Image processing method and device and electronic equipment

By guiding merchants to collect and send multi-angle videos of stores and products, the server generates target images, solving the problem that merchants find it difficult to obtain high-quality target images at low cost, and achieving fast and low-cost 3D models and animations, improving the development of high-quality images. presents the effect.

CN119007058APending Publication Date: 2024-11-22RAJAX NETWORK &TECHNOLOGY (SHANGHAI) CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202310580189.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-22
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

In the prior art, it is difficult for merchants to obtain high-quality store and product target images at low technical costs, and they need professional equipment and knowledge to take multi-angle photos to generate good models.

Method used

By guiding the merchant to use the first terminal to collect the initial video from multiple angles and send it to the server, the server extracts some frames from the video frame to generate the target image, and the merchant can obtain high-quality target image without professional equipment.

Benefits of technology

It realizes the rapid generation of 3D models and animations close to real vision without relying on professional equipment, reducing the technical cost of merchants' decoration stores and products, and improving processing efficiency and presentation effect.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119007058A_ABST
    Figure CN119007058A_ABST
Patent Text Reader

Abstract

The invention discloses an image processing method and device and electronic equipment. The method comprises the following steps: in response to a first instruction for guiding a merchant to provide an initial video, obtaining the initial video of a to-be-shot object collected from multiple angles; in response to a second instruction for providing the initial video for a server, providing the initial video for the server; wherein the server side is used for extracting at least part of video frames from the initial video, and generating a target image of the to-be-shot object based on the at least part of video frames. By adopting the method, the problem of providing high-quality target images corresponding to shops and commodities at low technical cost is solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of image data processing, and in particular to an image processing method, device, electronic device and storage medium. Background Art

[0002] With the development of online shopping, how to present stores and products on the Internet, as important assets of merchants, is becoming more and more important for merchant operations. Good presentation of stores and products can attract users and improve user retention rate.

[0003] In the prior art, in order to optimize the presentation of stores and goods, videos are generally used for store decoration and to display 3D models of goods. However, in actual operation, merchants are often required to take multiple photos from different angles in order to generate models of corresponding stores or goods. These photos generally need to be taken with more professional equipment, such as automatic rotating platforms, pan-tilt devices, etc., and operators need to have certain professional knowledge to obtain usable models. Otherwise, the obtained models are of poor quality and poor effect. Therefore, it is difficult for merchants to obtain good store and product presentation effects with low technical costs.

[0004] Therefore, how to provide higher-quality target images corresponding to stores and products at a low technical cost for merchant operations is a problem that needs to be solved.

[0005] The above information disclosed in the Background section is only for enhancement of understanding of the background of the present application and therefore it may contain information that does not constitute the prior art that is already known to a person of ordinary skill in the art. Summary of the invention

[0006] The image processing method provided in the embodiment of the present application solves the problem of providing high-quality target images corresponding to stores and products for merchant operations at a low technical cost.

[0007] An embodiment of the present application provides an image processing method, which is applied to a first terminal, comprising: in response to a first instruction for guiding a merchant to provide an initial video, obtaining an initial video of an object to be photographed captured from multiple angles; in response to a second instruction for providing the initial video to a server, providing the initial video to the server; wherein the server extracts at least a portion of video frames from the initial video, and generates a target image of the object to be photographed based on the at least a portion of the video frames.

[0008] Optionally, in response to a first instruction for guiding a merchant to provide an initial video, obtaining an initial video of the object to be photographed captured from multiple angles includes: the first terminal is provided with a camera device; and displaying first guide information for guiding the merchant to operate the first terminal to shoot around the object to be photographed, so as to capture the initial video.

[0009] Optionally, it also includes: detecting the shooting angle of the camera device to the object to be photographed; updating the first guidance information according to the change of the shooting angle to guide the merchant to operate the first terminal to adjust the shooting angle, and capture a full-range video around the object to be photographed as the initial video.

[0010] Optionally, the first guidance information further includes guidance information for guiding the merchant to capture the initial video from multiple viewing angles including the front, side, top view, and top view of the object to be photographed.

[0011] Optionally, the method further includes: displaying second guidance information for guiding the merchant to operate the first terminal to shoot around the object to be shot within a preset shooting time, so as to shoot and obtain the initial video within the preset shooting time.

[0012] Optionally, the target image is generated by extracting video frames from the initial video by the server according to a preset interval frame number or interval duration, and using the extracted video frames.

[0013] Optionally, the method further includes: providing description information for the initial video to the server; accordingly, the target image is an image generated by the server according to at least part of the video frame and the description information.

[0014] Optionally, the target image is generated by the server according to the visual effect characteristics of the object to be photographed and at least part of the video frame, and the target image provides corresponding visual effects to the user after being displayed; wherein, the visual effect characteristics of the object to be photographed are determined based on the description information.

[0015] Optionally, the object to be photographed is a dish provided by the merchant to the user; the server obtains one or more dish attributes of the dish according to the description information of the dish, determines the visual effect characteristics of the dish according to the dish attributes, and generates a target image of the dish according to the visual effect characteristics of the object to be photographed and at least part of the video frame.

[0016] Optionally, the dish attributes include at least one of dish category attributes, ingredient attributes, taste attributes, and atmosphere attributes; the target image of the dish includes image information and / or text information representing the visual effects corresponding to the dish attributes.

[0017] Optionally, the visual effects of the target image of the dish include any of the following visual effects: hot steam effect, iced effect, bubble effect, heart-shaped effect, picture switching display effect, motion lens effect, and lighting effect.

[0018] Optionally, the object to be filmed is the store and / or goods of the merchant; the initial video includes a store video collected for the store of the merchant, and / or a product video collected for the goods of the merchant; accordingly, the target image includes a store story video or a store 3D panoramic model generated corresponding to the store video and corresponding description information, and / or a product animated image or a product 3D model generated corresponding to the product video and corresponding description information.

[0019] Optionally, it also includes: when the object to be photographed is a product of the merchant, in response to a first page setting instruction, sending first page editing information to the server to instruct the use of a target image corresponding to the product and the product description information of the product to set the first page; and / or, when the object to be photographed is a store of the merchant, in response to a second page setting instruction, sending second page editing information to the server to instruct the use of a target image corresponding to the store and the store description information of the store to set the second page.

[0020] Optionally, the target image is provided to a second terminal and displayed on the second terminal to assist the user in deciding whether to select the object to be photographed for transaction.

[0021] The present application also provides an image processing method, which is applied to a server, including: obtaining an initial video of a merchant provided by a first terminal; the initial video is a video captured from multiple angles by the first terminal to guide the merchant to operate the first terminal for an object to be photographed; extracting at least part of the video frames from the initial video, and generating a target image of the object to be photographed based on the at least part of the video frames; providing the target image to a second terminal so that the second terminal displays the target image.

[0022] Optionally, the videos captured from multiple angles are videos captured around the object to be photographed.

[0023] Optionally, extracting at least part of the video frames from the initial video includes: extracting at least part of the video frames from the initial video according to a preset interval frame number or interval duration.

[0024] Optionally, it also includes: receiving description information for the initial video provided by the first terminal; generating the target image of the object to be photographed based on the at least part of the video frame includes: generating the target image according to the at least part of the video frame and the description information.

[0025] Optionally, generating the target image according to the at least part of the video frame and the description information includes: determining visual effect characteristics of the object to be photographed based on the description information; generating the target image according to the visual effect characteristics of the object to be photographed and the at least part of the video frame, and providing a corresponding visual effect to the user after the target image is displayed on the second terminal.

[0026] Optionally, the object to be photographed is a dish provided by the merchant to users; determining the visual effect characteristics of the object to be photographed based on the description information includes: acquiring one or more dish attributes of the dish according to the description information of the dish; determining the visual effect characteristics of the dish according to the dish attributes; generating the target image according to the visual effect characteristics of the object to be photographed and at least a portion of the video frames includes: generating the target image of the dish according to the visual effect characteristics of the dish and at least a portion of the video frames.

[0027] Optionally, the dish attributes include at least one of dish category attributes, ingredient attributes, taste attributes, and atmosphere attributes; the target image of the dish includes image information and / or text information representing the visual effects corresponding to the dish attributes.

[0028] Optionally, the visual effects of the target image of the dish include any of the following visual effects: hot steam effect, iced effect, bubble effect, heart-shaped effect, picture switching display effect, motion lens effect, and lighting effect.

[0029] Optionally, it also includes: using an image generated based on at least part of the video frame as an initial target image; synthesizing audio based on the description information, fusing the audio with the initial target image, and using the audio and video data obtained after the fusion as the target image, and the target image is used for display on the second terminal.

[0030] Optionally, the object to be filmed is the store and / or goods of the merchant; the initial video includes a store video collected for the store of the merchant, and / or a product video collected for the goods of the merchant; accordingly, the target image includes a store story video or a store 3D panoramic model generated corresponding to the store video, and / or a product animated image or a product 3D model generated corresponding to the product video.

[0031] Optionally, it also includes: when the object to be photographed is a product of the merchant, receiving first page editing information sent by the first terminal, and setting the first page using a target image corresponding to the product and product description information of the product; and / or, when the object to be photographed is a store of the merchant, receiving second page editing information sent by the first terminal, and setting the second page using a target image corresponding to the store and store description information of the store.

[0032] Optionally, the method further includes: providing the target image to the first terminal and displaying it on the first terminal, so that the merchant can operate the target image.

[0033] The present application also provides an image processing method, which is applied to a second terminal, comprising: in response to a page loading instruction, loading a page including a target image; wherein the target image is generated by extracting at least a portion of video frames from an initial video of an object to be photographed provided by a first terminal, and based on the at least a portion of the video frames; the initial video is captured by the first terminal from multiple angles for the object to be photographed by guiding a merchant to operate the first terminal; and the target image is displayed to assist a user in deciding whether to select the object to be photographed for a transaction.

[0034] Optionally, in response to a page loading instruction, loading a page including a target image includes: in response to a loading instruction of a first page, loading the first page, the target image included in the first page being a product animated image or a product 3D model; or, in response to a loading instruction of a second page, loading the second page, the target image included in the second page being a store story video or a store 3D panoramic model.

[0035] Optionally, when the object to be photographed is a dish, the target image is a product animated image or a product 3D model of the dish, and the visual effects of the target image include any of the following visual effects: hot air effect, ice effect, bubble effect, heart-shaped effect, picture switching display effect, motion lens effect, and lighting effect.

[0036] Optionally, it also includes: receiving the user's operation behavior information on the target image, and performing at least one of the following operations on the target image according to the operation behavior information: rotating, flipping, scaling, displaying corresponding description information corresponding to the user's current viewing angle, and displaying the image after the operation corresponding to the operation instruction.

[0037] The present application also provides an image processing device, including: an acquisition unit, used to respond to a first instruction for guiding a merchant to provide an initial video, and obtain an initial video of an object to be photographed acquired from multiple angles; a sending unit, used to respond to a second instruction for providing the initial video to a server, and provide the initial video to the server; wherein the server extracts at least a portion of video frames from the initial video, and generates a target image of the object to be photographed based on the at least portion of the video frames.

[0038] The present application also provides an image processing device, including: an initial video acquisition unit, used to acquire an initial video of a merchant provided by a first terminal; the initial video is a video captured from multiple angles by the first terminal to guide the merchant to operate the first terminal for an object to be photographed; a target image generation unit, used to extract at least part of the video frames from the initial video, and generate a target image of the object to be photographed based on the at least part of the video frames; a display unit, used to provide the target image to a second terminal, so that the second terminal displays the target image.

[0039] The present application also provides an image processing device, including: a page loading unit, used to load a page including a target image in response to a page loading instruction; wherein the target image is generated by extracting at least part of the video frames from an initial video of an object to be photographed provided by a first terminal by a server, and based on the at least part of the video frames; the initial video is obtained by the first terminal guiding a merchant to operate the first terminal to capture the object to be photographed from multiple angles; and a display unit, used to display the target image to assist a user in deciding whether to select the object to be photographed for a transaction.

[0040] An embodiment of the present application further provides an electronic device, comprising: a memory, and a processor; the memory is used to store a computer program, and after the computer program is run by the processor, the method provided in the embodiment of the present application is executed.

[0041] The embodiment of the present application also provides a computer storage medium storing computer execution instructions, which are used to implement the method provided in the embodiment of the present application when executed by a processor.

[0042] Compared with the prior art, this application has the following advantages:

[0043] An image processing method, device, electronic device and storage medium provided in an embodiment of the present application are applied to a first terminal, and the method obtains an initial video of the object to be photographed collected from multiple angles by responding to a first instruction for guiding a merchant to provide an initial video; and provides the initial video to the server in response to a second instruction for providing the initial video to the server; wherein the server extracts at least part of the video frame from the initial video, and generates a target image of the object to be photographed based on the at least part of the video frame. Guide merchants to collect videos of the object to be photographed, and do not need additional professional equipment and more professional shooting knowledge to shoot the video of the object to be photographed from multiple angles, and send it to the server. The server can generate the target image of the object to be photographed based on the partial video frame, so that a suitable target image can be obtained at a low technical cost, which is convenient for the merchant to operate. Further, the merchant provides the description information of the object to be photographed to the server, so that the server generates the target image of the object to be photographed (such as a product model or a store story video) according to the description information, and uses it to generate a product page or a store page, so that the merchant can decorate the store and present the product at a low technical cost, and provide a good store and product presentation effect.

[0044] Another image processing method, device, electronic device and storage medium provided in the embodiment of the present application, the method is applied to the server, by obtaining the initial video of the merchant provided by the first terminal; the initial video is the video collected from multiple angles by the first terminal guiding the merchant to operate the first terminal for the object to be photographed; at least part of the video frames are extracted from the initial video, and the target image of the object to be photographed is generated based on the at least part of the video frames; the target image is provided to the second terminal so that the second terminal displays the target image. The first terminal guides the merchant to collect videos of the object to be photographed, and the video of the object to be photographed can be photographed from multiple angles without additional professional equipment and more professional shooting knowledge. The server generates the target image of the object to be photographed based on the partial video frames, so that a suitable target image can be obtained at a low technical cost, which is convenient for the merchant to operate. The target image is displayed on the second terminal for users using the second terminal to browse the target image. Good presentation quality and effect can improve the user experience.

[0045] Another image processing method, device, electronic device and storage medium provided by the embodiment of the present application, the method is applied to the second terminal, and a page including a target image is loaded by responding to a page loading instruction; wherein the target image is generated based on at least a portion of the video frames extracted by the server from the initial video of the object to be photographed provided by the first terminal; the initial video is obtained by the first terminal guiding the merchant to operate the first terminal to collect the object to be photographed from multiple angles; the target image is displayed to assist the user in deciding whether to select the object to be photographed for transaction. The first terminal guides the merchant to collect videos of the object to be photographed, and the video of the object to be photographed can be photographed from multiple angles without additional professional equipment and more professional shooting knowledge. The server generates the target image of the object to be photographed based on the partial video frames, so that a suitable target image can be obtained at a low technical cost, which is convenient for the merchant to operate. The target image is displayed on the second terminal for users using the second terminal to browse the target image, helping users to make decisions, and good presentation quality and effect can improve user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 This is a schematic diagram of an application scenario of the image processing method provided by this application;

[0047] Figure 2 is a processing flow chart of an image processing method provided in the first embodiment of the present application;

[0048] Figure 3 This is a schematic diagram of device interaction of an image processing method provided by the first embodiment of the present application;

[0049] Figure 4 is a processing flow chart of an image processing method provided in the second embodiment of the present application;

[0050] Figure 5 is a processing flow chart of an image processing method provided in the third embodiment of the present application;

[0051] Figure 6 is a schematic diagram of an image processing device provided in the fourth embodiment of the present application;

[0052] Figure 7 is a schematic diagram of an image processing device provided in the fifth embodiment of the present application;

[0053] Figure 8 is a schematic diagram of an image processing device provided in a sixth embodiment of the present application;

[0054] Fig. 9 It is a schematic diagram of an electronic device provided by this application. DETAILED DESCRIPTION

[0055] Many specific details are described in the following description to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present application, so the present application is not limited by the specific implementation disclosed below.

[0056] The embodiments of the present application provide several image processing methods, devices, electronic devices and storage media, which are described one by one in the following embodiments.

[0057] For ease of understanding, an application scenario of the image processing method provided in this application is first given. This scenario is only an embodiment, and the purpose of providing this scenario embodiment is to facilitate understanding of the application of the image processing method provided in this application, and is not used to limit the image processing method of this application.

[0058] Please refer to Figure 1 , the application scenario shown in the figure includes: a first terminal 101, a server 102, and a second terminal 103. Among them, the first terminal uploads the initial video of the store and / or the product to the server, and the present application does not specifically limit the method of uploading the initial video. The first terminal includes a terminal used by a merchant. For example, in one implementation, the store and / or the product of the merchant are taken as the object to be photographed, and the merchant uses the first terminal to collect the initial video of the object to be photographed from multiple angles, which may specifically include shooting around the object to be photographed to obtain the initial video, and sending the initial video to the server. For another example, in one implementation, the first terminal sends the initial video stored (locally or online) to the server. For another example, in one implementation, the first terminal sends the storage address information of the initial video to the server, and the server obtains the initial video. The server generates a corresponding target image based on the initial video, and the target image can be used to generate the product page and / or store page of the merchant. The second terminal can obtain and display the target image, and the specific acquisition method and display method are not specifically limited. The second terminal preferably includes a terminal used by a user. For example, in one method, a user uses a second terminal to browse a product page and / or a store page, and the second terminal displays the product page and / or the store page, and the target image is then displayed on the second terminal and presented to the user. Of course, the target image can also be displayed on the second terminal through other pages or containers, such as being displayed on the second terminal through an advertising page. The first terminal and the second terminal both include but are not limited to mobile phones, computers, smart interactive devices, etc. When the first terminal has the function of capturing the initial video, the first terminal includes but is not limited to mobile phones, computers, smart interactive devices, etc. equipped with a camera device. The server can be an independent physical server or a cluster consisting of multiple physical servers.

[0059] It should be noted that the above disclosed information is only used to help understand the present application and does not mean to constitute the prior art known to ordinary technicians in the field.

[0060] In the image processing method provided in the first embodiment of the present application, the merchant is guided to send (upload) the initial video to the server, and the initial video is a video collected from multiple angles of the object to be photographed; the server extracts video frames from the initial video, and generates a target image of the object to be photographed based on the extracted video frames. Thus, the image material (i.e., the extracted video frame) for synthesizing the target image can be provided to the server without relying on more professional video shooting equipment such as an automatic rotation platform and a pan / tilt, and the server helps to synthesize a target image with better quality. In particular, the first terminal guides the merchant to use the first terminal to collect the initial video from multiple angles, such as shooting a video, which can help the merchant provide sufficient image materials to the server without relying on professional equipment, thereby quickly generating a 3D model that is closer to real vision, improving processing efficiency and providing a target image with better visual effects.

[0061] The following combination Figure 2 and Figure 3 The image processing method provided in the first embodiment of the present application is described.

[0062] Figure 2 The image processing method shown is applied to a first terminal, and includes:

[0063] Step S201, in response to a first instruction for guiding a merchant to provide an initial video, obtaining an initial video of the object to be photographed collected from multiple angles;

[0064] Step S202, in response to a second instruction for providing the initial video to the server, providing the initial video to the server;

[0065] Wherein, the server extracts at least part of the video frames from the initial video, and generates the target image of the object to be photographed based on the at least part of the video frames.

[0066] As described in step S201, the first terminal guides the merchant to obtain an initial video of the object to be photographed, and the initial video is a video collected from multiple angles. The object to be photographed includes the merchant's store and / or goods. The first terminal displays different guidance information to instruct the merchant to obtain the initial video. The present application does not limit the specific implementation method of obtaining the initial video. In a preferred implementation, the first terminal displays the first guidance information to guide the merchant to operate the first terminal to collect the initial video for the object to be photographed, or guides the merchant to select the stored initial video in the local storage of the first terminal to send the collected or stored initial video to the server. Further, it also includes: if it is detected that the first terminal is equipped with a camera device, the first guidance information includes guidance information for guiding the merchant to operate the first terminal to collect the initial video for the object to be photographed. In one implementation, the first terminal displays the second guidance information to guide the merchant to enter or select the storage address information of the initial video and send it to the server, so that the server obtains the initial video according to the storage address information of the initial video. Preferably, the storage address information is the storage location and / or storage file name of the store video and / or product video included in the merchant data stored online.

[0067] The video shot from multiple angles includes: a video captured by shooting around the object to be shot, such as a video shot around 360 degrees. When guiding the merchant to operate the first terminal to shoot and obtain the initial video, the first instruction for guiding the merchant to provide the initial video is used to obtain the initial video of the object to be shot from multiple angles, specifically including: the first terminal is provided with a camera; and the first guide information for guiding the merchant to operate the first terminal to shoot around the object to be shot is displayed to shoot and obtain the initial video. Further, it also includes: detecting the shooting angle of the camera device to the object to be shot; updating the first guide information according to the change of the shooting angle, so as to guide the merchant to operate the first terminal to adjust the shooting angle, and shoot and obtain a full-range video around the object to be shot as the initial video. The first guide information is information in the form of images and / or text. The image includes any of the following images: arrows, progress bars, etc. For example, dynamic arrows and / or texts are used to indicate the change of the shooting angle, and the dynamic arrows and / or texts are updated as the shooting angle changes. The dynamic arrow is preferably a dynamic surround arrow. For another example, the progress bar can be a progress bar in various forms, which updates the progress as the shooting angle changes. Shooting starts from the first terminal until 360-degree shooting around the object to be photographed is completed, and the initial video is saved and / or uploaded to the server. Furthermore, the first guidance information also includes guidance information for guiding the merchant to capture the initial video from multiple perspectives of the front, side, top and bottom directions of the object to be photographed, so as to obtain a 360-degree panoramic video.

[0068] In a preferred embodiment, the initial video is a video collected within a preset shooting time, and accordingly, the method specifically includes: displaying second guidance information for guiding the merchant to operate the first terminal to shoot around the object to be shot within the preset shooting time, so as to obtain the initial video by shooting within the preset shooting time. For example, the initial video obtained is a video shot within 10 seconds around the object to be shot.

[0069] As described in step S202, the first terminal responds to the second instruction for providing the initial video to the server by providing the initial video to the server, so that the server generates the target image based on the initial video. Specifically, the target image is generated by the server extracting video frames from the initial video according to a preset interval frame number or interval duration, and using the extracted video frames. For example, the server extracts one video frame every 10 frames of the initial video shot around the object to be photographed within 10 seconds, and uses the extracted video frames as materials to generate the target image of the object to be photographed. During implementation, the target image generated in this embodiment includes any of the following types of images: story video, animated image, 3D model. The story video refers to a story video generated by extracting video frames from the initial video according to the extracted video frames and corresponding description information. The animated image refers to a dynamic picture generated by extracting video frames from the initial video, that is, a GIF picture. The so-called 3D model includes a three-dimensional panoramic image of the object to be photographed obtained by splicing video frames extracted from the initial video, wherein each extracted video frame is a photo, and the video frames extracted from the initial video can be understood as one or more groups of photos taken in 360 degrees. In this embodiment, by using the method of shooting videos, merchants are helped to quickly generate 3D models, animated images, and story videos without relying on professional equipment.

[0070] Preferably, the server refers to a platform-side server that provides multimedia visual capabilities, wherein the multimedia visual capabilities include at least one of the following multimedia capabilities: generating 3D models, generating animated images (GIFs), and generating story videos. Among them, one implementation includes generating a 3D model, specifically including the following processing: the first terminal guides the merchant to shoot a video of the object to be photographed (stores and / or goods), and the server intelligently generates a 3D model. The first terminal can obtain the 3D model and receive the merchant's operation on the 3D model. Specifically, the method includes the following processing: obtaining the target image and displaying it; in response to a compliance review instruction for the target image, sending the target image to a compliance device for compliance review to conduct a compliance review on the target image. The target image after compliance review can be used to be displayed on the second terminal. The 3D model can be a 3D panoramic model. Among them, one implementation includes generating a dynamic image, and the dynamic image can be generated by using at least one of the following dynamic image production methods: a motion lens dynamic effect production method, a lighting dynamic effect production method, a synthetic dynamic effect production method, and a generated dynamic effect production method. Among them, in the motion lens dynamic effect production method, it includes separating the foreground and background of the object to be photographed in the target image, and taking at least one method such as translation, scaling, rotation, etc. to process the foreground to obtain a dynamic image of the dynamic effect of the lens motion shooting, which is used as the target image output by the server. In the lighting dynamic effect production method, edge special effects, sweeping light, etc. are added to the foreground to achieve a dynamic image that highlights the foreground effect. In the synthetic dynamic effect production method, the target image and the corresponding image are superimposed to synthesize different effects, such as a heart-shaped effect, a bubble effect, an ice effect, a hot effect, a picture switching display effect, and at least one other effect. In the generation dynamic effect production method, a text generation video model is applied, and text information (such as description information or other text content provided by the merchant) is used as input, and multi-frame rate layered training is used to obtain a high frame rate dynamic effect video. The text generation video model includes two modules. The first module generates several frames of images through text to synthesize a low frame rate video with a low frame rate; the second module interpolates several frames of the low frame rate video based on the bidirectional attention model to generate a high frame rate dynamic image. An example of a text generation video model is the CogVideo model. In the absence of conflict, the above-mentioned animation production methods can be combined with each other to generate corresponding target images.

[0071] In this embodiment, the story video generation capability provided by the server includes generating store story videos. Based on text-to-speech synthesis technology, the input text is synthesized into an audio (waveform) output through a deep learning method, such as Tacotron (an artificial intelligence synthesis system). Specifically, the first terminal obtains the corresponding description information (such as text) provided by the merchant for the initial video, and the server extracts video frames based on the initial video, generates a first image based on the video frame, synthesizes the first audio based on the description information, and synthesizes the first image and the first audio into a story video as the target image. When the object to be shot is a store, the generated story video is a store story video; when the object to be shot is a product, the generated story video is a product story video.

[0072] In a preferred embodiment, it further includes: the first terminal provides the server with description information for the initial video; accordingly, the target image is an image generated by the server according to the at least part of the video frame and the description information. Wherein, the target image is generated by the server according to the visual effect characteristics of the object to be photographed and the at least part of the video frame, and the target image provides the user with corresponding visual effects after being displayed; wherein, the visual effect characteristics of the object to be photographed are determined based on the description information. During implementation, the server performs word segmentation processing on the description information, matches each word segmentation obtained by the word segmentation processing with a reference word representing the visual effect, and uses the visual effect associated with the matched reference word as the visual effect characteristic of the object to be photographed. The server then generates the target image using the video frame according to the visual effect characteristics. One application scenario of the method is to provide merchants in the catering industry with a solution for quickly generating target images of dishes and / or stores close to the merchant at a low technical cost. In this application scenario, the object to be photographed is the dish provided by the merchant to the user; the server obtains one or more dish attributes of the dish according to the description information of the dish, determines the visual effect characteristics of the dish according to the dish attributes, and generates a target image of the dish according to the visual effect characteristics of the object to be photographed and at least part of the video frame. Among them, the dish attributes include at least one of dish category attributes, ingredient attributes, taste attributes, and atmosphere attributes; the target image of the dish includes image information and / or text information that characterizes the visual effects corresponding to the dish attributes. The visual effects of the target image of the dish include any of the following visual effects: hot air effect, ice effect, bubble effect, heart-shaped effect, picture switching display effect, motion lens effect, and lighting effect. For example, if the dish is beef noodles, and the dish description information includes hot dishes and spicy taste, the server extracts the dish category attribute as hot dishes and the taste attribute as spicy from the dish description information, and determines that the visual effect characteristics of the dish include heat effect and special effects indicating spiciness; accordingly, the generated target image is an initial 3D model generated by extracting video frames based on the initial video of beef noodles, and the initial 3D model is then superimposed with synthetic dynamic effects to obtain a 3D model with heat effect and pictures and / or texts representing spiciness (such as flames indicating spiciness) as the target image of beef noodles. The target image generated by using the initial video shot by the merchant for the goods and / or stores is closer to the actual situation of the merchant's goods and stores, and can display the goods and / or stores more realistically.

[0073] In this embodiment, the first terminal also: obtains the target image, the target image includes a 3D model of the store and / or the product; sends the target image to a compliance device used for compliance audit; the target image audited by the compliance device is used to display on the product details page or the store basic page associated with the product. The 3D model includes a 3D panoramic model. Further, after the first terminal obtains the target image, it also includes: the first terminal receives the merchant's operation behavior information on the target image, and performs at least one of the following operations on the target image according to the operation behavior information: rotate, flip, zoom, display corresponding description information corresponding to the user's current perspective, and display the image after the operation corresponding to the operation instruction. This allows merchants to preview the target image in an all-round and interactive manner.

[0074] In practical applications, a preferred implementation includes: the object to be photographed is the store and / or goods of the merchant; the initial video includes a store video collected for the store of the merchant, and / or a product video collected for the goods of the merchant; accordingly, the target image includes a store story video or a store 3D panoramic model generated corresponding to the store video and corresponding description information, and / or a product animated image or a product 3D model generated corresponding to the product video and corresponding description information. Further, the target image is provided to the second terminal and displayed on the second terminal to assist the user in deciding whether to select the object to be photographed for transaction. In this application, the specific method for the second terminal to obtain the target image is not specifically limited. In one acquisition method, the first page and / or the second page carries the target image, and the second terminal displays the target image by loading the first page and / or the second page. The method specifically includes: when the object to be photographed is a commodity of the merchant, in response to a first page setting instruction, sending first page editing information to the server to indicate that the first page is set using the target image corresponding to the commodity and the commodity description information of the commodity; and / or, when the object to be photographed is a store of the merchant, in response to a second page setting instruction, sending second page editing information to the server to indicate that the second page is set using the target image corresponding to the store and the store description information of the store. For example, the first page includes a commodity page, which includes but is not limited to a commodity details page, an event venue page, etc. The second page includes a store page, which includes but is not limited to a store basic page, a store list page, a channel advertising page, etc. In one acquisition method, the second terminal interacts with the user using the second terminal in all directions through computer technology so that the user can watch the real scene to restore and display the target image, which specifically includes the second terminal integrating the acquired target image with the real scene photographed by the second terminal.

[0075] Of course, the first terminal can also extract at least part of the video frames from the initial video, and based on a 3D model generation algorithm or function such as an open source nerf algorithm or iOS's RealityKit function, convert the extracted video frames (each frame is equivalent to a photo) to obtain a 3D model of the object to be photographed, and further generate a dynamic image as the target image. The target image is provided to the server, which provides it to the second terminal and displays it. Specifically, the server uses the target image to set the first page and / or the second page, and the second terminal requests to load the first page and / or the second page, thereby displaying the target image; or, the second terminal obtains the target image from the server in an interactive manner and displays it in combination with the real scene captured by the second terminal.

[0076] Please refer to Figure 3 , the figure shows the interaction process between the first and second terminals and the server, including: S301, guiding the merchant using the first terminal to shoot an initial video of the object to be shot from multiple angles. The object to be shot is the merchant's goods and / or shops. The goods can be a single product or a package product. S302, uploading the initial video to the server. S303, providing the server with description information corresponding to the initial video. This step is optional. If it is necessary to provide product description information for the goods or packages, and / or store description information for the store, the merchant uses the first terminal to provide the server with corresponding description information for the initial video. S304, the server intelligently generates a target image, and the target image includes at least one of a 3D model, a gif, and a story video. For the goods, at least one of a 3D model of the product, a gif of the product, and a story video of the product is generated; for the store, at least one of a 3D model of the store, a gif of the store, and a story video of the store is generated. The server extracts several video frames from the initial video, uses the video frames to synthesize the target image, and if the corresponding description information is obtained, generates a product story video and / or a store story video according to the description information. Of course, the visual effect features can also be determined based on the description information, so that the server can process the target image to have the corresponding visual effect. S305, obtain the target image, preview and / or operate the target image. For example, the first terminal can obtain the 3D model generated by the server and operate it, such as submitting a compliance review, flipping, rotating, scaling, displaying the corresponding description information corresponding to the merchant's current perspective, and displaying the image after the operation corresponding to the operation instructions. S306, generate a product page and / or a store page based on the target image. S307, the second terminal displays the target image. Such as requesting to load a product page and / or a store page. The product page is specifically a product details page, and the store page specifically includes the product list page of the store. The product list page can display product videos, and the product details page can display product 3D models. Among them, steps S301 and S302, that is, guiding merchants to shoot videos and send videos to the server can be implemented based on the native image SDK of the first terminal.

[0077] The image processing method provided in this embodiment can provide a solution to help merchants quickly generate 3D models, animated images, and story videos at low or no cost, so that merchants can simply and effectively decorate their important assets (stores and goods), and can provide high-quality target images for stores and / or goods without professional knowledge reserves and professional equipment, which is helpful for merchants' brand expression and operation. It should be noted that models other than 3D models generated based on some video frames of the initial video, other types of videos different from the story video, and other forms of animated images different from GIF animated images are also within the scope of protection of this application.

[0078] It should be noted that, in the absence of conflict, the features given in this embodiment and other embodiments of the present application can be combined with each other, and steps S201 and S202 or similar terms do not limit the steps to be executed sequentially.

[0079] So far, the method provided in this embodiment has been described. The method generates the target image of the object to be photographed based on part of the video frame, so that a suitable target image can be obtained at a low technical cost, which is convenient for the merchant to operate. Further, the merchant provides the description information of the object to be photographed to the server, so that the server generates the target image of the object to be photographed (such as a product model or a store video) based on the description information, and uses it to generate a product page or a store page, so that the merchant can decorate the store and present the product at a low technical cost, and provide a good store and product presentation effect.

[0080] Based on the above embodiment, the second embodiment of the present application provides another image processing method. Figure 4 The method is described below. For the same parts, please refer to the description of the corresponding parts of the above embodiments and will not be repeated here. Figure 4 The image processing method shown is applied to the server and includes:

[0081] Step S401, obtaining an initial video of a merchant provided by a first terminal; the initial video is a video captured from multiple angles by the merchant under the guidance of the first terminal to operate the first terminal for an object to be photographed;

[0082] Step S402, extracting at least part of the video frames from the initial video, and generating a target image of the object to be photographed based on the at least part of the video frames;

[0083] Step S403: providing the target image to the second terminal so that the second terminal displays the target image.

[0084] As described in step S401, the server obtains the initial video provided by the first terminal. During implementation, the server receives the initial video sent by the first terminal, or the storage address information of the initial video provided by the first terminal, and obtains the initial video according to the storage address information. The initial video is a video captured from multiple angles. The video captured from multiple angles is a video captured around the object to be captured, including but not limited to a video captured 360 degrees around the product, a video obtained by stereoscopic panoramic shooting of the store, etc.

[0085] As described in step S402, video frames are extracted based on the initial video, and the video frames are used to generate the target image. Wherein, extracting at least part of the video frames from the initial video includes: extracting at least part of the video frames from the initial video according to a preset interval frame number or interval duration. Preferably, the initial video is a video within a preset shooting duration, for example, the initial video is: a video shot around the object to be shot within 10 seconds. Further, the server extracts video frames from the initial video within the preset shooting duration according to the preset interval frame number or interval duration. For example, the server extracts one video frame every 10 frames of the initial video shot around the object to be shot within 10 seconds, and uses the extracted video frames as materials to generate the target image of the object to be shot. Generating the target image based on the video frames of the initial video can ensure the correlation between the generated target image (such as a 3D model, a story video, and a gif) and the originally collected video information, thereby having a higher degree of restoration of the object to be shot.

[0086] In this embodiment, it also includes: receiving description information for the initial video provided by the first terminal; correspondingly, generating the target image of the object to be photographed based on at least part of the video frame includes: generating the target image according to at least part of the video frame and the description information. The description information can be used to extract visual effect features for determining the target image (to obtain a target image with corresponding visual effects), and can also be used to extract information for generating a story video. Moreover, the description information can also be used in the method of generating motion effects. The description information is converted into text information as input to the text-generated video model, and the text-generated video model uses multi-frame rate hierarchical training to obtain a high frame rate motion effect video as the target image.

[0087] In one embodiment, the generating of the target image according to the at least part of the video frame and the description information includes: determining the visual effect characteristics of the object to be photographed based on the description information; generating the target image according to the visual effect characteristics of the object to be photographed and the at least part of the video frame, and providing the user with a corresponding visual effect after the target image is displayed on the second terminal, that is, the visual effect of the object to be photographed displayed on the second terminal viewed by the user matches the description information provided by the merchant. Of course, the target image can also be provided to the first terminal and displayed on the first terminal for the merchant to preview, so that the merchant can determine whether the presented visual effect meets the merchant's expectations, and assist the merchant in deciding whether to display the target image to the user. An application scenario of the method is to provide merchants in the catering industry with a solution for quickly generating target images that are close to the merchant's dishes and / or the actual situation of the store and have been processed at a low technical cost. Dishes are broadly defined and refer to the goods and / or services provided by merchants in the catering industry to users. Wherein, the object to be photographed is the dish provided by the merchant to the user; then the determining of the visual effect features of the object to be photographed based on the description information includes: obtaining one or more dish attributes of the dish according to the description information of the dish; determining the visual effect features of the dish according to the dish attributes; generating the target image according to the visual effect features of the object to be photographed and at least part of the video frame includes: generating the target image of the dish according to the visual effect features of the dish and at least part of the video frame. Wherein, the dish attributes include at least one of the dish category attributes, ingredient attributes, taste attributes, and atmosphere attributes; the target image of the dish includes image information and / or text information representing the visual effects corresponding to the dish attributes. The visual effects of the target image of the dish generated by the server include any of the following visual effects: hot air effect, ice effect, bubble effect, heart-shaped effect, picture switching display dynamic effect, motion lens dynamic effect, and lighting dynamic effect.

[0088] In one embodiment, the method includes: using an image generated according to at least part of the video frame (including at least one of a 3D model, a dynamic image, and a video of the object to be photographed) as an initial target image; synthesizing audio according to the description information, fusing the audio with the initial target image, and using the audio and video data obtained after the fusion as the target image, and the target image is used to be displayed on the second terminal. The fused audio and video data is the target image finally displayed on the second terminal. After the target image is displayed on the second terminal, the corresponding story video is provided to the user, that is, the object to be photographed displayed in the form of a story on the second terminal viewed by the user matches the description information provided by the merchant. Of course, the target image can also be provided to the first terminal and displayed on the first terminal for the merchant to preview, so that the merchant can determine whether the presented story effect meets the merchant's expectations, and assist the merchant in deciding whether to display the target image to the user.

[0089] As shown in step S403, the target image is displayed on the second terminal. Preferably, the object to be photographed is the store and / or the product of the merchant; the initial video includes a store video collected for the store of the merchant, and / or a product video collected for the product of the merchant; accordingly, the target image includes a store story video or a store 3D panoramic model generated corresponding to the store video, and / or a product animated image or a product 3D model generated corresponding to the product video. In the present application, the specific method for the second terminal to obtain the target image is not specifically limited. In one acquisition method, the first page and / or the second page carries the target image, and the second terminal displays the target image by loading the first page and / or the second page. Among them, it also includes the second terminal setting or editing the first page and / or the second page, specifically including: when the object to be photographed is the commodity of the merchant, receiving the first page editing information sent by the first terminal, using the target image corresponding to the commodity and the commodity description information of the commodity to set the first page; and / or, when the object to be photographed is the store of the merchant, receiving the second page editing information sent by the first terminal, using the target image corresponding to the store and the store description information of the store to set the second page. For example, the first page includes a commodity page, and the commodity page includes but is not limited to a commodity details page, an event venue page, etc. The second page includes a store page, and the store page includes but is not limited to a store basic page, a store list page, a channel advertising page, etc. The second terminal can obtain the first page and / or the second page through the user APP for display. In another acquisition method, the second terminal interacts with the user using the second terminal in all directions through computer technology so that the user can watch the real scene to restore and display the target image, specifically including the second terminal integrating the acquired target image with the real scene photographed by the second terminal for display. The second terminal can interact with the server in all directions through the user APP.

[0090] In this embodiment, it also includes: providing the target image to the first terminal and displaying it on the first terminal, so that the merchant can operate the target image. The merchant can interact with the server through the merchant APP to perform the operation. This application does not limit the specific content of the operation, and existing operations or operations that can be inferred based on the existing ones are within the protection scope of this application. For example, the operation may include but is not limited to: the first terminal receives the merchant to modify or supplement the corresponding description information and sends it to the server, so that the server regenerates the target image based on the modified or supplemented description information; the first terminal receives the merchant submitting the target image for compliance review, and the target image that passes the compliance review can be displayed on the second terminal to present to the user; the first terminal receives the visual effect indicated by the merchant and sends it to the server, so that the server modifies or regenerates the target image according to the indicated visual effect; the first terminal downloads or downloads and stores the target image, etc.

[0091] Of course, at least some of the steps of this embodiment can be applied to the first terminal, for example, step S402 can be applied to the first terminal, that is, the first terminal responds to the first instruction for guiding the merchant to provide the initial video, obtains the initial video of the object to be photographed collected from multiple angles, extracts at least part of the video frames from the initial video, and generates the target image of the object to be photographed based on the at least part of the video frames. The generated target image can be sent to the server, and the server provides the target image to the second terminal so that the second terminal displays the target image. Thus, when the first terminal has the ability to synthesize the target image, the target image can be directly synthesized, and the target image includes at least one of the animated image, 3D model, and story video of the object to be photographed.

[0092] Of course, the method can not only be used to provide merchants with a solution for quickly generating target images that are close to the merchant's goods and / or stores with low technical costs, but can also be extended to other scenarios without conflict. For example, in a live or recorded broadcast scenario, it can provide merchants with a solution for quickly generating target images that are close to the merchant's goods and / or stores in real life and have been processed to a certain extent with low technical costs, so that the merchant's goods and / or stores can be displayed in an all-round manner with decoration that is close to the real thing, thereby helping merchants to operate.

[0093] So far, the method provided in this embodiment has been described, and the method is applied to the server. In this method, the merchant is guided to collect videos of the object to be photographed through the first terminal, and the video of the object to be photographed can be photographed from multiple angles without additional professional equipment and more professional shooting knowledge. The server generates the target image of the object to be photographed based on part of the video frames, so that a suitable target image can be obtained at a low technical cost, which is convenient for the merchant to operate. The target image is displayed on the second terminal for users using the second terminal to browse the target image. Good presentation quality and effect can improve the user experience.

[0094] Based on the above embodiment, the third embodiment of the present application provides another image processing method. Figure 5 The method is described below. For the same parts, please refer to the description of the corresponding parts of the above embodiments and will not be repeated here. Figure 5 The image processing method shown is applied to the second terminal, including:

[0095] Step S501, in response to a page loading instruction, loading a page including a target image; wherein the target image is generated by extracting at least a portion of video frames from an initial video of the object to be photographed provided by the first terminal, and based on the at least a portion of the video frames; the initial video is obtained by the first terminal guiding the merchant to operate the first terminal to capture the object to be photographed from multiple angles;

[0096] Step S502, displaying the target image to assist the user in deciding whether to select the object to be photographed for transaction.

[0097] Preferably, the object to be photographed is the store and / or product of the merchant; the initial video includes a store video collected for the store of the merchant, and / or a product video collected for the product of the merchant; accordingly, the target image includes a store story video or a store 3D panoramic model generated corresponding to the store video, and / or a product animated image or a product 3D model generated corresponding to the product video. In this application, the specific method by which the second terminal obtains the target image is not specifically limited.

[0098] In one acquisition method, the first page and / or the second page carries the target image, and the second terminal displays the target image by loading the first page and / or the second page.

[0099] As described in step S501, the second terminal loads a page of a target image of the object to be photographed, and the page includes a first page and / or a second page. Accordingly, the response to the page loading instruction to load the page including the target image includes: responding to the loading instruction of the first page, loading the first page, the target image included in the first page is a product animation or a product 3D model; or, responding to the loading instruction of the second page, loading the second page, the target image included in the second page is a store story video or a store 3D panoramic model. For example, the first page includes a product page, and the product page includes but is not limited to a product details page, an event venue page, etc. The second page includes a store page, and the store page includes but is not limited to a store basic page, a store list page, a channel advertising page, etc.

[0100] As described in step 502, the target image is displayed. In an example of practical application, the product page is specifically a product details page, and the store page specifically includes a product list page of the store. The product list page can display a product video, and the product details page can display a product 3D model. The second terminal can obtain the first page and / or the second page through the user APP for display.

[0101] In another acquisition method, the second terminal interacts with the user using the second terminal in all directions through computer technology so that the user can view the real scene and restore the target image, which specifically includes the second terminal integrating the acquired target image with the real scene captured by the second terminal. The second terminal can interact with the server in all directions through the user APP.

[0102] One application scenario of the method is to provide catering merchants with a solution for quickly generating a target image that is close to the merchant's dishes and / or the actual situation of the store and has been processed in a certain manner at a low technical cost, and the dish is the object to be photographed. When the object to be photographed is a dish, the target image is a product animation or a product 3D model of the dish, and the visual effects of the target image include any of the following visual effects: hot air effect, ice effect, bubble effect, heart-shaped effect, picture switching display effect, motion lens effect, and lighting effect. The target image is displayed on the second terminal with the above visual effects to assist the user in making a decision to buy or not buy.

[0103] In this embodiment, the target image also includes a story video generated based on the description information provided by the merchant. Specifically: the server synthesizes audio according to the description information corresponding to the initial video, fuses the audio with the initial target image generated based on the initial video, and displays the fused audio and video data on the second terminal. The fused audio and video data can be understood as the target image finally displayed on the second terminal. After the target image is displayed on the second terminal, the corresponding story video is provided to the user, that is, the object to be photographed displayed in the form of a story on the second terminal viewed by the user matches the description information provided by the merchant. Of course, the target image can also be provided to the first terminal and displayed on the first terminal for the merchant to preview, so that the merchant can determine whether the presented story effect meets the merchant's expectations, and assist the merchant in deciding whether to display the target image to the user.

[0104] In this embodiment, it also includes receiving the user's operation on the target image displayed on the second terminal. Specifically, it includes: the second terminal receives the user's operation behavior information on the target image, and performs at least one of the following operations on the target image according to the operation behavior information: rotation, flipping, scaling, displaying corresponding description information corresponding to the user's current perspective, and displaying the image after the operation corresponding to the operation instruction and the user operation. For example, the target image is a 3D model of the object to be photographed, and the second terminal receives the user's operation gesture, rotates, flips, and scales the 3D model with a motion lens effect according to the user's operation gesture, and displays the description information corresponding to the perspective in association with different perspectives. For another example, if a perspective of the target image is associated with a switch operation, the user's switch operation trigger is received to display the image effect corresponding to on or off.

[0105] So far, the method provided in this embodiment has been described, and the method is applied to the second terminal. In this method, the merchant is guided by the first terminal to collect videos of the object to be photographed, and the video of the object to be photographed can be photographed from multiple angles without additional professional equipment and more professional shooting knowledge. The server generates the target image of the object to be photographed based on part of the video frames, so that a suitable target image can be obtained at a low technical cost, which is convenient for the merchant to operate. The target image is displayed on the second terminal for users using the second terminal to browse the target image, helping users make decisions, and good presentation quality and effect can improve the user experience.

[0106] Corresponding to the first embodiment, the fourth embodiment of the present application provides an image processing device. For the relevant parts, please refer to the description of the corresponding method embodiment. Figure 6 , the image processing device shown in the figure comprises:

[0107] The acquisition unit 601 is configured to acquire an initial video of the object to be photographed acquired from multiple angles in response to a first instruction for guiding the merchant to provide an initial video;

[0108] A sending unit 602 is configured to provide the initial video to the server in response to a second instruction for providing the initial video to the server;

[0109] Wherein, the server extracts at least part of the video frames from the initial video, and generates the target image of the object to be photographed based on the at least part of the video frames.

[0110] Optionally, the acquisition unit 601 is specifically used for: the first terminal is provided with a camera device; and displaying first guidance information for guiding the merchant to operate the first terminal to shoot around the object to be photographed, so as to capture the initial video.

[0111] Optionally, the acquisition unit 601 is specifically used to: detect the shooting angle of the camera device for the object to be photographed; update the first guidance information according to the change of the shooting angle to guide the merchant to operate the first terminal to adjust the shooting angle, and capture a full-range video around the object to be photographed as the initial video.

[0112] Optionally, the first guidance information further includes guidance information for guiding the merchant to capture the initial video from multiple viewing angles including the front, side, top view, and top view of the object to be photographed.

[0113] Optionally, the acquisition unit 601 is specifically used to: display second guidance information for guiding the merchant to operate the first terminal to shoot around the object to be photographed within a preset shooting time, so as to obtain the initial video within the preset shooting time.

[0114] Optionally, the target image is generated by extracting video frames from the initial video by the server according to a preset interval frame number or interval duration, and using the extracted video frames.

[0115] Optionally, the sending unit 602 is specifically used to: provide description information for the initial video to the server; correspondingly, the target image is an image generated by the server according to at least part of the video frame and the description information.

[0116] Optionally, the target image is generated by the server according to the visual effect characteristics of the object to be photographed and at least part of the video frame, and the target image provides corresponding visual effects to the user after being displayed; wherein, the visual effect characteristics of the object to be photographed are determined based on the description information.

[0117] Optionally, the object to be photographed is a dish provided by the merchant to the user; the server obtains one or more dish attributes of the dish according to the description information of the dish, determines the visual effect characteristics of the dish according to the dish attributes, and generates a target image of the dish according to the visual effect characteristics of the object to be photographed and at least part of the video frame.

[0118] Optionally, the dish attributes include at least one of dish category attributes, ingredient attributes, taste attributes, and atmosphere attributes; the target image of the dish includes image information and / or text information representing the visual effects corresponding to the dish attributes.

[0119] Optionally, the visual effects of the target image of the dish include any of the following visual effects: hot steam effect, iced effect, bubble effect, heart-shaped effect, picture switching display effect, motion lens effect, and lighting effect.

[0120] Optionally, the object to be filmed is the store and / or goods of the merchant; the initial video includes a store video collected for the store of the merchant, and / or a product video collected for the goods of the merchant; accordingly, the target image includes a store story video or a store 3D panoramic model generated corresponding to the store video and corresponding description information, and / or a product animated image or a product 3D model generated corresponding to the product video and corresponding description information.

[0121] Optionally, the sending unit 602 is specifically used to: when the object to be photographed is a product of the merchant, in response to a first page setting instruction, send first page editing information to the server to instruct the use of a target image corresponding to the product and the product description information of the product to set the first page; and / or, when the object to be photographed is a store of the merchant, in response to a second page setting instruction, send second page editing information to the server to instruct the use of a target image corresponding to the store and the store description information of the store to set the second page.

[0122] Optionally, the target image is provided to a second terminal and displayed on the second terminal to assist the user in deciding whether to select the object to be photographed for transaction.

[0123] Corresponding to the second embodiment, the fifth embodiment of the present application provides an image processing device. For the relevant parts, please refer to the description of the corresponding method embodiment. Figure 7 , the image processing device shown in the figure comprises:

[0124] An initial video acquisition unit 701 is used to acquire an initial video of a merchant provided by a first terminal; the initial video is a video captured from multiple angles by the merchant under the guidance of the first terminal to operate the first terminal for the object to be photographed;

[0125] A target image generating unit 702 is configured to extract at least a portion of video frames from the initial video, and generate a target image of the object to be photographed based on the at least a portion of the video frames;

[0126] The display unit 703 is configured to provide the target image to the second terminal so that the second terminal displays the target image.

[0127] Optionally, the videos captured from multiple angles are videos captured around the object to be photographed.

[0128] Optionally, the target image generating unit 702 is specifically configured to extract at least part of the video frames from the initial video according to a preset interval frame number or interval duration.

[0129] Optionally, the target image generating unit 702 is specifically configured to: receive description information for the initial video provided by the first terminal; and generate the target image according to at least part of the video frame and the description information.

[0130] Optionally, the target image generation unit 702 is specifically used to: determine the visual effect characteristics of the object to be photographed based on the description information; generate the target image according to the visual effect characteristics of the object to be photographed and at least part of the video frame, and the target image is displayed on the second terminal to provide a corresponding visual effect to the user.

[0131] Optionally, the object to be photographed is a dish provided by the merchant to the user; the target image generation unit 702 is specifically used to: obtain one or more dish attributes of the dish based on the description information of the dish; determine the visual effect characteristics of the dish based on the dish attributes; and generate a target image of the dish based on the visual effect characteristics of the dish and at least part of the video frame.

[0132] Optionally, the dish attributes include at least one of dish category attributes, ingredient attributes, taste attributes, and atmosphere attributes; the target image of the dish includes image information and / or text information representing the visual effects corresponding to the dish attributes.

[0133] Optionally, the visual effects of the target image of the dish include any of the following visual effects: hot steam effect, iced effect, bubble effect, heart-shaped effect, picture switching display effect, motion lens effect, and lighting effect.

[0134] Optionally, the target image generation unit 702 is specifically used to: use the image generated according to the at least part of the video frame as the initial target image; synthesize audio according to the description information, fuse the audio with the initial target image, and use the audio and video data obtained after the fusion as the target image, and the target image is used to be displayed on the second terminal.

[0135] Optionally, the object to be filmed is the store and / or goods of the merchant; the initial video includes a store video collected for the store of the merchant, and / or a product video collected for the goods of the merchant; accordingly, the target image includes a store story video or a store 3D panoramic model generated corresponding to the store video, and / or a product animated image or a product 3D model generated corresponding to the product video.

[0136] Optionally, the display unit 703 is specifically used to: when the object to be photographed is a product of the merchant, receive first page editing information sent by the first terminal, and use the target image corresponding to the product and the product description information of the product to set the first page; and / or, when the object to be photographed is a store of the merchant, receive second page editing information sent by the first terminal, and use the target image corresponding to the store and the store description information of the store to set the second page.

[0137] Optionally, the display unit 703 is specifically configured to: provide the target image to the first terminal and display it on the first terminal, so that the merchant can operate the target image.

[0138] Corresponding to the third embodiment, the sixth embodiment of the present application provides an image processing device. For the relevant parts, please refer to the description of the corresponding method embodiment. Figure 8 , the image processing device shown in the figure comprises:

[0139] The page loading unit 801 is configured to load a page including a target image in response to a page loading instruction; wherein the target image is generated based on at least a portion of the video frames extracted by the server from an initial video of the object to be photographed provided by the first terminal; and the initial video is obtained by the first terminal guiding the merchant to operate the first terminal to capture the object to be photographed from multiple angles;

[0140] The display unit 802 is used to display the target image to assist the user in deciding whether to select the object to be photographed for transaction.

[0141] Optionally, the page loading unit 801 is specifically used to: load the first page in response to a loading instruction of the first page, wherein the target image included in the first page is a product animation or a product 3D model; or, load the second page in response to a loading instruction of the second page, wherein the target image included in the second page is a store story video or a store 3D panoramic model.

[0142] Optionally, when the object to be photographed is a dish, the target image is a product animated image or a product 3D model of the dish, and the visual effects of the target image include any of the following visual effects: hot air effect, ice effect, bubble effect, heart-shaped effect, picture switching display effect, motion lens effect, and lighting effect.

[0143] Optionally, the device also includes a user operation unit for receiving the user's operation behavior information on the target image, and performing at least one of the following operations on the target image according to the operation behavior information: rotating, flipping, scaling, displaying corresponding description information corresponding to the user's current viewing angle, and displaying the image after the operation corresponding to the operation instruction.

[0144] Based on the above embodiments, the seventh embodiment of the present application provides an electronic device. For the relevant parts, please refer to the corresponding description of the above embodiments. Fig. 9 The electronic device shown in the figure includes: a memory 901 and a processor 902; the memory is used to store a computer program, and after the computer program is run by the processor, the method provided in the embodiment of the present application is executed.

[0145] Based on the above embodiments, the eighth embodiment of the present application provides a computer storage medium. For the relevant parts, please refer to the corresponding description of the above embodiments. Fig. 9 The memory in the figure can be understood as the storage medium. The computer storage medium stores computer execution instructions, which are used to implement the method provided in the embodiment of the present application when executed by the processor.

[0146] In a typical configuration, an electronic device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory. The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0147] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0148] Although the present application is disclosed as above in the form of a preferred embodiment, it is not intended to limit the present application. Any technical personnel in this field may make possible changes and modifications without departing from the spirit and scope of the present application. Therefore, the scope of protection of the present application shall be based on the scope defined by the claims of the present application.

Claims

1. An image processing method, characterized in that: Applied to the first terminal, comprising: In response to a first instruction for guiding a merchant to provide an initial video, obtaining an initial video of the object to be photographed collected from multiple angles; In response to a second instruction for providing the initial video to the server, providing the initial video to the server; Wherein, the server extracts at least part of the video frames from the initial video, and generates the target image of the object to be photographed based on the at least part of the video frames.

2. The method according to claim 1, characterized in that: The step of obtaining, in response to a first instruction for guiding a merchant to provide an initial video, an initial video of the object to be photographed collected from multiple angles includes: The first terminal is provided with a camera device; The first guiding information for guiding the merchant to operate the first terminal to shoot around the object to be shot is displayed to shoot and obtain the initial video.

3. The method according to claim 2, characterized in that Also includes: Detecting a shooting angle of the camera device with respect to the object to be photographed; The first guidance information is updated according to the change of the shooting angle to guide the merchant to operate the first terminal to adjust the shooting angle and shoot an all-round video around the object to be shot as the initial video.

4. The method according to claim 2, characterized in that: The first guidance information also includes guidance information for guiding the merchant to capture the initial video from multiple viewing angles including the front, side, top, and top directions of the object to be photographed.

5. The method according to claim 2, characterized in that: Also includes: The second guiding information for guiding the merchant to operate the first terminal to shoot around the object to be shot within a preset shooting time is displayed, so as to shoot and obtain the initial video within the preset shooting time.

6. The method according to claim 1, characterized in that The target image is generated by extracting video frames from the initial video by the server according to a preset interval frame number or interval duration, and using the extracted video frames.

7. The method according to claim 1, characterized in that Also includes: Providing description information for the initial video to the server; Correspondingly, the target image is an image generated by the server according to at least part of the video frame and the description information.

8. The method according to claim 7, characterized in that The target image is generated by the server according to the visual effect characteristics of the object to be photographed and at least part of the video frame, and the target image provides a corresponding visual effect to the user after being displayed; Wherein, the visual effect features of the object to be photographed are determined based on the description information.

9. An image processing method, characterized in that: Applied to the server, including: Acquire an initial video of the merchant provided by the first terminal; the initial video is a video captured from multiple angles by the merchant under the guidance of the first terminal to operate the first terminal for the object to be photographed; Extracting at least a portion of video frames from the initial video, and generating a target image of the object to be photographed based on the at least a portion of the video frames; The target image is provided to a second terminal, so that the second terminal displays the target image.

10. An image processing method, characterized in that: Applied to the second terminal, including: In response to the page loading instruction, a page including a target image is loaded; wherein the target image is generated by extracting at least a portion of video frames from an initial video of the object to be photographed provided by the first terminal, and the server side extracts at least a portion of the video frames; the initial video is obtained by the first terminal guiding the merchant to operate the first terminal to capture the object to be photographed from multiple angles; The target image is displayed to assist the user in deciding whether to select the object to be photographed for transaction.

Citation Information

Patent Citations

  • Information generation method and device, computer equipment and storage medium

    CN113141498A

  • Marketing poster generation method and electronic equipment

    CN115271808A