WO2022037634A1 - 一种图片处理方法、装置、设备及存储介质 - Google Patents

一种图片处理方法、装置、设备及存储介质 Download PDF

Info

Publication number
WO2022037634A1
WO2022037634A1 PCT/CN2021/113463 CN2021113463W WO2022037634A1 WO 2022037634 A1 WO2022037634 A1 WO 2022037634A1 CN 2021113463 W CN2021113463 W CN 2021113463W WO 2022037634 A1 WO2022037634 A1 WO 2022037634A1
Authority
WO
WIPO (PCT)
Prior art keywords
picture
target object
special effect
background
segmentation
Prior art date
Application number
PCT/CN2021/113463
Other languages
English (en)
French (fr)
Inventor
张树鹏
李雅萌
王一同
刘思雪
田原
廖建军
文杰
Original Assignee
北京字节跳动网络技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京字节跳动网络技术有限公司 filed Critical 北京字节跳动网络技术有限公司
Priority to EP21857726.0A priority Critical patent/EP4170580A4/en
Priority to JP2023504566A priority patent/JP2023534750A/ja
Publication of WO2022037634A1 publication Critical patent/WO2022037634A1/zh
Priority to US18/090,181 priority patent/US20230162419A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/04—Context-preserving transformations, e.g. by using an importance map
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T13/00—Animation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—2D [Two Dimensional] image generation
    • G06T11/60—Editing figures and text; Combining figures or text
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/20—Linear translation of whole images or parts thereof, e.g. panning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/60—Rotation of whole images or parts thereof
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47—End-user applications
    • H04N21/472—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content
    • H04N21/47205—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content for manipulating displayed content, e.g. interacting with MPEG-4 objects, editing locally
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/222—Studio circuitry; Studio devices; Studio equipment
    • H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
    • H04N5/2628—Alteration of picture size, shape, position or orientation, e.g. zooming, rotation, rolling, perspective, translation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20212—Image combination
    • G06T2207/20221—Image fusion; Image merging
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2210/00—Indexing scheme for image generation or computer graphics
    • G06T2210/32—Image data format

Definitions

  • the present disclosure relates to the field of data processing, and in particular, to a picture processing method, apparatus, device, and storage medium.
  • the present disclosure provides a picture processing method, device, device and storage medium, which can display pictures to users in a three-dimensional and dynamic manner to meet users' needs for effect display of pictures.
  • the present disclosure provides a picture processing method, the method comprising:
  • the picture to be processed includes a target object segmentation picture and a background completion picture from the same original picture;
  • special effects processing is performed on the segmented image of the target object and the complementary background image respectively, so as to obtain the corresponding images of the segmented image of the target object and the complementary background image respectively.
  • the special effect pictures corresponding to the target object segmentation picture and the background completion picture respectively are synthesized into a special effect video corresponding to the original picture.
  • special effects processing is performed on the target object image segmentation picture and the background complementing picture to obtain the target object image segmentation picture.
  • the special effects pictures corresponding to the background completion pictures including:
  • the target object image segmentation picture is translated and enlarged according to a preset first direction to obtain a special effect picture corresponding to the target object image segmentation picture;
  • the preset first direction is right or left;
  • the preset second direction is left or right, and the preset second direction is It is assumed that the first direction and the preset second direction are different.
  • special effects processing is performed on the target object image segmentation picture and the background complementing picture to obtain the target object image segmentation picture.
  • the special effects pictures corresponding to the background completion pictures including:
  • the picture type of the target object image segmentation picture is a half-body picture, then the target object image segmentation picture is enlarged according to the forward direction, and the special effect picture corresponding to the target object image segmentation picture is obtained;
  • the special effect pictures corresponding to the target object segmentation picture and the background complementing picture, respectively are synthesized into a special effect video of the original picture, including:
  • the special effect pictures corresponding to the target object segmentation picture and the background completion picture respectively are synthesized into a rotation animation corresponding to the original picture.
  • the special effect pictures corresponding to the target object image segmentation picture and the background completion picture are synthesized into a rotation animation corresponding to the original picture, including:
  • the picture type of the target object segmentation picture is a half-body picture, then determine the connection point between the target object in the special effect picture corresponding to the target object segmentation picture and the special effect picture corresponding to the background complementing picture;
  • the special effect pictures corresponding to the target object segmentation picture and the background complementing picture respectively are synthesized into a rotation animation corresponding to the original picture.
  • the target object segmentation picture includes a portrait segmentation picture.
  • the method further includes:
  • the special effects videos corresponding to the plurality of original pictures are synthesized into an album.
  • the target object image segmentation picture and the background complementing picture are respectively subjected to special effects processing to obtain the target object image segmentation.
  • special effect pictures corresponding to the picture and the background complementing picture respectively, it also includes:
  • the picture type of the target object segmentation picture is determined to be a half-body picture; otherwise, the picture type of the target object segmentation picture is determined to be a full-body picture.
  • the present disclosure provides a picture processing apparatus, the apparatus comprising:
  • an acquisition module for acquiring a picture to be processed;
  • the picture to be processed includes a target object segmentation picture and a background completion picture from the same original picture;
  • a special effect processing module configured to perform special effects processing on the target object image segmentation picture and the background complementing picture based on the picture type of the target object image segmentation picture, to obtain the target object image segmentation picture and the background Complement the corresponding special effect pictures of the pictures;
  • the synthesis module is used for synthesizing the special effect pictures corresponding to the target object segmentation picture and the background completion picture respectively into a special effect video corresponding to the original picture.
  • the present disclosure provides a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the instructions are executed on a terminal device, the terminal device is made to implement the above method.
  • the present disclosure provides a device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, when the processor executes the computer program, Implement the above method.
  • the embodiment of the present disclosure provides a picture processing method. First, a target object segmentation picture and a background completion picture from the same original picture are determined as pictures to be processed, and secondly, based on the picture type of the target object segmentation picture, the target object segmentation picture is divided into pictures. Perform special effects processing with the background completion picture separately to obtain the corresponding special effects pictures for the two. Finally, the special effect pictures corresponding to the target object image segmentation picture and the background completion picture respectively are synthesized into the rotation animation corresponding to the original picture. In the embodiment of the present disclosure, the target object segmentation picture and the background completion picture from the same original picture are processed with special effects respectively, and then synthesized into a rotating animation of the original picture. Through the rotating animation, the embodiment of the present disclosure can show the user in a more three-dimensional and dynamic manner. The original picture meets the user's needs for the effect display of the picture.
  • FIG. 1 is a flowchart of a picture processing method according to an embodiment of the present disclosure
  • FIG. 2 is a structural block diagram of a picture processing apparatus according to an embodiment of the present disclosure
  • FIG. 3 is a structural block diagram of a picture processing device according to an embodiment of the present disclosure.
  • the present disclosure provides a picture processing method.
  • the target object image segmentation picture and the background completion picture from the same original picture are determined as the pictures to be processed, and then the target object segmentation picture is based on the target object.
  • Picture type the special effect processing is performed on the target object segmentation picture and the background completion picture respectively, and the special effect pictures corresponding to the two are obtained respectively.
  • the special effect pictures corresponding to the two are collectively called the rotation animation corresponding to the original picture.
  • an embodiment of the present disclosure provides a picture processing method.
  • a flowchart of a picture processing method provided by an embodiment of the present disclosure includes:
  • S101 Obtain a picture to be processed; the picture to be processed includes a target object segmentation picture and a background completion picture from the same original picture.
  • the target object in the original picture is separated from the background, and the target image segmentation picture and the background complementing picture corresponding to the original picture are obtained.
  • the target image segmentation picture includes the target object in the original picture
  • the background complement picture includes the background in the original picture.
  • the target objects may include portraits, animals, plants, etc., and usually the original picture includes at least one target object.
  • the target object is segmented from the original image, and a segmented image of the target image corresponding to the original image is obtained.
  • the area where the target object is removed can be completed to obtain a complete image as the background completion image corresponding to the original image.
  • the completion method can use the existing algorithm model to understand the content on the original image, and then complete the content based on the understood content.
  • the target object segmentation picture and the background complementing picture are determined as pictures to be processed.
  • S102 Based on the picture type of the target object image segmentation picture, perform special effects processing on the target object image segmentation picture and the background complementing picture respectively, to obtain the target object segmentation picture and the background complementing picture respectively The corresponding effect picture.
  • the picture before processing the picture, first identify the picture type of the target object segmentation picture, and then perform special effects on the target object segmentation picture and the background completion picture based on the special effect processing method corresponding to the picture type to which it belongs. deal with.
  • the picture types may include full-body pictures and half-body pictures.
  • full-body pictures and half-body pictures based on the features of the full-body pictures and half-body pictures, the embodiments of the present disclosure provide different processing methods.
  • the image type of the segmented image of the target object can be determined by identifying whether the segmented image of the target object contains foot features. Specifically, if the segmented image of the target object contains foot features, the segmented image of the target object is determined as a whole body image, otherwise, it is determined as a half-body image.
  • the embodiments of the present disclosure do not limit other methods for identifying the picture type to which the target object segmentation picture belongs.
  • the target object segmentation picture may include multiple target objects, such as a multi-person picture. If it is recognized that the multi-person picture contains not only full-body portraits, but also half-length portraits, in order to ensure the original picture. If the display effect is displayed, the multi-person picture can be determined as the picture type of the half-body picture, and the subsequent processing can be performed according to the special effect processing method of the half-body picture.
  • the target object in the target object segmentation picture includes a half-body object; if it is determined that the target object in the target object segmentation picture includes a half-body object, then determine that the picture type of the target object segmentation picture is Half-body picture; otherwise, determine that the picture type of the segmented picture of the target object is a full-body picture.
  • the characteristics of the animal and plant can be learned by means of big data learning, and then the picture type of the target object segmentation picture can be determined based on the learned characteristics, which is no longer in this embodiment of the present disclosure. Too much introduction.
  • the special effect processing method for the target object segmentation picture and the background complementing picture determine the special effect processing method for the target object segmentation picture and the background complementing picture, and respectively process the corresponding special effect processing methods. After the target object image segmentation picture and the background completion picture are processed with special effects, the corresponding special effects pictures are obtained respectively.
  • the target object image segmentation picture is translated and enlarged according to a preset first direction to obtain a special effect picture corresponding to the target object image segmentation picture;
  • the preset first direction is rightward or leftward.
  • the background completion picture is subjected to perspective rotation processing according to the preset second direction, so as to obtain special effect pictures corresponding to the background completion picture respectively; wherein, the preset second direction is left or right, and the preset first direction and the preset Let the second direction be different.
  • the segmented picture of the target object can be translated and enlarged according to the effect to the right, and at the same time, the background complementing picture can be subjected to the perspective rotation according to the effect of the left.
  • the target image segmentation picture may be translated and enlarged according to the effect to the left, and at the same time, the background completion picture may be subjected to perspective rotation according to the effect of the right.
  • the target object image segmentation picture belongs to a half-body picture
  • the target object image segmentation picture is enlarged in the forward direction to obtain a special effect picture corresponding to the target object image segmentation picture, and the background is supplemented
  • the whole picture is subjected to perspective rotation processing according to the effect that the front is pushed down to the preset angle, and the special effect picture corresponding to the background complement picture is obtained.
  • the preset angle may include any angle from 45 degrees to 90 degrees.
  • the present disclosure can satisfy the user's demand for three-dimensional dynamic display of pictures.
  • the embodiment of the present disclosure also performs enlargement processing on the target image segmentation picture, so as to highlight the target object in the original picture, which can improve the user experience to a certain extent.
  • S103 Synthesize special effect pictures corresponding to the target object segmentation picture and the background complementing picture respectively into a special effect video corresponding to the original picture.
  • the special effect pictures corresponding to the two are obtained respectively, and then they are synthesized into a special effect video corresponding to the original picture.
  • the target object in the original image can be displayed dynamically and stereoscopically, and the user experience can be improved.
  • the special effect pictures corresponding to the target object segmentation picture and the background completion picture respectively may be synthesized into a rotation animation corresponding to the original picture.
  • the special effect pictures corresponding to the target object segmentation picture and the background completion picture are synthesized into the rotation animation corresponding to the original picture. , so that there is a connection point between the target object in the synthesized rotating animation and the background complementing picture, so as to ensure the effect of the picture display.
  • the target object segmentation picture and the background completion picture from the same original picture are determined as the pictures to be processed, then the picture type of the target object segmentation picture is identified, and the picture is segmented based on the target object
  • the special effect processing is performed on the target object segmentation image and the background completion image, respectively, to obtain the special effect images corresponding to the two, and finally the special effect images corresponding to the two are collectively referred to as the rotation animation corresponding to the original image.
  • the present disclosure can display the original picture to the user in a more three-dimensional and dynamic manner, which satisfies the user's demand for displaying the effect of the picture.
  • the original picture may include multiple portrait pictures
  • the image processing method provided by the embodiment of the present disclosure may obtain a corresponding special effect video for each portrait picture, and then synthesize the respective special effect videos corresponding to the multiple portrait pictures. for the album.
  • the three-dimensional dynamic effect of multiple pictures can be displayed at the same time, which satisfies the user's effect requirement of converting pictures into videos for three-dimensional dynamic display, and improves the user's experience.
  • the present disclosure further provides a picture processing apparatus.
  • FIG. 2 a schematic structural diagram of a picture processing apparatus provided by an embodiment of the present disclosure, the apparatus includes:
  • the obtaining module 201 is used for obtaining the picture to be processed; the picture to be processed includes the target object segmentation picture and the background completion picture from the same original picture;
  • the special effect processing module 202 is configured to perform special effects processing on the target image segmentation picture and the background completion picture based on the picture type of the target object image segmentation picture, to obtain the target object image segmentation picture and the The special effect pictures corresponding to the background completion pictures respectively;
  • the synthesis module 203 is used for synthesizing the special effect pictures corresponding to the target object segmentation picture and the background complementing picture respectively into a special effect video corresponding to the original picture.
  • the special effect processing module 202 includes:
  • the first processing submodule is configured to translate and enlarge the segmented image of the target object according to a preset first direction when the image type of the segmented image of the target object is a whole body image, to obtain the image of the target object
  • the first processing sub-module is used to perform perspective rotation processing on the background completion picture according to a preset second direction, so as to obtain special effect pictures corresponding to the background completion picture respectively; the preset second direction is left or To the right, the preset first direction and the preset second direction are different.
  • the special effect processing module 202 includes:
  • the third processing sub-module is configured to, when the picture type of the target object segmentation picture is a half-body picture, amplify the target object segmentation picture according to the forward direction, and obtain the special effect corresponding to the target object segmentation picture picture;
  • the fourth processing sub-module is configured to perform perspective rotation processing on the background complementing picture according to the effect that the front side is pushed down to a preset angle, so as to obtain a special effect picture corresponding to the background complementing picture.
  • the synthesizing module 203 is specifically configured to synthesize special effect pictures corresponding to the target object segmentation picture and the background complementing picture respectively into a rotation animation corresponding to the original picture.
  • the synthesis module 203 includes:
  • the first determination submodule is used to determine the special effect corresponding to the target object in the special effect picture corresponding to the target object image segmentation picture and the background completion picture when the picture type of the target object segmentation picture is a half-body picture connection points between pictures;
  • the synthesis sub-module is used for synthesizing the special effect pictures corresponding to the target object image segmentation picture and the background completion picture respectively into the rotation animation corresponding to the original picture based on the connection point.
  • the target object segmentation picture includes a portrait segmentation picture.
  • the device further includes:
  • the video synthesis module is used for synthesizing the special effect videos corresponding to the plurality of original pictures into an album.
  • the device further includes:
  • a first determining module configured to determine whether the target object in the target object segmentation picture includes a half-body object
  • a second determination module configured to determine that the picture type of the target object segmentation picture is a half-body picture when the determination result of the first determination module is yes;
  • a third determination module configured to determine that the picture type of the target object segmentation picture is a whole body picture when the determination result of the first determination module is no.
  • the picture processing apparatus first determines the target object image segmentation picture and the background completion picture from the same original picture as the picture to be processed, and then divides the target object image and background based on the picture type of the target object segmentation picture.
  • the completed pictures are processed with special effects respectively to obtain the special effect pictures corresponding to the two respectively, and finally the special effect pictures corresponding to the two are collectively referred to as the rotation animation corresponding to the original picture.
  • the present disclosure can display the original picture to the user in a more three-dimensional and dynamic manner, which satisfies the user's demand for displaying the effect of the picture.
  • an embodiment of the present disclosure further provides a picture processing device, as shown in FIG. 3 , which may include:
  • the number of processors 301 in the image processing device may be one or more, and one processor is taken as an example in FIG. 3 .
  • the processor 301 , the memory 302 , the input device 303 and the output device 304 may be connected by a bus or in other ways, wherein the connection by a bus is taken as an example in FIG. 3 .
  • the memory 302 can be used to store software programs and modules, and the processor 301 executes various functional applications and data processing of the image processing apparatus by running the software programs and modules stored in the memory 302 .
  • the memory 302 may mainly include a stored program area and a stored data area, wherein the stored program area may store an operating system, an application program required for at least one function, and the like. Additionally, memory 302 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
  • the input device 303 can be used to receive input numerical or character information, and generate signal input related to user setting and function control of the picture processing apparatus.
  • the processor 301 loads the executable files corresponding to the processes of one or more application programs into the memory 302 according to the following instructions, and the processor 301 runs the executable files stored in the memory 302 application, so as to realize various functions of the above picture processing device.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Signal Processing (AREA)
  • Multimedia (AREA)
  • Databases & Information Systems (AREA)
  • Human Computer Interaction (AREA)
  • Processing Or Creating Images (AREA)
  • Studio Circuits (AREA)
  • Image Processing (AREA)
  • Controls And Circuits For Display Device (AREA)

Abstract

本公开提供了一种图片处理方法、装置、设备及存储介质，所述方法包括：获取待处理图片，包括来自同一原始图片的目标对像分割图片和背景补全图片；基于目标对像分割图片的图片类型，对目标对像分割图片和背景补全图片分别进行特效处理，得到分别对应的特效图片；将分别对应的特效图片合成为原始图片对应的旋转动画。本公开对来自同一原始图片的目标对象分割图片和背景补全图片分别进行特效处理后，合成为原始图片的旋转动画，通过对旋转动画的展示，能够更立体动态的向用户展示原始图片，满足了用户对图片的效果展示需求。

Description

一种图片处理方法、装置、设备及存储介质
本申请要求于2020年8月19日提交的申请号为202010838589.8、申请名称为“一种图片处理方法、装置、设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本公开涉及数据处理领域，尤其涉及一种图片处理方法、装置、设备及存储介质。
背景技术
随着图片处理技术的不断发展，用户对于图片效果的展示需求越来越多样化。
对于包含有目标对象的图片，例如人像图片，如何将其立体动态的展示给用户，是当前存在的图片效果展示需求之一。
因此，如何满足上述图片效果展示需求，是目前亟需解决的技术问题。
发明内容
为了解决上述技术问题或者至少部分地解决上述技术问题，本公开提供了一种图片处理方法、装置、设备及存储介质，能够立体动态的将图片展示给用户，满足用户对图片的效果展示需求。
第一方面，本公开提供了一种图片处理方法，所述方法包括：
获取待处理图片；所述待处理图片包括来自同一原始图片的目标对像分割图片和背景补全图片；
基于所述目标对像分割图片的图片类型，对所述目标对像分割图片和所述背景补全图片分别进行特效处理，得到所述目标对像分割图片和所述背景补全图片分别对应的特效图片；
将所述目标对像分割图片和所述背景补全图片分别对应的特效图片，合成为所述原始图片对应的特效视频。
一种可选的实施方式中，所述基于所述目标对像分割图片的图片类型，对所述目标对像分割图片和所述背景补全图片进行特效处理，得到所述目标对像分割图片和所述背景补全图片分别对应的特效图片，包括：
如果所述目标对像分割图片的图片类型为全身图片，则将所述目标对像分割图片按照预设第一方向进行平移且放大处理，得到所述目标对像分割图片对应的特效图片；所述预设第一方向为向右或向左；
以及，将所述背景补全图片按照预设第二方向进行透视旋转处理，得到所述背景补全图片分别对应的特效图片；所述预设第二方向为向左或向右，所述预设第一方向和所述预设第二方向不同。
一种可选的实施方式中，所述基于所述目标对像分割图片的图片类型，对所述目标对像分割图片和所述背景补全图片进行特效处理，得到所述目标对像分割图片和所述背景补 全图片分别对应的特效图片，包括：
如果所述目标对像分割图片的图片类型为半身图片，则将所述目标对像分割图片按照正向进行放大处理，得到所述目标对像分割图片对应的特效图片；
以及，将所述背景补全图片按照正面推倒至预设角度的效果进行透视旋转处理，得到所述背景补全图片对应的特效图片。
在一种可选的实施方式中，所述将所述目标对象分割图片和所述背景补全图片分别对应的特效图片，合成为所述原始图片的特效视频，包括：
将所述目标对象分割图片和所述背景补全图片分别对应的特效图片，合成为所述原始图片对应的旋转动画。
一种可选的实施方式中，所述将所述目标对像分割图片和所述背景补全图片分别对应的特效图片，合成为所述原始图片对应的旋转动画，包括：
如果所述目标对像分割图片的图片类型为半身图片，则确定所述目标对像分割图片对应的特效图片中的目标对象与所述背景补全图片对应的特效图片之间的连接点；
基于所述连接点，将所述目标对像分割图片和所述背景补全图片分别对应的特效图片合成为所述原始图片对应的旋转动画。
一种可选的实施方式中，所述目标对像分割图片包括人像分割图片。
一种可选的实施方式中，所述将所述目标对像分割图片和所述背景补全图片分别对应的特效图片，合成为所述原始图片对应的旋转动画之后，还包括：
将多张所述原始图片分别对应的特效视频合成为影集。
一种可选的实施方式中，所述基于所述目标对像分割图片的图片类型，对所述目标对像分割图片和所述背景补全图片分别进行特效处理，得到所述目标对像分割图片和所述背景补全图片分别对应的特效图片之前，还包括：
确定所述目标对象分割图片中的目标对象是否包括半身对象；
如果确定所述目标对象分割图片中的目标对象包括半身对象，则确定所述目标对像分割图片的图片类型为半身图片；否则，确定所述目标对像分割图片的图片类型为全身图片。
第二方面，本公开提供了一种图片处理装置，所述装置包括：
获取模块，用于获取待处理图片；所述待处理图片包括来自同一原始图片的目标对像分割图片和背景补全图片；
特效处理模块，用于基于所述目标对像分割图片的图片类型，对所述目标对像分割图片和所述背景补全图片分别进行特效处理，得到所述目标对像分割图片和所述背景补全图片分别对应的特效图片；
合成模块，用于将所述目标对像分割图片和所述背景补全图片分别对应的特效图片，合成为所述原始图片对应的特效视频。
第三方面，本公开提供了一种计算机可读存储介质，所述计算机可读存储介质中存储有指令，当所述指令在终端设备上运行时，使得所述终端设备实现上述的方法。
第四方面，本公开提供了一种设备，包括：存储器，处理器，及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时，实现上述的 方法。
本公开实施例提供的技术方案与现有技术相比具有如下优点：
本公开实施例提供了一种图片处理方法，首先，确定来自同一原始图片的目标对象分割图片和背景补全图片为待处理图片，其次，基于目标对象分割图片的图片类型，对目标对象分割图片和背景补全图片分别进行特效处理，得到二者分别对应的特效图片。最终，将目标对像分割图片和背景补全图片分别对应的特效图片，合成为该原始图片对应的旋转动画。本公开实施例对来自同一原始图片的目标对象分割图片和背景补全图片分别进行特效处理后，合成为原始图片的旋转动画，本公开实施例通过该旋转动画，能够更立体动态的向用户展示原始图片，满足了用户对图片的效果展示需求。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理。
为了更清楚地说明本公开实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，对于本领域普通技术人员而言，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1为本公开实施例提供的一种图片处理方法的流程图；
图2为本公开实施例提供的一种图片处理装置结构框图；
图3为本公开实施例提供的一种图片处理设备结构框图。
具体实施方式
为了能够更清楚地理解本公开的上述目的、特征和优点，下面将对本公开的方案进行进一步描述。需要说明的是，在不冲突的情况下，本公开的实施例及实施例中的特征可以相互组合。
在下面的描述中阐述了很多具体细节以便于充分理解本公开，但本公开还可以采用其他不同于在此描述的方式来实施；显然，说明书中的实施例只是本公开的一部分实施例，而不是全部的实施例。
为了满足用户对图片的效果展示需求，本公开提供了一种图片处理方法，首先将来自同一原始图片的目标对像分割图片和背景补全图片确定为待处理图片，然后基于目标对象分割图片的图片类型，对目标对象分割图片和背景补全图片分别进行特效处理，得到二者分别对应的特效图片，最终将二者分别对应的特效图片合称为原始图片对应的旋转动画。本公开通过对旋转动画的展示，能够更立体动态的向用户展示原始图片，满足了用户对图片的效果展示需求。
基于此，本公开实施例提供了一种图片处理方法，参考图1，为本公开实施例提供的一种图片处理方法的流程图，该方法包括：
S101：获取待处理图片；所述待处理图片包括来自同一原始图片的目标对像分割图片 和背景补全图片。
本公开实施例中，在确定待处理的原始图片之后，将原始图片中的目标对象与背景分离，得到该原始图片对应的目标图像分割图片和背景补全图片。其中，该目标图像分割图片包括原始图片中的目标对象，该背景补全图片包括原始图片中的背景。目标对象可以包括人像、动物、植物等，通常原始图片上包括至少一个目标对象。
具体的，将目标对象从原始图片中分割出来，得到该原始图片对应的目标图片分割图片。将目标对象从原始图片分割移除之后，由于原始图片不够完整，因此可以将移除目标对象的区域进行补全，得到一张完整的图片，作为该原始图片对应的背景补全图片。其中，补全的方式可以利用现有算法模型理解原始图片上的内容，进而基于理解到的内容进行补全。
本公开实施例在获取到来自同一原始图片的目标对象分割图片和背景补全图片之后，将该目标对象分割图片和背景补全图片确定为待处理图片。
S102：基于所述目标对像分割图片的图片类型，对所述目标对像分割图片和所述背景补全图片分别进行特效处理，得到所述目标对像分割图片和所述背景补全图片分别对应的特效图片。
本公开实施例中，在对图片进行处理之前，首先识别目标对象分割图片的图片类型，后续基于其所属的图片类型对应的特效处理方式，对目标对像分割图片和背景补全图片分别进行特效处理。
其中，图片类型可以包括全身图片和半身图片，针对全身图片和半身图片，基于全身图片和半身图片的特征，本公开实施例提供了不同的处理方式。
针对人像图片或者动物图片等，全身图片与半身图片的其中一个区别特征是，全身图片中通常包含脚部特征，而半身图片中不包含脚部特征。因此，本公开实施例可以通过识别目标对象分割图片上是否包含脚部特征，确定该目标对象分割图片的图片类型。具体的，如果目标对象分割图片上包含脚部特征，则将该目标对象分割图片确定为全身图片，否则将其确定为半身图片。
另外，对于其他能够识别出目标对象分割图片所属图片类型的方法，本公开实施例不作限定。
一种可选的实施方式中，目标对象分割图片中可能包括多个目标对象，例如多人图片，假设识别出多人图片中不仅包含全身人像，同时还包含半身人像，则为了保证原始图片的展示效果，则可以将该多人图片确定为半身图片的图片类型，后续按照半身图片的特效处理方式进行处理即可。
具体的，首先，确定所述目标对象分割图片中的目标对象是否包括半身对象；如果确定所述目标对象分割图片中的目标对象包括半身对象，则确定所述目标对像分割图片的图片类型为半身图片；否则，确定所述目标对像分割图片的图片类型为全身图片。
另外，对于目标对象为动物、植物等的情况，可以通过大数据学习的方式学习动物、植物的特征，然后基于学习到的特征确定目标对象分割图片的图片类型，对此本公开实施例不再过多介绍。
本公开实施例在确定目标对象分割图片的图片类型之后，基于该目标对象分割图片的图片类型，确定对目标对像分割图片和背景补全图片的特效处理方式，经过对应的特效处理方式分别对目标对像分割图片和背景补全图片进行特效处理后，得到二者分别对应的特效图片。
一种可选的实施方式中，如果确定目标对像分割图片属于全身图片，则将目标对像分割图片按照预设第一方向进行平移且放大处理，得到目标对像分割图片对应的特效图片；其中，预设第一方向为向右或向左。以及，将背景补全图片按照预设第二方向进行透视旋转处理，得到背景补全图片分别对应的特效图片；其中，预设第二方向为向左或向右，预设第一方向和预设第二方向不同。
也就是说，可以将目标对像分割图片按照向右的效果进行平移且放大处理，同时，将背景补全图片按照向左的效果进行透视旋转处理。或者，可以将目标对像分割图片按照向左的效果进行平移且放大处理，同时，将背景补全图片按照向右的效果进行透视旋转处理。
另一种可选的实施方式中，如果目标对像分割图片属于半身图片，则将目标对像分割图片按照正向进行放大处理，得到目标对像分割图片对应的特效图片，以及，将背景补全图片按照正面推倒至预设角度的效果进行透视旋转处理，得到背景补全图片对应的特效图片。其中，预设角度可以包括45度至90度中的任一角度。
由于在上述特效处理方式中，对背景补全图片和目标对象分割图片均进行了立体动态的处理，因此，本公开能够满足用户对图片立体动态展示的需求。另外，本公开实施例对目标图像分割图片还进行了放大处理，突出展示了原始图片中的目标对象，一定程度上能够提高用户的使用体验。
S103：将所述目标对像分割图片和所述背景补全图片分别对应的特效图片，合成为所述原始图片对应的特效视频。
本公开实施例在对目标对象分割图片和背景补全图片分别进行特效处理之后，得到二者分别对应的特效图片，然后将其合成为原始图片对应的特效视频。通过原始图片对应的特效视频，能够立体动态的展示原始图片中的目标对象，提升用户的体验。
一种可选的实施方式中，可以将目标对像分割图片和背景补全图片分别对应的特效图片，合成为原始图片对应的旋转动画。
一种可选的实施方式中，为了保证图片处理的效果，在对属于半身图片的目标图像分割图片和对应的背景补全图片的特效图片进行合成之后，首先确定目标对像分割图片对应的特效图片中的目标对象与背景补全图片对应的特效图片之间的连接点，然后基于该连接点，将目标对像分割图片和背景补全图片分别对应的特效图片合成为原始图片对应的旋转动画，使得合成后的旋转动画中的目标对象与背景补全图片之间存在连接点，保证图片展示的效果。
本公开实施例提供的图片处理方法中，首先将来自同一原始图片的目标对像分割图片和背景补全图片确定为待处理图片，然后识别目标对象分割图片的图片类型，并基于目标对象分割图片的图片类型，对目标对象分割图片和背景补全图片分别进行特效处理，得到二者分别对应的特效图片，最终将二者分别对应的特效图片合称为原始图片对应的旋转动 画。本公开通过对旋转动画的展示，能够更立体动态的向用户展示原始图片，满足了用户对图片的效果展示需求。
一种应用场景中，原始图片可以包括多张人像图片，本公开实施例提供的图片处理方法可以针对每一张人像图片，得到对应的特效视频，然后将多张人像图片分别对应的特效视频合成为影集。
实际应用中，通过对合成的影集的播放，能够实现同时对多张图片的立体动态效果进行展示，满足了用户将图片转换成视频进行立体动态展示的效果需求，提高了用户的体验。
与上述方法实施例相对应的，本公开还提供了一种图片处理装置，参考图2，为本公开实施例提供的一种图片处理装置的结构示意图，所述装置包括：
获取模块201，用于获取待处理图片；所述待处理图片包括来自同一原始图片的目标对像分割图片和背景补全图片；
特效处理模块202，用于基于所述目标对像分割图片的图片类型，对所述目标对像分割图片和所述背景补全图片分别进行特效处理，得到所述目标对像分割图片和所述背景补全图片分别对应的特效图片；
合成模块203，用于将所述目标对像分割图片和所述背景补全图片分别对应的特效图片，合成为所述原始图片对应的特效视频。
一种可选的实施方式中，所述特效处理模块202，包括：
第一处理子模块，用于在所述目标对像分割图片的图片类型为全身图片时，将所述目标对像分割图片按照预设第一方向进行平移且放大处理，得到所述目标对像分割图片对应的特效图片；所述预设第一方向为向右或向左；
第一处理子模块，用于将所述背景补全图片按照预设第二方向进行透视旋转处理，得到所述背景补全图片分别对应的特效图片；所述预设第二方向为向左或向右，所述预设第一方向和所述预设第二方向不同。
一种可选的实施方式中，所述特效处理模块202，包括：
第三处理子模块，用于在所述目标对像分割图片的图片类型为半身图片时，将所述目标对像分割图片按照正向进行放大处理，得到所述目标对像分割图片对应的特效图片；
第四处理子模块，用于将所述背景补全图片按照正面推倒至预设角度的效果进行透视旋转处理，得到所述背景补全图片对应的特效图片。
一种可选的实施方式中，所述合成模块203，具体用于将所述目标对象分割图片和所述背景补全图片分别对应的特效图片，合成为所述原始图片对应的旋转动画。
一种可选的实施方式中，所述合成模块203，包括：
第一确定子模块，用于在所述目标对像分割图片的图片类型为半身图片时，确定所述目标对像分割图片对应的特效图片中的目标对象与所述背景补全图片对应的特效图片之间的连接点；
合成子模块，用于基于所述连接点，将所述目标对像分割图片和所述背景补全图片分 别对应的特效图片合成为所述原始图片对应的旋转动画。
一种可选的实施方式中，所述目标对像分割图片包括人像分割图片。
一种可选的实施方式中，所述装置还包括：
视频合成模块，用于将多张所述原始图片分别对应的特效视频合成为影集。
一种可选的实施方式中，所述装置还包括：
第一确定模块，用于确定所述目标对象分割图片中的目标对象是否包括半身对象；
第二确定模块，用于在所述第一确定模块的确定结果为是时，确定所述目标对像分割图片的图片类型为半身图片；
第三确定模块，用于在所述第一确定模块的确定结果为否时，确定所述目标对像分割图片的图片类型为全身图片。
本公开实施例提供的图片处理装置，首先将来自同一原始图片的目标对像分割图片和背景补全图片确定为待处理图片，然后基于目标对象分割图片的图片类型，对目标对象分割图片和背景补全图片分别进行特效处理，得到二者分别对应的特效图片，最终将二者分别对应的特效图片合称为原始图片对应的旋转动画。本公开通过对旋转动画的展示，能够更立体动态的向用户展示原始图片，满足了用户对图片的效果展示需求。
另外，本公开实施例还提供了一种图片处理设备，参见图3所示，可以包括：
处理器301、存储器302、输入装置303和输出装置304。图片处理设备中的处理器301的数量可以一个或多个，图3中以一个处理器为例。在本发明的一些实施例中，处理器301、存储器302、输入装置303和输出装置304可通过总线或其它方式连接，其中，图3中以通过总线连接为例。
存储器302可用于存储软件程序以及模块，处理器301通过运行存储在存储器302的软件程序以及模块，从而执行图片处理设备的各种功能应用以及数据处理。存储器302可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序等。此外，存储器302可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。输入装置303可用于接收输入的数字或字符信息，以及产生与图片处理设备的用户设置以及功能控制有关的信号输入。
具体在本实施例中，处理器301会按照如下的指令，将一个或一个以上的应用程序的进程对应的可执行文件加载到存储器302中，并由处理器301来运行存储在存储器302中的应用程序，从而实现上述图片处理设备的各种功能。
需要说明的是，在本文中，诸如“第一”和“第二”等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要 素，并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。
以上所述仅是本公开的具体实施方式，使本领域技术人员能够理解或实现本公开。对这些实施例的多种修改对本领域的技术人员来说将是显而易见的，本文中所定义的一般原理可以在不脱离本公开的精神或范围的情况下，在其它实施例中实现。因此，本公开将不会被限制于本文所述的这些实施例，而是要符合与本文所公开的原理和新颖特点相一致的最宽的范围。

Claims (11)

  1. 一种图片处理方法，其特征在于，所述方法包括：
    获取待处理图片；所述待处理图片包括来自同一原始图片的目标对像分割图片和背景补全图片；
    基于所述目标对像分割图片的图片类型，对所述目标对像分割图片和所述背景补全图片分别进行特效处理，得到所述目标对像分割图片和所述背景补全图片分别对应的特效图片；
    将所述目标对像分割图片和所述背景补全图片分别对应的特效图片，合成为所述原始图片对应的特效视频。
  2. 根据权利要求1所述的方法，其特征在于，所述基于所述目标对像分割图片的图片类型，对所述目标对像分割图片和所述背景补全图片进行特效处理，得到所述目标对像分割图片和所述背景补全图片分别对应的特效图片，包括：
    如果所述目标对像分割图片的图片类型为全身图片，则将所述目标对像分割图片按照预设第一方向进行平移且放大处理，得到所述目标对像分割图片对应的特效图片；所述预设第一方向为向右或向左；
    以及，将所述背景补全图片按照预设第二方向进行透视旋转处理，得到所述背景补全图片分别对应的特效图片；所述预设第二方向为向左或向右，所述预设第一方向和所述预设第二方向不同。
  3. 根据权利要求1或2所述的方法，其特征在于，所述基于所述目标对像分割图片的图片类型，对所述目标对像分割图片和所述背景补全图片进行特效处理，得到所述目标对像分割图片和所述背景补全图片分别对应的特效图片，包括：
    如果所述目标对像分割图片的图片类型为半身图片，则将所述目标对像分割图片按照正向进行放大处理，得到所述目标对像分割图片对应的特效图片；
    以及，将所述背景补全图片按照正面推倒至预设角度的效果进行透视旋转处理，得到所述背景补全图片对应的特效图片。
  4. 根据权利要求2或3所述的方法，其特征在于，所述将所述目标对象分割图片和所述背景补全图片分别对应的特效图片，合成为所述原始图片的特效视频，包括：
    将所述目标对象分割图片和所述背景补全图片分别对应的特效图片，合成为所述原始图片对应的旋转动画。
  5. 根据权利要求4所述的方法，其特征在于，所述将所述目标对像分割图片和所述背景补全图片分别对应的特效图片，合成为所述原始图片对应的旋转动画，包括：
    如果所述目标对像分割图片的图片类型为半身图片，则确定所述目标对像分割图片对应的特效图片中的目标对象与所述背景补全图片对应的特效图片之间的连接点；
    基于所述连接点，将所述目标对像分割图片和所述背景补全图片分别对应的特效图片合成为所述原始图片对应的旋转动画。
  6. 根据权利要求1所述的方法，其特征在于，所述目标对像分割图片包括人像分割图片。
  7. 根据权利要求1所述的方法，其特征在于，所述将所述目标对像分割图片和所述背景补全图片分别对应的特效图片，合成为所述原始图片对应的特效视频之后，还包括：
    将多张所述原始图片分别对应的特效视频合成为影集。
  8. 根据权利要求1所述的方法，其特征在于，所述基于所述目标对像分割图片的图片类型，对所述目标对像分割图片和所述背景补全图片分别进行特效处理，得到所述目标对像分割图片和所述背景补全图片分别对应的特效图片之前，还包括：
    确定所述目标对象分割图片中的目标对象是否包括半身对象；
    如果确定所述目标对象分割图片中的目标对象包括半身对象，则确定所述目标对像分割图片的图片类型为半身图片；否则，确定所述目标对像分割图片的图片类型为全身图片。
  9. 一种图片处理装置，其特征在于，所述装置包括：
    获取模块，用于获取待处理图片；所述待处理图片包括来自同一原始图片的目标对像分割图片和背景补全图片；
    特效处理模块，用于基于所述目标对像分割图片的图片类型，对所述目标对像分割图片和所述背景补全图片分别进行特效处理，得到所述目标对像分割图片和所述背景补全图片分别对应的特效图片；
    合成模块，用于将所述目标对像分割图片和所述背景补全图片分别对应的特效图片，合成为所述原始图片对应的特效视频。
  10. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质中存储有指令，当所述指令在终端设备上运行时，使得所述终端设备实现如权利要求1-7任一项所述的方法。
  11. 一种设备，其特征在于，包括：存储器，处理器，及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时，实现如权利要求1-7任一项所述的方法。
PCT/CN2021/113463 2020-08-19 2021-08-19 一种图片处理方法、装置、设备及存储介质 WO2022037634A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
EP21857726.0A EP4170580A4 (en) 2020-08-19 2021-08-19 IMAGE PROCESSING METHOD AND APPARATUS, DEVICE, AND STORAGE MEDIUM
JP2023504566A JP2023534750A (ja) 2020-08-19 2021-08-19 ピクチャ処理方法、装置、デバイス及び記憶媒体
US18/090,181 US20230162419A1 (en) 2020-08-19 2022-12-28 Picture processing method and apparatus, device, and storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010838589.8A CN112037121A (zh) 2020-08-19 2020-08-19 一种图片处理方法、装置、设备及存储介质
CN202010838589.8 2020-08-19

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/090,181 Continuation US20230162419A1 (en) 2020-08-19 2022-12-28 Picture processing method and apparatus, device, and storage medium

Publications (1)

Publication Number Publication Date
WO2022037634A1 true WO2022037634A1 (zh) 2022-02-24

Family

ID=73576990

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/113463 WO2022037634A1 (zh) 2020-08-19 2021-08-19 一种图片处理方法、装置、设备及存储介质

Country Status (5)

Country Link
US (1) US20230162419A1 (zh)
EP (1) EP4170580A4 (zh)
JP (1) JP2023534750A (zh)
CN (1) CN112037121A (zh)
WO (1) WO2022037634A1 (zh)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112037121A (zh) * 2020-08-19 2020-12-04 北京字节跳动网络技术有限公司 一种图片处理方法、装置、设备及存储介质
CN113225489B (zh) * 2021-04-30 2022-08-26 北京达佳互联信息技术有限公司 图像特效展示方法、装置、电子设备和存储介质
CN113744135A (zh) * 2021-09-16 2021-12-03 北京字跳网络技术有限公司 图像处理方法、装置、电子设备及存储介质
US11954828B2 (en) 2021-10-14 2024-04-09 Lemon Inc. Portrait stylization framework using a two-path image stylization and blending

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080129738A1 (en) * 2006-12-02 2008-06-05 Electronics And Telecommunications Research Institute Method and apparatus for rendering efficient real-time wrinkled skin in character animation
CN107633228A (zh) * 2017-09-20 2018-01-26 北京奇虎科技有限公司 视频数据处理方法及装置、计算设备
CN109840881A (zh) * 2018-12-12 2019-06-04 深圳奥比中光科技有限公司 一种3d特效图像生成方法、装置及设备
CN110288614A (zh) * 2019-06-24 2019-09-27 睿魔智能科技(杭州)有限公司 图像处理方法、装置、设备及存储介质
CN112037121A (zh) * 2020-08-19 2020-12-04 北京字节跳动网络技术有限公司 一种图片处理方法、装置、设备及存储介质

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016017987A1 (en) * 2014-07-31 2016-02-04 Samsung Electronics Co., Ltd. Method and device for providing image
US9898847B2 (en) * 2015-11-30 2018-02-20 Shanghai Sunson Activated Carbon Technology Co., Ltd. Multimedia picture generating method, device and electronic device
US10679428B1 (en) * 2017-05-26 2020-06-09 Snap Inc. Neural network-based image stream modification
CN109996107A (zh) * 2017-12-29 2019-07-09 百度在线网络技术（北京）有限公司 视频生成方法、装置和系统
CN108965743A (zh) * 2018-08-21 2018-12-07 百度在线网络技术（北京）有限公司 基于前后景分割的视频合成方法、装置及可读存储介质
CN110012352B (zh) * 2019-04-17 2020-07-24 广州华多网络科技有限公司 图像特效处理方法、装置及视频直播终端

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080129738A1 (en) * 2006-12-02 2008-06-05 Electronics And Telecommunications Research Institute Method and apparatus for rendering efficient real-time wrinkled skin in character animation
CN107633228A (zh) * 2017-09-20 2018-01-26 北京奇虎科技有限公司 视频数据处理方法及装置、计算设备
CN109840881A (zh) * 2018-12-12 2019-06-04 深圳奥比中光科技有限公司 一种3d特效图像生成方法、装置及设备
CN110288614A (zh) * 2019-06-24 2019-09-27 睿魔智能科技(杭州)有限公司 图像处理方法、装置、设备及存储介质
CN112037121A (zh) * 2020-08-19 2020-12-04 北京字节跳动网络技术有限公司 一种图片处理方法、装置、设备及存储介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4170580A4

Also Published As

Publication number Publication date
CN112037121A (zh) 2020-12-04
US20230162419A1 (en) 2023-05-25
JP2023534750A (ja) 2023-08-10
EP4170580A1 (en) 2023-04-26
EP4170580A4 (en) 2023-12-06

Similar Documents

Publication Publication Date Title
WO2022037634A1 (zh) 一种图片处理方法、装置、设备及存储介质
US11488355B2 (en) Virtual world generation engine
CN111460183B (zh) 多媒体文件生成方法和装置、存储介质、电子设备
CN1749958B (zh) 使用形状的公用图表
WO2019242271A1 (zh) 图像变形方法、装置及电子设备
CN111752557A (zh) 一种展示方法及装置
US9467495B2 (en) Transferring assets via a server-based clipboard
CN111930376A (zh) 风格化图标的自动生成
CN112149545B (zh) 样本生成方法、装置、电子设备及存储介质
JP2023549810A (ja) 動物顔スタイル画像の生成方法、モデルのトレーニング方法、装置及び機器
JP2016085534A (ja) 画像処理装置、画像処理装置の制御方法およびプログラム
WO2022170982A1 (zh) 图像处理方法、图像生成方法、装置、设备和介质
US9143754B2 (en) Systems and methods for modifying stereoscopic images
WO2018210113A1 (zh) 动态信息展示的方法、计算机设备和存储介质
US11967344B2 (en) Video processing method and apparatus, device and computer readable storage medium
JP2017084304A (ja) 画像表示装置、画像表示方法
WO2022160914A1 (zh) 一种效果处理方法、装置、设备及存储介质
CN114913277A (zh) 一种物体立体交互展示方法、装置、设备及介质
CN111460770B (zh) 文档内元素属性同步方法、装置、设备及存储介质
CN114495190A (zh) 换脸网络模型的训练方法、图像换脸方法及相关设备
CN110428453B (zh) 数据处理方法、装置、数据处理设备及存储介质
CN113947671A (zh) 全景360度图像分割合成方法、系统及介质
CN113379768A (zh) 一种图像处理方法、装置、存储介质和计算机设备
WO2021114824A1 (zh) 演示文稿生成方法、装置、设备及介质
WO2024087903A1 (zh) 一种视频超分方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21857726

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2023504566

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2021857726

Country of ref document: EP

Effective date: 20230117

NENP Non-entry into the national phase

Ref country code: DE