Search

CN-115908694-B - Video generation method, information display method and computing device

CN115908694BCN 115908694 BCN115908694 BCN 115908694BCN-115908694-B

Abstract

The embodiment of the application provides a video generation method, an information display method and computing equipment. The method comprises the steps of obtaining at least one original image containing a target object, constructing three-dimensional models corresponding to the at least one original image respectively, transforming the at least one three-dimensional model into a plurality of target images by utilizing a plurality of transformation parameters, determining material information corresponding to the target object, and generating a target video based on the plurality of target images and the material information. The technical scheme provided by the embodiment of the application improves the visual effect of the video and improves the video quality.

Inventors

  • ZHAN PENGXIN
  • LIU KUILONG
  • MEI BO

Assignees

  • 阿里巴巴（中国）有限公司

Dates

Publication Date
20260512
Application Date
20220922

Claims (13)

  1. 1. A video generation method, comprising: Acquiring at least one original image containing a target object; Constructing three-dimensional models respectively corresponding to the at least one original image; Transforming at least one three-dimensional model into a plurality of target images using a plurality of transformation parameters; Determining the material information matched with the target object; Generating a target video based on the plurality of target images and the material information; Wherein the method further comprises: Determining a plurality of layers contained in the original image; Determining the corresponding boundary area of one layer on the other layer in two adjacent layers; taking the boundary area corresponding to the original image as the boundary area corresponding to each of the plurality of target images; And filling any boundary area in any target image with the target color.
  2. 2. The method of claim 1, wherein generating a target video based on the plurality of target images and the material information comprises: Synthesizing the material information and the target images; a target video is generated based on the plurality of target images after the synthesis processing.
  3. 3. The method of claim 2, wherein the material information includes at least one material image, and wherein the synthesizing the material information with the plurality of target images includes: Determining the corresponding relation between the at least one material image and at least one target image; Any one of the material images is synthesized into a target image corresponding to the material image.
  4. 4. The method of claim 2, wherein the material information includes document information, and wherein the synthesizing the material information with the plurality of target images comprises: and synthesizing the document information into at least one target image in the plurality of target images.
  5. 5. The method of claim 3, wherein the determining material information that the target object matches comprises: and determining at least one material image according to the object category of the target object.
  6. 6. The method of claim 4, wherein the determining the material information that the target object matches comprises: And generating the document information of the target object according to the object related information of the target object, wherein the object related information comprises one or more of object description information, object evaluation information, object category information and an object image.
  7. 7. The method of claim 1, wherein transforming at least one three-dimensional model into a plurality of target images using a plurality of transformation parameters comprises: determining a plurality of transformation parameters corresponding to at least one lens transporting effect; Transforming the at least one three-dimensional model into a plurality of target images using the plurality of transformation parameters.
  8. 8. A video generation method, comprising: acquiring a commodity image of a target commodity; constructing a three-dimensional model corresponding to the commodity image; transforming the three-dimensional model into a plurality of target images using a plurality of transformation parameters; determining material information matched with the target commodity; Generating a target video based on the material information and the plurality of target images; Wherein the method further comprises: determining a plurality of layers contained in the commodity image; Determining the corresponding boundary area of one layer on the other layer in two adjacent layers; taking the boundary area corresponding to the commodity image as the boundary area corresponding to each of the plurality of target images; And filling any boundary area in any target image with the target color.
  9. 9. The method of claim 8, wherein the acquiring the merchandise image of the target merchandise comprises: Receiving an image processing request of a user, wherein the image processing request comprises the commodity image; Or alternatively And receiving an image processing request of a user, determining index information corresponding to a target commodity contained in the image processing request, and identifying a commodity image taking the target commodity as an image main body from a commodity detail page of the target commodity based on the index information.
  10. 10. The method of claim 8, wherein generating the target video comprises: Receiving a user release request, and updating an commodity detail page by using the target video; Or alternatively Establishing a link relation between the target video and the commodity detail page, and publishing the target video to the commodity popularization page so as to detect triggering operation aiming at the target video on the commodity popularization page and jump to the commodity detail page based on the link relation.
  11. 11. An information display method, comprising: Providing a display interface; displaying image processing prompt information on the display interface; The method comprises the steps of responding to image processing operation triggered by the image processing prompt information, sending an image processing request to a server, wherein the image processing request is used for determining at least one original image containing a target object by the server, constructing three-dimensional models corresponding to the at least one original image respectively, transforming the at least one three-dimensional model into a plurality of target images by utilizing a plurality of transformation parameters, determining material information matched with the target object, generating a target video based on the plurality of target images and the material information, determining a plurality of image layers contained in the original image by the server, determining a boundary area corresponding to one image layer on the other image layer in two adjacent image layers, taking the boundary area corresponding to the original image as the boundary area corresponding to the plurality of target images respectively, and filling target colors into any boundary area in any target image; and playing the target video on the display interface.
  12. 12. A computing device comprising a processing component, a storage component, the storage component storing one or more computer instructions for invocation and execution by the processing component to implement the video generation method of any one of claims 1-7 or the video generation method of any one of claims 8-10 or the information display method of claim 11.
  13. 13. A computer storage medium storing a computer program which, when executed by a computer, implements the video generation method according to any one of claims 1 to 7 or the video generation method according to any one of claims 8 to 10 or the information display method according to claim 11.

Description

Video generation method, information display method and computing device Technical Field The embodiment of the application relates to the technical field of computer application, in particular to a video generation method, an information display method and computing equipment. Background Compared with pictures, videos have the advantages of better visual effect and the like due to more image and vividness, and gradually become one of main modes for popularizing, propaganda or beautifying objects. Because the video is generated by adopting a means of shooting the object, the shooting cost is high, in the prior art, when the object image exists, a mode of splicing a plurality of object images can be adopted to generate the video, but the video generated by the mode has poor visual effect. Disclosure of Invention The embodiment of the application provides a video generation method, an information display method and computing equipment, which are used for solving the technical problem of poor visual effect of videos in the prior art. In a first aspect, an embodiment of the present application provides a video generating method, including: Acquiring at least one original image containing a target object; Constructing three-dimensional models respectively corresponding to the at least one original image; Transforming at least one three-dimensional model into a plurality of target images using a plurality of transformation parameters; Determining the material information matched with the target object; And generating a target video based on the plurality of target images and the material information. In a second aspect, an embodiment of the present application provides a video generating method, including: acquiring a commodity image of a target commodity; constructing a three-dimensional model corresponding to the commodity image; transforming the three-dimensional model into a plurality of target images using a plurality of transformation parameters; determining material information matched with the target commodity; And generating a target video based on the material information and the target images. In a third aspect, an embodiment of the present application provides an information display method, including: Providing a display interface; displaying image processing prompt information on the display interface; the method comprises the steps of responding to image processing operation triggered by the image processing prompt information, sending an image processing request to a server, wherein the image processing request is used for determining at least one original image containing a target object by the server, constructing three-dimensional models respectively corresponding to the at least one original image, transforming at least one three-dimensional model into a plurality of target images by utilizing a plurality of transformation parameters, determining material information matched with the target object, and generating a target video based on the plurality of target images and the material information; and playing the target video on the display interface. In a fourth aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component, where the storage component stores one or more computer instructions, and the one or more computer instructions are used to be invoked and executed by the processing component to implement a video generating method according to the first aspect, a video generating method according to the second aspect, or an information displaying method according to the third aspect. In a fifth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, where the computer program is executed by a computer to implement a video generating method as described in the first aspect, a video generating method as described in the second aspect, or an information displaying method as described in the third aspect. In the embodiment of the application, at least one original image containing a target object is obtained, a three-dimensional model corresponding to the at least one original image is constructed, the at least one three-dimensional model is transformed into a plurality of target images by utilizing a plurality of transformation parameters, material information corresponding to the target object is determined, and a target video is generated based on the plurality of target images and the material information. These and other aspects of the application will be more readily apparent from the following description of the embodiments. Drawings In order to more clearly illustrate the embodiments of the present application or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of