Cover image selection method and device, electronic equipment and storage medium
By optimizing the cover image based on spatial reference conditions and shooting locations in VR decoration scenes, the problem of low cover image attractiveness was solved, resulting in higher user attention and page views.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING CHENGSHI WANGLIN INFORMATION TECH CO LTD
- Filing Date
- 2023-03-15
- Publication Date
- 2026-06-02
AI Technical Summary
In existing technologies, the selection of cover images is not very attractive in VR decoration scenarios, and it easily exposes spaces with placement defects, causing users to lose interest in browsing.
By filtering the first candidate image in the 3D decoration scene based on spatial reference conditions, and combining the virtual camera shooting point and preset spatial priority order, the cover image with high effect quality is automatically selected as the display entry.
It increased the number of views for VR decoration scenes, attracting user attention by showcasing reasonable and high-quality decoration effects, and solving the problem of users losing interest due to poor cover image quality.
Smart Images
Figure CN116450979B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, electronic device and storage medium for selecting a cover image. Background Technology
[0002] In online property viewing scenarios, users can access the property's decoration effect display page through a virtual reality (VR) decoration portal to learn about the decoration effect of the property.
[0003] In existing technologies, a single image is typically captured from a real estate decoration scene and used as the cover image, which then serves as the VR decoration entry point. However, the current method of randomly selecting the cover image fails to identify optimal scene renderings, resulting in low user appeal and easily exposing flawed spaces.
[0004] It is evident that the existing methods of selecting cover images have the problem that the cover images used as entry points are not very attractive to users and easily expose spaces with placement defects. Summary of the Invention
[0005] This application provides a cover image selection method, apparatus, electronic device, and storage medium to solve the problems in existing cover image selection methods where the cover image used as the display entry point is not very attractive to users and easily exposes spaces with placement defects.
[0006] In a first aspect, embodiments of this application provide a method for selecting a cover image, including:
[0007] A first candidate image set is determined in the 3D decoration scene corresponding to the target property, and the first candidate image set includes a first image that meets the spatial reference conditions;
[0008] Select a second image from the first candidate image set whose shooting location meets the shooting conditions, and generate a second candidate image set based on the second image;
[0009] Based on a preset spatial priority order, a cover image is selected from the second candidate image set and set as the display entry point for the three-dimensional decoration scene.
[0010] Secondly, embodiments of this application provide a cover image selection device, comprising:
[0011] The determination module is used to determine a first candidate image set in the three-dimensional decoration scene corresponding to the target property, wherein the first candidate image set includes a first image that satisfies the spatial reference conditions;
[0012] The filtering and generation module is used to filter out second images from the first candidate image set whose shooting points meet the shooting conditions, and generate a second candidate image set based on the second images;
[0013] The filtering settings module is used to filter the cover image from the second candidate image set based on a preset spatial priority order, and set the cover image as the display entry point of the three-dimensional decoration scene.
[0014] Thirdly, embodiments of this application provide an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the cover image selection method as described in the first aspect above.
[0015] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the cover image selection method described in the first aspect above.
[0016] The technical solution of this application embodiment determines a first candidate image set based on spatial reference conditions in the 3D decoration scene corresponding to the target property. Based on the virtual camera's shooting position, it further filters images from the first candidate image set to obtain a second candidate image set. Then, based on a preset spatial priority order, it selects a cover image from the second candidate image set. It can automatically select a high-quality cover image according to the rules and conditions, using the selected image as the display entry point for the 3D decoration scene. This achieves the display of a reasonable and high-quality decoration scene at the property decoration effect entry point, attracting user attention and increasing the browsing volume of the VR decoration scene. This solves the problem of users losing browsing interest due to poor display effects at the decoration scene entry point. Attached Figure Description
[0017] Figure 1 A schematic diagram illustrating the cover image selection method provided in an embodiment of this application;
[0018] Figure 2 This is a schematic diagram illustrating image filtering based on the number of decoration model objects corresponding to the shooting location, as provided in an embodiment of this application.
[0019] Figure 3 This is a schematic diagram illustrating the image filtering based on the number of decoration model objects corresponding to the shooting point and the size of the window model object corresponding to the shooting point, as provided in the embodiments of this application.
[0020] Figure 4 This is a schematic diagram illustrating multiple shooting locations provided in an embodiment of this application;
[0021] Figure 5 This is a schematic diagram of the cover image selection device provided in an embodiment of this application;
[0022] Figure 6 This is a schematic diagram of the electronic device structure provided in the embodiments of this application. Detailed Implementation
[0023] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0024] It should be understood that the phrase "one embodiment" or "an embodiment" throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of this application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Multiple embodiments in this application may include two or more.
[0025] In the various embodiments of this application, it should be understood that the sequence number of each process described below does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.
[0026] This application provides a method for selecting a cover image. See [link to relevant documentation]. Figure 1 As shown, the method includes:
[0027] Step 101: Determine a first candidate image set in the 3D decoration scene corresponding to the target property. The first candidate image set includes a first image that meets the spatial reference conditions.
[0028] The cover image selection method provided in this application is applied to VR decoration scenes. In the three-dimensional decoration scene corresponding to the target property, a first image is selected based on spatial reference conditions, and a first candidate image set is determined based on the selected first image.
[0029] The target property can be a property to be recommended or a property selected by the user for online viewing. The corresponding 3D renovation scene is a VR renovation scene constructed based on the spatial structure of the target property. By constructing the VR renovation scene, users can be provided with renovation images to easily understand the renovation effect. When filtering images based on spatial reference conditions in the 3D renovation scene corresponding to the target property, it can be understood as taking pictures in the VR renovation scene using a virtual camera, and determining the images that meet the spatial reference conditions as the first image, thus realizing the first stage of image filtering based on spatial reference conditions.
[0030] Step 102: Select a second image from the first candidate image set whose shooting point meets the shooting conditions, and generate a second candidate image set based on the second image.
[0031] After determining the first candidate image set including the first image based on spatial reference conditions, image filtering is further performed in the first candidate image set. In this stage of filtering, the virtual camera shooting point corresponding to the image is used as the filtering parameter. Based on the filtering parameter, the second image that meets the shooting conditions at the shooting point is selected from the first candidate image set. The second candidate image set is determined based on the selected second image, thus realizing the second stage of image filtering based on the shooting point.
[0032] Step 103: Based on the preset spatial priority order, select the cover image from the second candidate image set and set the cover image as the display entrance of the three-dimensional decoration scene.
[0033] After completing the first and second stages of image screening to determine the second candidate image set, the preset spatial priority order can be used as the screening parameter to continue screening in the second candidate image set, and the screened images will be determined as the cover images.
[0034] It should be noted that if the second candidate image set contains only one second image, that second image can be directly determined as the cover image. If the second candidate image set contains multiple second images, the selection can be further based on a preset spatial priority order to determine the cover image.
[0035] After selecting the cover image, it can be set as the display entry point for the 3D decoration scene. Based on multiple conditions, the best scene can be selected from the VR decoration scene corresponding to the target property as the display entry point for the decoration effect of the property. This will attract users' attention by displaying a high-quality cover image, thereby increasing the number of views of the VR decoration scene.
[0036] The above-described implementation process of this application involves determining a first set of candidate images based on spatial reference conditions within the 3D decoration scene corresponding to the target property. Then, based on the virtual camera's shooting position, images from the first set are further filtered to obtain a second set of candidate images. Finally, a cover image is selected from the second set based on a preset spatial priority order. The system can automatically select a high-quality cover image according to the rules and conditions, using the selected image as the entry point for displaying the 3D decoration scene. This achieves the goal of displaying a reasonable and high-quality decoration scene at the property's decoration effect entry point, attracting user attention, increasing the browsing volume of the VR decoration scene, and solving the problem of users losing interest in browsing due to poor display effects at the decoration scene entry point.
[0037] The following describes the process of determining the first candidate image set based on spatial reference conditions in the first stage. Determining the first candidate image set within the 3D decoration scene corresponding to the target property includes:
[0038] In the 3D decoration scene corresponding to the target property, filter decoration images that meet the spatial reference conditions;
[0039] The selected decoration images are identified as the first image, and the first candidate image set is generated based on the first image.
[0040] The decoration scene that satisfies the spatial reference conditions includes a decoration model object whose height meets the first preset condition, and when the decoration scene includes a door model object and / or a window model object, the dimensions of the door model object and / or window model object corresponding to the decoration scene that satisfies the spatial reference conditions meet the second preset condition.
[0041] In the first stage of image screening, the selection of decoration images needs to be based on spatial reference conditions within the 3D decoration scene corresponding to the target property. In this embodiment, the spatial reference conditions are actually constraints related to the decoration model objects in the 3D house space. Decoration model objects can be understood as soft furnishing model objects, such as furniture model objects, lighting model objects, decorative painting model objects, curtain model objects, background wall model objects, and door and window model objects, etc.
[0042] When filtering decoration images that meet the spatial reference conditions, for decoration images that do not have door and window model objects, the decoration image can be determined to meet the spatial reference conditions if it includes decoration model objects whose height meets the first preset condition; for decoration images that have door model objects and / or window model objects, the decoration image can be determined to meet the spatial reference conditions if it includes decoration model objects whose height meets the first preset condition and the dimensions of the door model objects and / or window model objects corresponding to the decoration image meet the second preset condition.
[0043] Among them, the decoration model object whose height meets the first preset condition can be a decoration model object whose height is greater than the first threshold. For example, a decoration model object whose height is greater than 20mm is a decoration model object whose height meets the first preset condition. Here, 20mm refers to the actual height of the decoration model object (e.g., the actual height of furniture). For example, decoration model objects whose height meets the first preset condition can include sofa model objects, coffee table model objects, dining table model objects, etc. Since the actual height of the carpet model object is less than 20mm, the decoration model objects whose height meets the first preset condition do not include carpet model objects.
[0044] For a decoration scene containing door and / or window model objects, if the decoration scene includes decoration model objects whose height meets the first preset condition, and the width of the corresponding door and / or window model objects is greater than the corresponding second threshold, then the decoration scene is determined to meet the spatial reference condition. For example, the width of the door model object is greater than 1500mm, and the width of the window model object is greater than 1500mm. Here, 1500mm refers to the actual width of the door and window. The second thresholds for the door and window model objects can be the same or different. It should be noted that the decoration scene can include at least some door and / or window model objects. That is, for a decoration scene containing door and / or window model objects, the decoration scene can include complete door and / or window model objects, or it can include some door and / or window model objects.
[0045] After selecting decoration images in a 3D decoration scene based on spatial reference conditions and determining the decoration images that meet the spatial reference conditions, the selected decoration images are determined as the first image. Then, a first candidate image set is generated based on the first image, thus realizing the first stage of image selection based on spatial reference conditions and obtaining the first candidate image set.
[0046] The above implementation process of this application involves filtering decoration images in the three-dimensional decoration scene corresponding to the target property based on spatial reference conditions, determining the first image based on the filtered decoration images, and obtaining the first candidate image set by performing the first stage of image filtering based on spatial reference conditions.
[0047] The following describes the process of determining the second candidate image set based on the shooting location in the second stage. Selecting a second image from the first candidate image set whose shooting location meets the shooting conditions includes:
[0048] Based on at least one of the following conditions: a first constraint related to the number of decoration model objects in the image, a second constraint related to the size of the door model objects and / or window model objects displayed in the image, and a third constraint related to the completeness of the decoration model objects in the image, image filtering is performed in the first candidate image set, and a reference image set is determined based on the filtered images.
[0049] Based on filtering conditions that include the corner wall and / or the shooting point corresponding to the image in a specific location, the images in the reference image set are filtered, and the retained images are determined as the second image.
[0050] After determining the first candidate image set based on the first stage of image screening, the second stage of image screening continues in the first candidate image set. In the second stage of image screening, images that meet the shooting conditions are actually selected based on the shooting point corresponding to the image.
[0051] The specific process for selecting the second image can be as follows: From the first candidate image set, images are filtered based on at least one of the following three conditions, and the filtered images are aggregated to determine a reference image set. The three conditions can be: a first constraint related to the number of decoration model objects in the image, a second constraint related to the size of the door model objects and / or window model objects displayed in the image, and a third constraint related to the completeness of the decoration model objects in the image. That is, image filtering is performed based on at least one of the following: the number of decoration model objects in the image, the size of the door model objects and / or window model objects displayed in the image, and the completeness of the decoration model objects in the image.
[0052] After determining the reference image set based on at least one of the above three conditions, the images in the reference image set can be filtered. By filtering the images and retaining some images, the retained images are determined as the second images, and the second candidate image set is determined based on the second images.
[0053] Specifically, when filtering images in the reference image set, the images in the reference image set can be filtered according to at least one of the filtering conditions including the external corner wall and / or the filtering conditions of the shooting point corresponding to the image at a specific location, so as to filter images whose shooting point does not meet the conditions and retain images whose shooting point meets the conditions.
[0054] In the above implementation process of this application, after determining the first candidate image set, image screening is performed in the first candidate image set based on the image shooting location, and image filtering is performed in the screened images based on the image shooting location. The second stage of screening can be achieved through image screening and image filtering to obtain the second candidate image set.
[0055] The process of determining a reference image set based on image filtering is described below. The process involves filtering images from the first candidate image set based on at least one of the following: a first constraint related to the number of decoration model objects in the image; a second constraint related to the size of door model objects and / or window model objects displayed in the image; and a third constraint related to the completeness of decoration model objects in the image. The reference image set is then determined based on the filtered images. This includes:
[0056] Based on at least one of the following: the number of decoration model objects in the image is the largest, the size of the door model objects and / or window model objects displayed in the image is greater than the total size of the door model objects and / or window model objects by a preset ratio, and the completeness of the decoration model objects in the image is the highest, a first image that meets at least one of the following constraints is selected from the first candidate image set, and the reference image set is generated based on the selected first image.
[0057] The first constraint is that the number of decoration model objects in the image is the largest; the second constraint is that the size of the door model objects and / or window model objects displayed in the image is greater than a preset ratio of the total size of the door and window model objects; the third constraint is that the completeness of the decoration model objects in the image is the highest, and the priority of the first constraint, the second constraint, and the third constraint decreases in that order.
[0058] When filtering images in the first candidate image set, one or more of the following can be used as filtering parameters: the number of decoration model objects in the image is the largest; the size of the door model objects and / or window model objects displayed in the image is greater than the total size of the door model objects and / or window model objects; and the completeness of the decoration model objects in the image is the highest. Images that meet the filtering parameters are filtered in the first candidate image set, and the filtered images are aggregated to determine the reference image set.
[0059] The first constraint is that the number of decoration model objects in the image is the largest. The second constraint is that the size of the door model objects and / or window model objects displayed in the image is greater than the total size of the door model objects and / or window model objects by a preset ratio. The third constraint is that the completeness of the decoration model objects in the image is the highest. The first constraint has the highest priority, the second constraint has the next highest priority, and the third constraint has the lowest priority.
[0060] When filtering images based solely on the first constraint, the image with the largest number of corresponding decoration model objects can be selected. For example, see... Figure 2As shown, the number of decoration model objects corresponding to the shooting point K4 is greater than the number of decoration model objects corresponding to the shooting point K9, and the number of decoration model objects corresponding to the shooting point K4 is the largest. Therefore, it can be determined that the image taken at the shooting point K4 satisfies the first constraint condition.
[0061] When filtering images based solely on the second constraint, images that include door and / or window model objects, and whose displayed door and / or window model object sizes are larger than a preset proportion of the total size of the door and / or window model objects, can be filtered. For example, images whose displayed door and / or window model object sizes are larger than 1 / 3 of the total size of the door and / or window model objects can be filtered. When filtering images based solely on the third constraint, images with the highest completeness of the corresponding decoration model objects can be filtered.
[0062] When filtering images based on the first and second constraints, the image with the largest number of corresponding decoration model objects can be selected first. Then, further filtering can be performed on the selected images to identify those that include door model objects and / or window model objects, and whose displayed door model objects and / or window model objects have a size greater than a preset proportion of the total size of the door model objects and / or window model objects. See, for example... Figure 3 As shown, the number of decoration model objects corresponding to the shooting point A is greater than the number of decoration model objects corresponding to the shooting point B, and the number of decoration model objects corresponding to the shooting point A is the largest. Therefore, based on the first constraint, the image corresponding to the shooting point A can be determined. Furthermore, since the size of the window model object displayed in the image corresponding to the shooting point A is greater than 1 / 3 of the total size of the window model objects, the image is determined to be an image that satisfies both the first and second constraints.
[0063] When filtering images based on the first and third constraints, we can first filter out the images with the largest number of corresponding decoration model objects, and then further filter the images from the filtered images to select the images with the highest completeness of the model objects, so as to obtain images that meet the above two constraints.
[0064] When filtering images based on the second and third constraints, images that include door model objects and / or window model objects, and whose displayed door model objects and / or window model objects have a size greater than a preset ratio of the total size of the door model objects and / or window model objects, can be filtered first. Then, the image with the highest model object completeness can be selected from the filtered images to obtain images that meet the above two constraints.
[0065] When filtering images based on the first, second, and third constraints, the image with the largest number of corresponding decoration model objects can be filtered first. Then, based on the filtered images, further filtering can be performed to select images that include door model objects and / or window model objects, and whose displayed door model objects and / or window model objects have a size greater than a preset ratio of the total size of the door model objects and / or window model objects. Finally, the image with the highest model object completeness can be selected from the filtered images to obtain images that meet the three constraints.
[0066] The above implementation scheme can perform image filtering in the first candidate image set based on at least one of the first, second, and third restrictive conditions, and generate a reference image set based on the filtered images, thereby retaining valid images according to the restrictive conditions.
[0067] The following describes the process of filtering images in a reference image set based on filtering conditions. Based on filtering conditions that include images containing corner walls and / or images whose corresponding shooting points are located at specific positions, the images in the reference image set are filtered, and the retained images are determined as the second image, including:
[0068] Based on at least one of the following conditions: a first filtering condition that includes a wall with an external corner in the image; a second filtering condition that the shooting point corresponding to the image is in a dense area of the decoration model object; and a third filtering condition that the shooting point corresponding to the image is on a decoration model object whose height meets a third preset condition, the images in the reference image set are filtered respectively to obtain the retained images, thereby determining the second image.
[0069] After determining the reference image set, the images in the reference image set can be filtered based on at least one of the following filtering conditions to retain valid images in the reference image set. The filtering conditions may include: a first filtering condition that the image includes a corner wall, a second filtering condition that the image's shooting point is in a dense area of the decoration model object, and a third filtering condition that the image's shooting point is on a decoration model object whose height meets a third preset condition.
[0070] For filtering based solely on the first filtering condition, images of walls with external corners in the reference image set can be filtered. For filtering based solely on the second filtering condition, images in the reference image set whose shooting points are located in densely populated areas of the decoration model objects can be filtered. For filtering based solely on the third filtering condition, images in the reference image set whose shooting points are located on decoration model objects whose height meets the third preset condition can be filtered. The densely populated areas of decoration model objects can be pre-defined areas based on the placement of the decoration model objects, and these areas can vary depending on the decoration scene. See, for example... Figure 4 As shown, shooting points E, F, H, and I are located in a densely populated area of decoration model objects. Decoration model objects whose height meets the third preset condition can be those whose height exceeds a preset threshold. The height threshold corresponding to the third preset condition can be the same as or different from the height threshold corresponding to the first preset condition. For example, decoration model objects with a height greater than 20mm are defined as those whose height meets the third preset condition.
[0071] For filtering based on at least two filtering conditions, filtering can be performed separately for each condition. That is, in this embodiment, the image to be filtered only needs to satisfy one filtering condition; using two or three filtering conditions involves filtering the image based on filtering parameters of different dimensions. Specifically, when filtering based on the first and second filtering conditions, images in the reference image set can be filtered simultaneously based on both conditions, or filtering can be performed first based on the first condition, and then filtering the remaining images based on the second condition. Correspondingly, filtering based on the first and third filtering conditions, and filtering based on the second and third filtering conditions, follows a similar approach to filtering based on the first and second conditions.
[0072] When filtering based on the first, second, and third filtering conditions, images in the reference image set can be filtered simultaneously based on all three conditions. Alternatively, filtering can be performed first based on the first condition, then on the second condition, and finally on the third condition. Other filtering methods are also possible. This embodiment does not specifically limit the priority of the three filtering conditions. When filtering images sequentially based on at least two conditions, the filtering order can be determined according to requirements.
[0073] The above implementation scheme can further filter the images in the reference image set after determining the reference image set through image screening, so as to delete images that do not meet the shooting requirements, determine the second candidate image set, and achieve the retention of valid images in the reference image set based on image filtering.
[0074] The following describes the process of selecting a cover image from the second candidate image set after determining the second candidate image set, based on a preset spatial priority order. When selecting the cover image, the second image with the highest spatial object priority is selected from the second candidate image set based on a preset spatial object priority order; the selected second image is then determined as the cover image.
[0075] For each frame in the second candidate image set, determine the spatial object corresponding to the image, and then sort them according to the preset spatial object priority. Among the second images corresponding to the second candidate image set, select the second image with the highest spatial object priority and determine it as the cover image. If there are multiple second images with the highest spatial object priority, one of the multiple second images can be selected as the cover image.
[0076] For example, if the second candidate image set includes three second images, corresponding to the living room space, dining room space, and master bedroom space respectively, and since the priority of the living room space, dining room space, and master bedroom space decreases in that order, the second image corresponding to the living room space will be selected as the cover image. Alternatively, if the second candidate image set includes three second images, with second image 1 and second image 2 corresponding to the living room space and second image 3 corresponding to the dining room space, and since the living room space has a higher priority than the dining room space, either second image 1 or second image 2 can be chosen as the cover image.
[0077] After determining the cover image, set the cover image as the display entry point for the 3D decoration scene, so that the selected best scene can be used as the display entry point for the decoration effect of the house.
[0078] The above implementation process, by sorting images based on spatial object priority and filtering images in the second candidate image set, and using the filtered second image as the cover image, can determine the second image with the highest spatial object priority as the cover image.
[0079] The above is the overall implementation process of the cover image selection method provided in this application embodiment. By determining a first candidate image set based on spatial reference conditions in the three-dimensional decoration scene corresponding to the target property, and continuing to filter images in the first candidate image set based on the virtual camera shooting point to obtain a second candidate image set, and filtering the cover image in the second candidate image set based on a preset spatial priority order, the cover image can be automatically selected according to the guidance of the rules and conditions. The selected image is used as the display entrance of the three-dimensional decoration scene, so as to realize the display of reasonable and high-quality decoration effect scene at the property decoration effect entrance, attract users' attention, increase the browsing volume of VR decoration scene, and solve the problem that users lose browsing interest due to poor effect of decoration scene display entrance.
[0080] Furthermore, by filtering decoration images in the 3D decoration scene corresponding to the target property based on spatial reference conditions, and determining the first image based on the filtered decoration images, the first stage of image filtering can be carried out based on spatial reference conditions to obtain a first candidate image set; by filtering images in the first candidate image set based on the image shooting point to determine a reference image set, and filtering images in the reference image set based on the image shooting point, a second candidate image set can be obtained through image filtering and image selection.
[0081] By filtering images in the first candidate image set based on at least one of the first, second, and third constraints, a reference image set can be generated based on the filtered images, thus retaining valid images according to the constraints. After determining the reference image set through image filtering, the images in the reference image set are further filtered to delete images that do not meet the shooting requirements, and a second candidate image set is determined, thus retaining valid images in the reference image set based on image filtering.
[0082] By sorting images based on spatial object priority and filtering them in the second candidate image set, the selected second image can be used as the cover image, thus determining the second image with the highest spatial object priority as the cover image.
[0083] This application provides a cover image selection device, see [link to relevant documentation]. Figure 5 As shown, the device includes:
[0084] The determination module 501 is used to determine a first candidate image set in the three-dimensional decoration scene corresponding to the target property, wherein the first candidate image set includes a first image that satisfies the spatial reference condition;
[0085] The filtering and generation module 502 is used to filter out a second image from the first candidate image set whose shooting point meets the shooting conditions, and generate a second candidate image set based on the second image;
[0086] The filtering setting module 503 is used to filter the cover image from the second candidate image set based on a preset spatial priority order, and set the cover image as the display entry point of the three-dimensional decoration scene.
[0087] Optionally, the determining module includes:
[0088] The first filtering submodule is used to filter decoration images that meet the spatial reference conditions in the three-dimensional decoration scene corresponding to the target property.
[0089] The generation submodule is used to identify the selected decoration images as the first image and generate the first candidate image set based on the first image.
[0090] The decoration scene that satisfies the spatial reference conditions includes a decoration model object whose height meets the first preset condition, and when the decoration scene includes a door model object and / or a window model object, the dimensions of the door model object and / or window model object corresponding to the decoration scene that satisfies the spatial reference conditions meet the second preset condition.
[0091] Optionally, the filtering generation module includes:
[0092] The filtering and determination submodule is used to filter images in the first candidate image set based on at least one of a first constraint associated with the number of decoration model objects in the image, a second constraint associated with the size of the door model objects and / or window model objects displayed in the image, and a third constraint associated with the completeness of the decoration model objects in the image, and to determine a reference image set based on the filtered images.
[0093] The filtering determination submodule is used to filter the images in the reference image set based on filtering conditions including the corner wall and / or the shooting point corresponding to the image being in a specific location, and to determine the retained image as the second image.
[0094] Optionally, the filtering and determining submodule is further used for:
[0095] Based on at least one of the following: the number of decoration model objects in the image is the largest, the size of the door model objects and / or window model objects displayed in the image is greater than the total size of the door model objects and / or window model objects by a preset ratio, and the completeness of the decoration model objects in the image is the highest, a first image that meets at least one of the following constraints is selected from the first candidate image set, and the reference image set is generated based on the selected first image.
[0096] The first constraint is that the number of decoration model objects in the image is the largest; the second constraint is that the size of the door model objects and / or window model objects displayed in the image is greater than a preset ratio of the total size of the door and window model objects; the third constraint is that the completeness of the decoration model objects in the image is the highest, and the priority of the first constraint, the second constraint, and the third constraint decreases in that order.
[0097] Optionally, the filtering determination submodule is further configured to:
[0098] Based on at least one of the following conditions: a first filtering condition that includes a wall with an external corner in the image; a second filtering condition that the shooting point corresponding to the image is in a dense area of the decoration model object; and a third filtering condition that the shooting point corresponding to the image is on a decoration model object whose height meets a third preset condition, the images in the reference image set are filtered respectively to obtain the retained images, thereby determining the second image.
[0099] Optionally, the filtering settings module includes:
[0100] The second filtering submodule is used to filter out the second image with the highest spatial object priority from the second candidate image set based on the preset spatial object priority sorting.
[0101] The determination submodule is used to determine the selected second image as the cover image.
[0102] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.
[0103] This application also provides an electronic device, including: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the various processes of the above-described cover image selection method embodiment and achieves the same technical effect. To avoid repetition, it will not be described again here.
[0104] For example, Figure 6 A schematic diagram of the physical structure of an electronic device is shown. See also... Figure 6As shown, the electronic device may include a processor 610, a communications interface 620, a memory 630, and a communication bus 640, wherein the processor 610, communications interface 620, and memory 630 communicate with each other via the communication bus 640. The processor 610 can call logical instructions in the memory 630 to perform the following steps: determining a first candidate image set in the 3D decoration scene corresponding to the target property, the first candidate image set including a first image that meets spatial reference conditions; selecting a second image from the first candidate image set whose virtual camera shooting point meets the shooting conditions, and generating a second candidate image set based on the second image; selecting a cover image from the second candidate image set based on a preset spatial priority order, and setting the cover image as the display entry point of the 3D decoration scene. The processor 610 can also execute other schemes in the embodiments of this application, which will not be further described here.
[0105] Furthermore, the logical instructions in the aforementioned memory 630 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.
[0106] This application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes of the above-described cover image selection method embodiments and achieves the same technical effect. To avoid repetition, it will not be described again here. The computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.
[0107] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
[0108] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.
[0109] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.
[0110] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0111] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.
[0112] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.
[0113] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0114] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0115] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.
[0116] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
Claims
1. A method for selecting a cover image, characterized in that, include: A first candidate image set is determined in the 3D decoration scene corresponding to the target property, and the first candidate image set includes a first image that meets the spatial reference conditions; Select a second image from the first candidate image set whose shooting location meets the shooting conditions, and generate a second candidate image set based on the second image; Based on a preset spatial priority order, a cover image is selected from the second candidate image set and set as the display entry point for the three-dimensional decoration scene; The step of selecting a second image from the first candidate image set whose shooting location meets the shooting conditions includes: Based on a first constraint related to the number of decoration model objects in the image, a second constraint related to the size of the door model objects and / or window model objects displayed in the image, and a third constraint related to the completeness of the decoration model objects in the image, images are filtered in the first candidate image set, and a reference image set is determined based on the filtered images. Based on filtering conditions that include the corner wall and / or the shooting point corresponding to the image in a specific location, the images in the reference image set are filtered, and the retained images are determined as the second image.
2. The method according to claim 1, characterized in that, The step of determining the first candidate image set in the 3D decoration scene corresponding to the target property includes: In the 3D decoration scene corresponding to the target property, filter decoration images that meet the spatial reference conditions; The selected decoration images are identified as the first image, and the first candidate image set is generated based on the first image. The decoration scene that satisfies the spatial reference conditions includes a decoration model object whose height meets the first preset condition, and when the decoration scene includes a door model object and / or a window model object, the dimensions of the door model object and / or window model object corresponding to the decoration scene that satisfies the spatial reference conditions meet the second preset condition.
3. The method according to claim 1, characterized in that, The first candidate image set is filtered based on a first constraint related to the number of decoration model objects in the image, a second constraint related to the size of the door model objects and / or window model objects displayed in the image, and a third constraint related to the completeness of the decoration model objects in the image. A reference image set is then determined based on the filtered images, including: Based on the following conditions: the number of decoration model objects in the image is the largest, the door model objects displayed in the image are larger than the total size of the door model objects by a preset ratio, and / or the size of the window model objects displayed in the image is larger than the total size of the window model objects by a preset ratio, and the completeness of the decoration model objects in the image is the highest, a first image that meets the limiting conditions is selected from the first candidate image set, and the reference image set is generated based on the selected first image. The first constraint is that the number of decoration model objects in the image is the largest; the second constraint is that the door model objects displayed in the image are larger than the total size of the door model objects by a preset ratio and / or the size of the window model objects displayed in the image is larger than the total size of the window model objects by a preset ratio; and the third constraint is that the completeness of the decoration model objects in the image is the highest.
4. The method according to claim 1, characterized in that, The filtering of images in the reference image set based on the filtering conditions of the image including the corner wall and / or the corresponding shooting point in the image being at a specific location, and determining the retained image as the second image, includes: Based on at least one of the following conditions: a first filtering condition that includes a wall with an external corner in the image; a second filtering condition that the shooting point corresponding to the image is in a dense area of the decoration model object; and a third filtering condition that the shooting point corresponding to the image is on a decoration model object whose height meets a third preset condition, the images in the reference image set are filtered respectively to obtain the retained images, thereby determining the second image.
5. The method according to claim 1, characterized in that, The step of selecting a cover image from the second candidate image set based on a preset spatial priority order includes: Based on the preset spatial object priority sorting, the second image with the highest spatial object priority is selected from the second candidate image set; The selected second image is determined as the cover image.
6. A cover image selection device, characterized in that, include: The determination module is used to determine a first candidate image set in the three-dimensional decoration scene corresponding to the target property, wherein the first candidate image set includes a first image that satisfies the spatial reference conditions; The filtering and generation module is used to filter out second images from the first candidate image set whose shooting points meet the shooting conditions, and generate a second candidate image set based on the second images; The filtering setting module is used to filter the cover image from the second candidate image set based on a preset spatial priority order, and set the cover image as the display entry point of the three-dimensional decoration scene; The filtering generation module includes: The filtering and determination submodule is used to filter images in the first candidate image set based on a first constraint related to the number of decoration model objects in the image, a second constraint related to the size of the door model objects and / or window model objects displayed in the image, and a third constraint related to the completeness of the decoration model objects in the image, and to determine a reference image set based on the filtered images. The filtering determination submodule is used to filter the images in the reference image set based on filtering conditions including the corner wall and / or the shooting point corresponding to the image being in a specific location, and to determine the retained image as the second image.
7. An electronic device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the cover image selection method as described in any one of claims 1 to 5.
8. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the steps of the cover image selection method as described in any one of claims 1 to 5.