second model is used to perform image processing on the initial fusion effect image based on image effect description parameters to obtain a target fusion effect image.

34. The method according to any one of claims 30 to 33, wherein: After displaying the target fusion effect diagram in response to the second image generation operation, the method further includes: In response to the third image generation operation, an enhanced fusion effect image is obtained; the enhanced fusion effect image is obtained by overlaying the foreground image of the target object on the area where the target object is located in the target fusion effect image.

35. The method according to any one of claims 30 to 34, wherein: Before determining the wireframe image of the foreground image and the target background image showing the target object in the current operation area, it also includes: Displaying at least an initial image including the target object in the current operation area; In response to an object recognition operation on a target object in the initial image, a foreground image of the target object is obtained.

36. The method according to any one of claims 30 to 35, wherein: Before determining the wireframe image of the foreground image and the target background image showing the target object in the current operation area, it also includes: At least display the target background image in the current operation area; In response to the wireframe extraction operation on the target background image, a wireframe image of the target background image is obtained.

37. The method of claim 36, wherein: After obtaining a wireframe image of the target background image in response to a wireframe extraction operation on the target background image, the method further includes: In response to a wireframe editing operation on the wireframe image of the target background image, a wireframe image after the wireframe editing operation is obtained.

38. The method according to any one of claims 35 to 37, wherein: Before displaying the initial fusion effect image in response to the first image generation operation, the method further includes: The positional relationship between the foreground image of the target object and the wireframe image of the target background image in the current operation area is adjusted by at least one of the following methods: In response to a layout adjustment operation on the foreground image of the target object, obtaining the foreground image after the layout adjustment operation; In response to the layout adjustment operation on the wireframe image of the target background image, a wireframe image after the layout adjustment operation is obtained.

39. An image generating device, comprising: A processing unit, configured to obtain an initial fusion effect image in response to a first image generation operation when it is determined that a wireframe image of a foreground image of a target object and a wireframe image of a target background image are displayed in a current operation area; the initial fusion effect image is obtained by fusing the wireframe image of the foreground image of the target object and the wireframe image of the target background image; A display unit, used to display the initial fusion effect diagram; The processing unit is further used to obtain a target fusion effect image in response to the second image generation operation; wherein the target fusion effect image is a simulated effect image obtained by performing image processing on the initial fusion effect image using image effect description parameters, and is used to represent the fusion of the target object and the target background image; The display unit is also used to display the target fusion effect diagram.

40. The device according to claim 39, wherein The processing unit is specifically configured to obtain N candidate fusion effect images in response to the second image generation operation; each candidate fusion effect image in the N candidate fusion effect images is obtained by performing image processing on the initial fusion effect image using the image effect description parameter or the adjusted image effect description parameter; N is a positive integer greater than or equal to 1; in response to a selection operation on a candidate fusion effect image in the N candidate fusion effect images, obtain the target fusion effect image, wherein the target fusion effect image is the candidate fusion effect image selected by the selection operation; The display unit is also used to display the N candidate fusion effect diagrams.

41. The device according to claim 40, wherein The processing unit is specifically used for: In response to the second image generation operation, the image effect description parameter and the initial fusion effect graph are input into the first model to obtain the N candidate fusion effect graphs; The first model is used to perform image processing on the initial fusion effect image based on the image effect description parameters or the adjusted image effect description parameters to obtain N candidate fusion effect images.

42. An electronic device comprising: at least one processor; as well as a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor performs the method according to any one of claims 1-14, 18-27 and 30-38.

43. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause a computer to execute the method according to any one of claims 1-14, 18-27 and 30-38.

44. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-14, 18-27 and 30-38.

Images