WO2022037111A1 - 图像处理方法及装置、互动式展示装置和电子设备 - Google Patents

图像处理方法及装置、互动式展示装置和电子设备 Download PDF

Info

Publication number
WO2022037111A1
WO2022037111A1 PCT/CN2021/090249 CN2021090249W WO2022037111A1 WO 2022037111 A1 WO2022037111 A1 WO 2022037111A1 CN 2021090249 W CN2021090249 W CN 2021090249W WO 2022037111 A1 WO2022037111 A1 WO 2022037111A1
Authority
WO
WIPO (PCT)
Prior art keywords
stylized
template
image
target object
processed
Prior art date
Application number
PCT/CN2021/090249
Other languages
English (en)
French (fr)
Inventor
田济源
Original Assignee
深圳市慧鲤科技有限公司
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 深圳市慧鲤科技有限公司 filed Critical 深圳市慧鲤科技有限公司
Publication of WO2022037111A1 publication Critical patent/WO2022037111A1/zh

Links

Images

Classifications

    • G06T3/04—
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
    • 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
    • G06T2207/20081—Training; Learning
    • 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
    • G06T2207/20084—Artificial neural networks [ANN]
    • 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

Definitions

  • the present disclosure relates to the field of computer technology, and in particular, to an image processing method and device, an interactive display device, and an electronic device.
  • multimedia data can be beautified, special effects, and filters can be added.
  • multimedia data processing methods There is a growing demand for the richness and quality of multimedia data processing methods.
  • the present disclosure proposes an image processing technical solution for processing and fusing images.
  • an image processing method comprising:
  • the stylized target object and the stylized template are fused to obtain a stylized image.
  • the determining a stylized template for stylizing the to-be-processed image includes:
  • target object recognition on the to-be-processed image to obtain a target-object recognition result of the to-be-processed image, where the target object recognition result includes a target object attribute;
  • a stylization template for stylizing the image to be processed is determined.
  • the determining a stylized template for stylizing the to-be-processed image includes:
  • the selected reference stylization template is determined as the stylization template for stylizing the image to be processed.
  • the fusion of the stylized target object and the stylized template to obtain a stylized image includes:
  • adjusting the target object according to a preset adjustment rule includes:
  • the size of the stylization target object is adjusted according to the size of the template object.
  • the fusion of the stylized target object and the stylized template to obtain a stylized image includes:
  • the stylized target object is fused at the position in the stylized template to obtain the stylized image.
  • the method further includes:
  • the template image is sent to the server, so that the server performs image processing on the template image to obtain a reference stylized template.
  • the stylized target object is fused with the stylized template to obtain a stylized image, including:
  • a stylized image is obtained in response to an adjustment operation for the stylization target object in the preliminary stylized image, the adjustment operation including a size adjustment operation and/or a position adjustment operation for the stylization target object.
  • an interactive display device includes: an image processing module and a display module, the image processing module includes an image acquisition unit and an image processing unit; wherein,
  • the image acquisition unit used to acquire images to be processed
  • the image processing unit is configured to determine a stylization template for stylizing the image to be processed, and perform stylization processing on the target object in the to-be-processed image according to the stylization template to obtain a style A stylized target object, the style of the stylized target object is the same as that of the stylized template;
  • the image processing unit is further configured to fuse the stylized target object and the stylized template to obtain a stylized image
  • the display module is used to display the stylized image.
  • an image processing apparatus including:
  • a first acquisition module used for acquiring the image to be processed
  • a determining module for determining a stylized template for stylizing the to-be-processed image
  • a processing module configured to stylize the target object in the to-be-processed image according to the stylized template to obtain a stylized target object, where the stylized target object has the same style as the stylized template;
  • the fusion module is used to fuse the stylized target object with the stylized template to obtain a stylized image.
  • the determining module is further configured to:
  • target object recognition on the to-be-processed image to obtain a target-object recognition result of the to-be-processed image, where the target object recognition result includes a target object attribute;
  • a stylization template for stylizing the image to be processed is determined.
  • the determining module is further configured to:
  • the selected reference stylization template is determined as the stylization template for stylizing the image to be processed.
  • the fusion module is further used for:
  • the fusion module is further used for:
  • the size of the stylization target object is adjusted according to the size of the template object.
  • the fusion module is further used for:
  • the stylized target object is fused at the position in the stylized template to obtain the stylized image.
  • the apparatus further includes:
  • the second acquiring module is configured to send the template image to the server, so that the server performs image processing on the template image to obtain a reference stylized template.
  • the fusion module is further used for:
  • a stylized image is obtained in response to an adjustment operation for the stylization target object in the preliminary stylized image, the adjustment operation including a size adjustment operation and/or a position adjustment operation for the stylization target object.
  • an electronic device comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to invoke the instructions stored in the memory to execute the above method.
  • a computer-readable storage medium having computer program instructions stored thereon, the computer program instructions implementing the above method when executed by a processor.
  • a computer program product comprising computer readable code which, when the computer readable code is executed in an electronic device, is executed by a processor in the electronic device for implementing the above method.
  • an image to be processed may be acquired, and after a stylized template for stylizing the image to be processed is determined, the target object in the image to be processed may be stylized according to the stylized template.
  • Stylization processing is performed to obtain a stylized target object, where the style of the stylized target object is the same as that of the stylized template.
  • the stylized target object and the stylized template may be fused to obtain a stylized image.
  • the image processing method and device, the interactive display device, and the electronic device provided according to the embodiments of the present disclosure not only enrich the image processing method, but also alleviate the problem of blunt fusion caused by the unnatural segmentation edge effect of the target object.
  • FIG. 1 shows a flowchart of an image processing method according to an embodiment of the present disclosure
  • FIGS. 2a-2c show schematic diagrams of an image processing method according to an embodiment of the present disclosure
  • FIG. 3 shows a schematic diagram of an image processing method according to an embodiment of the present disclosure
  • FIG. 4 shows a block diagram of an image processing apparatus according to an embodiment of the present disclosure
  • FIG. 5 shows a block diagram of an electronic device 800 according to an embodiment of the present disclosure
  • FIG. 6 shows a block diagram of an electronic device 1900 according to an embodiment of the present disclosure.
  • the image processing method may be executed by an electronic device such as a terminal device or a server.
  • the terminal device may be a user equipment (User Equipment, UE), a mobile device, a user Terminal, terminal, cellular phone, cordless phone, Personal Digital Assistant (PDA), handheld device, computing device, in-vehicle device, wearable device, etc.
  • the method can call the computer-readable memory stored in the memory through the processor instructions are implemented.
  • the method may be performed by a server.
  • the image processing method may include:
  • step S11 an image to be processed is acquired.
  • the image to be processed can be collected by an image collection device (such as a mobile phone, a camera, a camera device, etc. with an image collection function), or, or the image to be processed can be obtained by uploading, downloading, etc. through a terminal, and the present disclosure implements the
  • the method of acquiring the image to be processed is not specifically limited.
  • step S12 a stylization template for stylizing the to-be-processed image is determined.
  • the stylized template may be an image of a work of art.
  • the stylized template may be an image corresponding to a work of art such as oil painting, sketch, ink painting, sculpture, or sculpture. Accordingly, these stylized templates may be presented respectively. Oil painting style, sketch style, ink painting style, sculpture or engraving style, etc.
  • the stylized template can be an image of other styles, for example: the stylized template can be a comic style image, or the stylized template can be a movie style image images, etc.
  • a stylization template for stylizing the image to be processed may be determined in response to a user's selection operation for the stylization template; or, a stylization template for stylizing the image to be processed may be determined according to the image to be processed Stylized template.
  • the terminal device may acquire and store at least one stylized template from the server, and after acquiring the to-be-processed image, determine from the stored at least one stylized template for A stylized template for stylizing the image to be processed.
  • the terminal device may determine a stylized template for stylizing the to-be-processed image according to the to-be-processed image; or, the terminal device may display at least one stylized template on the display interface, the user can make a selection, and the terminal device responds to the According to the selection operation of the stylized template, the user determines that the selected stylized template is the stylized template for stylizing the image to be processed.
  • the server may receive a stylized processing instruction from the terminal device, the stylized processing instruction may include the image to be processed, and the server may store the image locally according to the stylized processing instruction.
  • the stylization template for stylizing the image to be processed is determined in the stylization template.
  • the server may determine a stylized template for stylizing the image to be processed according to the image to be processed; or, the stylization processing instruction further includes the template image identification information of the stylized template selected by the user, and the server may determine the template
  • the stylized template identified by the image identification information is a stylized template used for stylizing the image to be processed.
  • step S13 stylizing processing is performed on the target object in the to-be-processed image according to the stylizing template to obtain a stylizing target object, and the stylizing target object has the same style as the stylizing template.
  • the image to be processed can be stylized through the stylization processing network corresponding to the pre-trained stylization template.
  • the stylization processing network is a neural network that can correspond to one or more stylized templates with the same style.
  • the image data processed by the stylization processing network has the same style as the stylized template, or the stylization processing network also has the same style. It may correspond to different stylized templates, which is not limited in this embodiment of the present disclosure.
  • Style can refer to the representative appearance of the image as a whole. Different images can present different styles. Exemplarily, the styles of the images can be reflected by the extracted features in the images, and whether the styles are the same or different can be judged by the similarity of these features between the images.
  • the training process of the stylized processing network may be performed on the server side, that is, the stylized processing network corresponding to each stylized template may be trained on the server side according to each stylized template.
  • the stylization processing network corresponding to the stylization template can be determined, and the target object in the image to be processed can be styled through the stylization processing network.
  • the style of the stylized target object is the same as that of the stylized template image. For example, if the stylized template is an image corresponding to an oil painting work, the stylized target object is an oil painting texture style.
  • the stylized template can be used to stylize the image to be processed to obtain the stylized image to be processed, and the stylized image to be processed can be identified and segmented to obtain the stylized target object.
  • target object recognition and segmentation can also be performed on the image to be processed to obtain the target object in the to-be-processed image, and the stylized target object is obtained by stylizing the target object through a stylized template.
  • target object recognition and segmentation process can be processed by using a pre-trained neural network for recognition and segmentation, and the embodiment of the present disclosure does not limit the neural network for target object recognition and segmentation.
  • step S14 the stylized target object and the stylized template are fused to obtain a stylized image.
  • the stylized target object can be fused into a stylized template to obtain a stylized image.
  • the stylized target object can be adjusted according to the preset size, and then added to the preset position of the stylized template, or it can be determined according to the position of the target object corresponding to the stylized target object in the image to be processed. The position of the stylized target object in the stylized template, at which the stylized target object is added.
  • the image to be processed is image data collected for user A
  • the stylized template is an oil painting
  • the human body image of user A in the image data is processed as this oil painting.
  • Oil painting texture style and the finally obtained stylized image data is the human body image in the oil painting including user A's oil painting texture style.
  • the embodiments of the present disclosure may also perform stylization processing on video data.
  • processing video data at least one video frame of the video data may be stylized by using the above image processing method to obtain at least one video frame corresponding to The stylized video frames corresponding to all video frames constitute stylized video data corresponding to the video data.
  • the image to be processed can be acquired, and after a stylized template for stylizing the image to be processed is determined, the target object in the image to be processed can be stylized according to the stylized template to obtain Stylizing the target object, the stylizing target object is the same style as the stylizing template.
  • the stylized target object can be fused with the stylized template to obtain a stylized image.
  • the determining a stylized template for stylizing the to-be-processed image may include:
  • target object recognition on the to-be-processed image to obtain a target-object recognition result of the to-be-processed image, where the target object recognition result includes a target object attribute;
  • a stylization template for stylizing the image to be processed is determined.
  • target object recognition may be performed on the image to be processed (eg, target object recognition may be performed on the image to be processed through a recognition network for identifying target objects) to obtain the target object recognition result of the image to be processed.
  • the target object recognition result may include target object attributes, and the target object attributes may include at least one attribute feature of the target object.
  • a stylized template matching the attributes of the target object can be determined, which is a stylized template for stylizing the image to be processed.
  • the stylization template may have at least one attribute tag information, and if the stylization template has attribute tag information that matches the attributes of the target object, it may be determined that the stylization template is used for stylizing the image to be processed. Stylized template for processing.
  • the target object attribute includes the age and/or gender of the target object, the size of the target object in the to-be-processed image, the facial expression of the target object, the target object At least one of the physical posture of the object and the color tone of the target object.
  • a stylized template whose attribute label matches the age and/or gender of the target object may be determined, which is the style used for stylizing the image to be processed.
  • template For example: when the age of the target object is 0-6 years old, you can find attribute tags including: infants or stylized templates of 0-6 years old, the stylized template can include infants or animals, etc., and the style is warm and cute The corresponding image of the artwork.
  • a stylized template whose attribute label matches the size of the target object in the to-be-processed image can be determined, and is used for stylizing the to-be-processed image.
  • Stylized template For example: when the size of the target object in the image to be processed is a*b, you can search for attribute tags including: a stylized model with a size of c*d, where c can be in (ax) ⁇ (a+x) Any value of , d can be any value in b(by) ⁇ (b+y) (wherein, x and y can be the same or different).
  • the stylized model can be an image corresponding to a work of art containing a person whose size is similar to the target object size a*b, or an art with a more harmonious visual effect presented by adding a target object of size a*b at a preset position The corresponding image of the work.
  • a stylized template whose attribute label matches the facial expression of the target object can be determined as a stylized model for stylizing the image to be processed. For example: when the facial expression of the target object is happy and laughing, you can find a stylized model version whose attribute tag matches happy, and the stylized template is an image corresponding to a light and bright art work, or a stylized template To include images of happy laughing people, etc.
  • a stylized template whose attribute label matches the body posture of the target object may be determined as a stylized template for stylizing the image to be processed. For example: when the body and posture of the target object is sitting, you can find a stylized template whose attribute tag matches the sitting (for example, the attribute tag includes sitting, items related to sitting (chair, sofa, etc.), etc.), the stylized template Include images of people in sitting postures, or stylize templates to include images of household items related to sitting postures.
  • a stylized template whose attribute label matches the color tone of the target object may be determined as a stylized template for stylizing the image to be processed. For example, when the color tone of the target object is gray and dark, you can find a stylized template whose attribute tag matches the gray and dark color, and the color of the stylized template is relatively dark.
  • the corresponding stylized template can be adaptively matched according to the attributes of the target object, which can improve the processing efficiency and interest of the image to be processed.
  • the stylized template used to stylize the image to be processed can be determined from the selection operation of the user; when there is no matching according to the attributes of the target object
  • the stylized template for stylizing the image to be processed can be determined from all the stylized templates in response to the user's selection operation, or the usage rate can be calculated according to the historical used data of all the stylized templates. Higher stylized templates are recommended to users.
  • the above-mentioned determining of a stylized template for stylizing the image to be processed may include:
  • the similarity (including content similarity, color similarity, etc.) between the image to be processed and at least one reference stylized template can be determined, and the similarity between the image to be processed and the at least one reference stylized template can be determined
  • the matching stylized template For example, it can be determined that the reference stylized template with the highest similarity is the stylized template used for stylizing the image to be processed.
  • the reference stylized templates may also be sorted in descending order of similarity according to the similarity between the image to be processed and at least one reference stylized template, and the reference stylized templates are displayed on the terminal device side according to the ranking for user selection.
  • the reference stylization template selected by the user is the stylization template used for stylizing the to-be-processed image.
  • content analysis can be performed according to the image to be processed to obtain the content of the image to be processed, the associated content of the content of the image to be processed is determined, and according to the content and associated content of the image to be processed, it is determined that the content of the image to be processed or the associated content matches the content of the image to be processed or the associated content stylized template.
  • the content of the image to be processed is that the target object is sitting, and the associated content is sitting-related items (chairs, sofas, etc.), etc.
  • the stylized template containing sitting or containing sitting-related items can be matched.
  • the multiple stylized templates may be displayed on the terminal device side for the user to select, and the stylized template selected by the user is the finalized template for stylizing the image to be processed. Stylized template.
  • the corresponding stylized template can be adaptively matched according to the attributes of the target object, which can improve the processing efficiency and interest of the image to be processed.
  • At least one reference stylized template may be displayed in the display area of the display interface of the terminal device.
  • the user can select a stylization template for stylizing the image to be processed by manually selecting a reference stylization template according to preference.
  • the user can select the reference stylized template through a selection operation such as touch or click.
  • the terminal device may determine the selected reference stylization template as the stylization template for stylizing the image to be processed in response to the user's selection operation on the reference stylization template.
  • the above-mentioned fusion of the stylized target object and the stylized template to obtain a stylized image may include:
  • the size adjustment condition may be a restriction condition for adjusting the size of the stylization target object
  • the preset adjustment rule may be a rule corresponding to the size adjustment condition for size adjustment of the stylization target object.
  • a first size threshold and a second size threshold are preset, and the first size threshold is greater than the second size threshold.
  • the size of the stylization target object may be adjusted to any value between the first size threshold and the second size threshold.
  • the size of the stylized target object may be adjusted according to the size of the character or item in the stylized template to make it match the size of the character or item in the stylized template. The dimensions of the items are matched, and the adjusted stylized target image is fused with the stylized template to obtain a stylized image.
  • adjusting the target object according to a preset adjustment rule may include:
  • the size of the stylization target object is adjusted according to the size of the template object.
  • the size of a template object in the stylized template which may be a character, animal, or item in the stylized template
  • the matching relationship between the template object and the stylization target object can be preset, for example: when the template object is a character, when the difference between the size of the character and the stylization target object is smaller than the first difference threshold, the stylization target can be determined.
  • the object matches the size of the template object, otherwise, it is determined that the stylization target object does not match the size of the template object.
  • the first difference threshold may be a value determined according to the age attribute of the character. For example, when the template object and the stylized object have the same age attribute (both children, or both adults, etc.), the determined first difference threshold The threshold is smaller; when the template object and the stylized object have different age attributes, the determined first difference threshold is larger.
  • the template object is an animal
  • the difference between the size of the animal and the stylized target object is smaller than the second difference threshold
  • the size of the target object does not match the size of the template object.
  • the second difference threshold may be a value determined according to the size of the animal. For example, when the size of the animal is small, the second difference threshold is set to be larger, and when the size of the animal is larger, the second difference threshold is set to be smaller.
  • the template object is an item
  • the size difference between the size of the item and the stylized target object is smaller than the third difference threshold
  • the size of the target object does not match the size of the template object.
  • the third difference threshold may be a value determined according to the item type, for example, different third difference thresholds are set for different item types, for example, the third difference threshold corresponding to the wardrobe is greater than the third difference threshold corresponding to the chair .
  • the size of the stylized target object can be adaptively adjusted, the user experience can be improved, and the obtained stylized image has a higher degree of fusion.
  • the above-mentioned fusion of the stylized target object and the stylized template to obtain a stylized image may include:
  • the stylized target object is fused at the position in the stylized template to obtain the stylized image.
  • the corresponding relationship between the sizes and positions of different stylization target objects can be preset, and then the corresponding stylization target objects in the stylization template can be determined according to the size of the stylization target objects. Location.
  • the size of the stylized target object corresponding to the position where the near content is displayed in the template is larger, and the size of the stylized target object corresponding to the position where the distant content is displayed is smaller; or , for a stylized template containing a character, the smaller the difference between the size of the character in the template and the size of the stylized target object, the closer the position of the stylized target object is to the position of the character.
  • the position of the stylized target object can be determined according to the correspondence between the position in the stylized template and the size of the stylized target object and the size of the stylized target object, and then the stylized target object can be fused and added to the position. .
  • the position of the stylized target object in the stylized image can be adaptively adjusted according to the size of the stylized target object, which can improve user experience and make the obtained stylized image more highly integrated.
  • the method may further include:
  • the template image is sent to the server, so that the server performs image processing on the template image to obtain a reference stylized template.
  • the user may collect the template image through an image collection device, or may obtain the template image through uploading, downloading, or other methods through the terminal.
  • the terminal device may send a template customization instruction to the server in response to the user's customization operation on the stylized template (triggering operation of the customization control or corresponding voice control instruction, etc.), and the template customization instruction may include a template image.
  • the server may, in response to the template customization instruction, perform image processing on the template image to obtain a reference stylization template, for example, train a stylization processing network corresponding to the template image according to a preset training set.
  • the server may process the sample images in the training set through the stylization processing network to obtain the stylized sample images, and obtain the content loss of the stylization processing network according to the sample images and the stylized sample images.
  • the processed sample images and template images get the style loss of the stylized processing network.
  • the content loss and the style loss for example, a weighted sum operation can be performed
  • the network loss of the stylized processing network can be obtained, and then the stylized processing network can be trained according to the network loss.
  • the calculation process of the above content loss and style loss may use any loss calculation function, and the variables in the function may include feature information reflecting the style of the image, which is not specifically limited in the embodiment of the present disclosure.
  • the server can use the template image as a reference stylization template, and perform stylization processing on the image to be processed according to the stylization processing network of the reference stylization template; or, the template customization instruction It also includes information such as the user's account information, and the server can send the stylized processing network referring to the stylized template to the terminal device corresponding to the user's account information (or the server can send a network training completion instruction to the user's account.
  • the terminal device corresponding to the information so that the user can realize the stylized fusion of the image to be processed and the reference stylized template through the stylization processing network corresponding to the reference stylization template.
  • FIG. 2a to Figure 2c and Figure 3 when a user likes an oil painting when visiting an art exhibition, and wants to integrate his own portrait into the oil painting, he can collect the corresponding image of the oil painting as a template image, and use the terminal device to convert the oil painting into the oil painting.
  • the template image is sent to the server for training of the corresponding stylization processing network. After the training of the stylization processing network is completed, the template image is used as a reference stylized template, and the reference stylized template is displayed in the display area of the stylized template in the display interface of the user terminal device.
  • the terminal device may, in response to the user's selection operation on the reference stylized template, perform stylization processing on the user's portrait in the to-be-processed image by using the reference stylized template to obtain a stylized
  • the processed user portrait, the stylized user portrait has the oil painting texture style of the reference stylized template, and the stylized user portrait is combined with the reference stylized template to obtain a stylized image.
  • the user can customize the reference stylized template, which can meet the user's personalized customization requirements and improve the user experience.
  • the stylized target object is fused with the stylized template to obtain a stylized image, including:
  • a stylized image is obtained in response to an adjustment operation for the stylization target object in the preliminary stylized image, the adjustment operation including a size adjustment operation and/or a position adjustment operation for the stylization target object.
  • the stylized target object can be placed in the stylized template by placing the stylized target object at a preset position of the stylized template, or according to the position of the target object corresponding to the stylized target object in the image to be processed. , to get a preliminary stylized image.
  • the user can adjust the position of the stylized target object in the preliminary stylized image through a position adjustment operation (for example, a drag operation for the stylized target object); the user can also adjust the size of the stylized target object (enlargement operation or Zoom out operation), adjust the position of the stylized target object in the preliminary stylized image to obtain the stylized image.
  • the stylization template includes a character image
  • the user can adjust the stylization target object to the position of the character image through the position adjustment operation, and adjust the stylization target object to be the same as the size adjustment operation of the stylization target object.
  • the size of the person image is similar, so that the person image in the stylized template is replaced by the user's own stylized portrait; or, the stylized template includes a chair, and the user can adjust the stylized target object to the chair position through the position adjustment operation and through the size adjustment operation of the stylized target object, the ratio of the stylized target object and the size of the chair is adjusted to conform to the proportion of the normal human body and the size of the chair, so as to achieve the visual effect of the stylized target object sitting on the chair, which can be achieved User interaction and interaction with stylized templates, making image processing more interesting.
  • the embodiment of the present disclosure further provides an interactive display device, the interactive display device includes: an image processing module and a display module, the image processing module includes an image acquisition unit and an image processing unit; wherein,
  • the image acquisition unit used to acquire images to be processed
  • the image processing unit is configured to determine a stylization template for stylizing the image to be processed, and perform stylization processing on the target object in the to-be-processed image according to the stylization template to obtain a style A stylized target object, the style of the stylized target object is the same as that of the stylized template;
  • the image processing unit is further configured to fuse the stylized target object and the stylized template to obtain a stylized image
  • the display module is used to display the stylized image.
  • the interactive display device can be a display device in a public place, such as a display device in an art exhibition venue such as a painting exhibition, a sculpture exhibition, a museum, etc.
  • an art exhibition venue such as a painting exhibition, a sculpture exhibition, a museum, etc.
  • the participating users can interact with the exhibition.
  • the images corresponding to the items are interactively fused.
  • the interactive display device can collect images to be processed through the image capture unit. For example, when a user stands in front of the interactive display device, the image capture unit starts to capture images for the user.
  • the image processing unit can determine the stylized template for stylizing the image to be processed according to the collected image to be processed, or can display all the stylized templates (the displayed part or all the images corresponding to the paintings) on the display module, and then respond to the Based on the user's selection operation on the stylized template on the display module, it is determined that the selected stylized template is the stylized template used for stylizing the image to be processed, or is determined from the stylized template according to the collected image to be processed.
  • a stylized template for stylizing an image to be processed reference may be made to the foregoing embodiment for a specific process, which will not be repeated in this embodiment of the present disclosure.
  • the image processing unit can stylize the target object in the collected image to be processed through the stylized template, obtain the stylized target object, and merge with the stylized template to obtain the stylized image and display it through the display module.
  • the specific details of the stylization processing in the disclosed embodiments will not be repeated, and the foregoing embodiments may be referred to.
  • the interaction between the user and the artwork can be enriched, and the user experience and interest can be improved.
  • the above-mentioned stylization processing of the image to be processed according to the stylization template may be implemented through a stylization network corresponding to the stylization template, which is not repeated here in the embodiments of the present disclosure, and the foregoing embodiments may be referred to.
  • stylization processing network By stylizing the image to be processed through the stylization processing network, the processing efficiency and accuracy of the image can be improved.
  • the interactive display device may further include a communication module
  • the communication module may be configured to establish a connection with a target terminal device, receive an image to be processed sent by the target terminal device, or send the stylized image to the target terminal device.
  • the interactive display device can establish a connection with the target terminal device through the communication module.
  • two-dimensional code information is displayed on the interactive display device, and the user can scan the two-dimensional code information through the target terminal device to establish a connection with the communication module.
  • the user can upload the to-be-processed image to the interactive display device through the target terminal device for stylization processing, and the terminal device can also send the stylized image to the target terminal device after the to-be-processed image is stylized.
  • the interactive display device may further include a customized module
  • the customization module is used to obtain the template image through the image acquisition unit or the communication module;
  • the communication module is further configured to send the first template image to the server, so that the server performs image processing on the template image to obtain a stylized template corresponding to the template image.
  • users can customize stylized templates through custom modules. For example, if the user likes a painting on display, but there is no stylized template corresponding to the painting in the interactive display device, the user can collect the image of the painting and send the image as a template image through the interactive display device to the server, so that the server trains the stylized processing model corresponding to the template image according to the preset training set and the template image, and then obtains the stylized template corresponding to the template image, which can be processed by the stylized processing model corresponding to the stylized template.
  • the stylized target object is obtained from the to-be-processed image collected by the user, and the stylized target object is fused with the stylized template to obtain a stylized image.
  • permissions can also be set for the custom module.
  • the custom module needs to be enabled when the administrator is logged in, so as to prevent the user from arbitrarily customizing and occupying too many resources.
  • the present disclosure also provides image processing apparatuses, electronic devices, computer-readable storage media, and programs, all of which can be used to implement any image processing method provided by the present disclosure.
  • image processing apparatuses electronic devices, computer-readable storage media, and programs, all of which can be used to implement any image processing method provided by the present disclosure.
  • FIG. 4 shows a block diagram of an image processing apparatus according to an embodiment of the present disclosure. As shown in FIG. 4 , the apparatus includes:
  • the first acquisition module 41 can be used to acquire the image to be processed
  • a determination module 42 which can be used to determine a stylized template for stylizing the image to be processed
  • the processing module 43 may be configured to perform stylization processing on the target object in the to-be-processed image according to the stylization template to obtain a stylized target object, where the stylized target object has the same style as the stylized template;
  • the fusion module 44 can be used to fuse the stylized target object and the stylized template to obtain a stylized image.
  • the image to be processed can be acquired, and after a stylized template for stylizing the image to be processed is determined, the target object in the image to be processed can be stylized according to the stylized template to obtain Stylizing the target object, the stylizing target object is the same style as the stylizing template.
  • the stylized target object and the stylized template may be fused to obtain a stylized image.
  • the image processing apparatus provided according to the embodiment of the present disclosure not only enriches the image processing methods, but also alleviates the problem of blunt fusion caused by the unnatural segmentation edge effect of the target object.
  • the determining module can also be used to:
  • target object recognition on the to-be-processed image to obtain a target-object recognition result of the to-be-processed image, where the target object recognition result includes a target object attribute;
  • a stylization template for stylizing the image to be processed is determined.
  • the determining module can also be used to:
  • the selected reference stylization template is determined as the stylization template for stylizing the image to be processed.
  • the fusion module can also be used to:
  • the fusion module can also be used to:
  • the size of the stylization target object is adjusted according to the size of the template object.
  • the fusion module can also be used to:
  • the stylized target object is fused at the position in the stylized template to obtain the stylized image.
  • the apparatus may further include:
  • the second acquiring module is configured to send the template image to the server, so that the server performs image processing on the template image to obtain a reference stylized template.
  • the fusion module can also be used to:
  • a stylized image is obtained in response to an adjustment operation for the stylization target object in the preliminary stylized image, the adjustment operation including a size adjustment operation and/or a position adjustment operation for the stylization target object.
  • the functions or modules included in the apparatuses provided in the embodiments of the present disclosure may be used to execute the methods described in the above method embodiments.
  • Embodiments of the present disclosure further provide a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the foregoing method is implemented.
  • the computer-readable storage medium may be a non-volatile computer-readable storage medium.
  • An embodiment of the present disclosure further provides an electronic device, including: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to invoke the instructions stored in the memory to execute the above method.
  • Embodiments of the present disclosure also provide a computer program product, including computer-readable codes.
  • a processor in the device executes the image processing method for implementing the image processing method provided by any of the above embodiments. instruction.
  • Embodiments of the present disclosure further provide another computer program product for storing computer-readable instructions, which, when executed, cause the computer to perform the operations of the image processing method provided by any of the foregoing embodiments.
  • the electronic device may be provided as a terminal, server or other form of device.
  • FIG. 5 shows a block diagram of an electronic device 800 according to an embodiment of the present disclosure.
  • electronic device 800 may be a mobile phone, computer, digital broadcast terminal, messaging device, game console, tablet device, medical device, fitness device, personal digital assistant, etc. terminal.
  • electronic device 800 may include one or more of the following components: processing component 802, memory 804, power supply component 806, multimedia component 808, audio component 810, input/output (I/O) interface 812, sensor component 814 , and the communication component 816 .
  • the processing component 802 generally controls the overall operation of the electronic device 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations.
  • the processing component 802 can include one or more processors 820 to execute instructions to perform all or some of the steps of the methods described above.
  • processing component 802 may include one or more modules that facilitate interaction between processing component 802 and other components.
  • processing component 802 may include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802.
  • Memory 804 is configured to store various types of data to support operation at electronic device 800 . Examples of such data include instructions for any application or method operating on electronic device 800, contact data, phonebook data, messages, pictures, videos, and the like. Memory 804 may be implemented by any type of volatile or nonvolatile storage device or combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory, Magnetic or Optical Disk.
  • SRAM static random access memory
  • EEPROM electrically erasable programmable read only memory
  • EPROM erasable Programmable Read Only Memory
  • PROM Programmable Read Only Memory
  • ROM Read Only Memory
  • Magnetic Memory Flash Memory
  • Magnetic or Optical Disk Magnetic Disk
  • Power supply assembly 806 provides power to various components of electronic device 800 .
  • Power supply components 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to electronic device 800 .
  • Multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user.
  • the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user.
  • the touch panel includes one or more touch sensors to sense touch, swipe, and gestures on the touch panel. The touch sensor may not only sense the boundaries of a touch or swipe action, but also detect the duration and pressure associated with the touch or swipe action.
  • the multimedia component 808 includes a front-facing camera and/or a rear-facing camera. When the electronic device 800 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera may receive external multimedia data. Each of the front and rear cameras can be a fixed optical lens system or have focal length and optical zoom capability.
  • Audio component 810 is configured to output and/or input audio signals.
  • audio component 810 includes a microphone (MIC) that is configured to receive external audio signals when electronic device 800 is in operating modes, such as calling mode, recording mode, and voice recognition mode.
  • the received audio signal may be further stored in memory 804 or transmitted via communication component 816 .
  • audio component 810 also includes a speaker for outputting audio signals.
  • the I/O interface 812 provides an interface between the processing component 802 and a peripheral interface module, which may be a keyboard, a click wheel, a button, or the like. These buttons may include, but are not limited to: home button, volume buttons, start button, and lock button.
  • Sensor assembly 814 includes one or more sensors for providing status assessment of various aspects of electronic device 800 .
  • the sensor assembly 814 can detect the on/off state of the electronic device 800, the relative positioning of the components, such as the display and the keypad of the electronic device 800, the sensor assembly 814 can also detect the electronic device 800 or one of the electronic device 800 Changes in the position of components, presence or absence of user contact with the electronic device 800 , orientation or acceleration/deceleration of the electronic device 800 and changes in the temperature of the electronic device 800 .
  • Sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects in the absence of any physical contact.
  • Sensor assembly 814 may also include a light sensor, such as a complementary metal oxide semiconductor (CMOS) or charge coupled device (CCD) image sensor, for use in imaging applications.
  • CMOS complementary metal oxide semiconductor
  • CCD charge coupled device
  • the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
  • Communication component 816 is configured to facilitate wired or wireless communication between electronic device 800 and other devices.
  • the electronic device 800 may access a wireless network based on a communication standard, such as wireless network (WiFi), second generation mobile communication technology (2G) or third generation mobile communication technology (3G), or a combination thereof.
  • the communication component 816 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel.
  • the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication.
  • the NFC module may be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.
  • RFID radio frequency identification
  • IrDA infrared data association
  • UWB ultra-wideband
  • Bluetooth Bluetooth
  • electronic device 800 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable A programmed gate array (FPGA), controller, microcontroller, microprocessor or other electronic component implementation is used to perform the above method.
  • ASICs application specific integrated circuits
  • DSPs digital signal processors
  • DSPDs digital signal processing devices
  • PLDs programmable logic devices
  • FPGA field programmable A programmed gate array
  • controller microcontroller, microprocessor or other electronic component implementation is used to perform the above method.
  • a non-volatile computer-readable storage medium such as a memory 804 comprising computer program instructions executable by the processor 820 of the electronic device 800 to perform the above method is also provided.
  • FIG. 6 shows a block diagram of an electronic device 1900 according to an embodiment of the present disclosure.
  • the electronic device 1900 may be provided as a server.
  • electronic device 1900 includes processing component 1922, which further includes one or more processors, and a memory resource represented by memory 1932 for storing instructions executable by processing component 1922, such as applications.
  • An application program stored in memory 1932 may include one or more modules, each corresponding to a set of instructions.
  • the processing component 1922 is configured to execute instructions to perform the above-described methods.
  • the electronic device 1900 may also include a power supply assembly 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input output (I/O) interface 1958 .
  • the electronic device 1900 can operate based on an operating system stored in the memory 1932, such as a Microsoft server operating system (Windows Server TM ), a graphical user interface based operating system (Mac OS X TM ) introduced by Apple, a multi-user multi-process computer operating system (Unix TM ), Free and Open Source Unix-like Operating System (Linux TM ), Open Source Unix-like Operating System (FreeBSD TM ) or the like.
  • Microsoft server operating system Windows Server TM
  • Mac OS X TM graphical user interface based operating system
  • Uniix TM multi-user multi-process computer operating system
  • Free and Open Source Unix-like Operating System Linux TM
  • FreeBSD TM Open Source Unix-like Operating System
  • a non-volatile computer-readable storage medium such as memory 1932 comprising computer program instructions executable by processing component 1922 of electronic device 1900 to perform the above-described method.
  • the present disclosure may be a system, method and/or computer program product.
  • the computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of the present disclosure.
  • a computer-readable storage medium may be a tangible device that can hold and store instructions for use by the instruction execution device.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing.
  • Non-exhaustive list of computer readable storage media include: portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM) or flash memory), static random access memory (SRAM), portable compact disk read only memory (CD-ROM), digital versatile disk (DVD), memory sticks, floppy disks, mechanically coded devices, such as printers with instructions stored thereon Hole cards or raised structures in grooves, and any suitable combination of the above.
  • RAM random access memory
  • ROM read only memory
  • EPROM erasable programmable read only memory
  • flash memory static random access memory
  • SRAM static random access memory
  • CD-ROM compact disk read only memory
  • DVD digital versatile disk
  • memory sticks floppy disks
  • mechanically coded devices such as printers with instructions stored thereon Hole cards or raised structures in grooves, and any suitable combination of the above.
  • Computer-readable storage media are not to be construed as transient signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (eg, light pulses through fiber optic cables), or through electrical wires transmitted electrical signals.
  • the computer readable program instructions described herein may be downloaded to various computing/processing devices from a computer readable storage medium, or to an external computer or external storage device over a network such as the Internet, a local area network, a wide area network, and/or a wireless network.
  • the network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and/or edge servers.
  • a network adapter card or network interface in each computing/processing device receives computer-readable program instructions from a network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing/processing device .
  • Computer program instructions for carrying out operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or instructions in one or more programming languages.
  • Source or object code written in any combination, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as the "C" language or similar programming languages.
  • the computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server implement.
  • the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (eg, using an Internet service provider through the Internet connect).
  • LAN local area network
  • WAN wide area network
  • custom electronic circuits such as programmable logic circuits, field programmable gate arrays (FPGAs), or programmable logic arrays (PLAs) can be personalized by utilizing state information of computer readable program instructions.
  • Computer readable program instructions are executed to implement various aspects of the present disclosure.
  • These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer or other programmable data processing apparatus to produce a machine that causes the instructions when executed by the processor of the computer or other programmable data processing apparatus , resulting in means for implementing the functions/acts specified in one or more blocks of the flowchart and/or block diagrams.
  • These computer readable program instructions can also be stored in a computer readable storage medium, these instructions cause a computer, programmable data processing apparatus and/or other equipment to operate in a specific manner, so that the computer readable medium on which the instructions are stored includes An article of manufacture comprising instructions for implementing various aspects of the functions/acts specified in one or more blocks of the flowchart and/or block diagrams.
  • Computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other equipment to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other equipment to produce a computer-implemented process , thereby causing instructions executing on a computer, other programmable data processing apparatus, or other device to implement the functions/acts specified in one or more blocks of the flowcharts and/or block diagrams.
  • each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more functions for implementing the specified logical function(s) executable instructions.
  • the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented in dedicated hardware-based systems that perform the specified functions or actions , or can be implemented in a combination of dedicated hardware and computer instructions.
  • the computer program product can be specifically implemented by hardware, software or a combination thereof.
  • the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK), etc. Wait.
  • a software development kit Software Development Kit, SDK

Abstract

本公开涉及一种图像处理方法及装置、互动式展示装置和电子设备，所述方法包括：获取待处理图像；确定用于对所述待处理图像进行风格化处理的风格化模板；根据所述风格化模板对所述待处理图像中的目标对象进行风格化处理，得到风格化目标对象，所述风格化目标对象与所述风格化模板的风格相同；将所述风格化目标对象与所述风格化模板进行融合，得到风格化图像。本公开实施例可丰富图像的处理方式。

Description

图像处理方法及装置、互动式展示装置和电子设备
本申请要求在2020年08月21日提交中国专利局、申请号为202010850797.X、发明名称为“图像处理方法及装置、互动式展示装置和电子设备”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
本公开涉及计算机技术领域，尤其涉及一种图像处理方法及装置、互动式展示装置和电子设备。
背景技术
随着科技的发展和进步，对多媒体数据的处理方式越来越多。例如：可以对多媒体数据进行美化、添加特效、添加滤镜等处理，对多媒体数据处理处理方式的丰富性以及处理质量，有着越来越高的需求。
发明内容
本公开提出了一种用于对图像进行处理和融合的图像处理技术方案。
根据本公开的一方面，提供了一种图像处理方法，包括：
获取待处理图像；
确定用于对所述待处理图像进行风格化处理的风格化模板；
根据所述风格化模板对所述待处理图像中的目标对象进行风格化处理，得到风格化目标对象，所述风格化目标对象与所述风格化模板的风格相同；
将所述风格化目标对象与所述风格化模板进行融合，得到风格化图像。
在一种可能的实现方式中，所述确定用于对所述待处理图像进行风格化处理的风格化模板，包括：
对所述待处理图像进行目标对象识别，得到所述待处理图像的目标对象识别结果，所述目标对象识别结果包括目标对象属性；
根据所述目标对象属性，确定用于对所述待处理图像进行风格化处理的风格化模板。
在一种可能的实现方式中，所述确定用于对所述待处理图像进行风格化处理的风格化模板，包括：
确定所述待处理图像与至少一个参考风格化模板的相似度，根据所述相似度从所述参考风格化模板中，确定用于对所述待处理图像进行风格化处理的风格化模板；或，
响应于针对参考风格化模板的选择操作，将选中的所述参考风格化模板确定为用于所述待处理图像进行风格化处理的风格化模板。
在一种可能的实现方式中，所述将所述风格化目标对象与所述风格化模板进行融合，得到风格化图像，包括：
在所述风格化目标对象的尺寸满足尺寸调整条件的情况下，按照预置调整规则对所 述目标对象进行调整，将调整后的风格化目标对象与所述风格化模板融合，得到风格化图像。
在一种可能的实现方式中，所述在所述风格化目标对象的尺寸满足尺寸调整条件的情况下，按照预置调整规则对所述目标对象进行调整，包括：
检测所述风格化模板中的模板对象的尺寸；
在所述风格化目标对象的尺寸与所述模板对象的尺寸不匹配的情况下，根据所述模板对象的尺寸调整所述风格化目标对象的尺寸。
在一种可能的实现方式中，所述将所述风格化目标对象与所述风格化模板进行融合，得到风格化图像，包括：
根据所述风格化目标对象的尺寸，确定所述风格化目标对象在所述风格化模板中对应的位置；
在所述风格化模板中的所述位置处融合所述风格化目标对象，得到所述风格化图像。
在一种可能的实现方式中，所述方法还包括：
获取模板图像；
向服务器发送所述模板图像，以使所述服务器对所述模板图像进行图像处理，得到参考风格化模板。
在一种可能的实现方式中，将所述风格化目标对象与所述风格化模板进行融合，得到风格化图像，包括：
将所述风格化目标对象与所述风格化模板进行融合，得到初步风格化图像；
响应于针对所述初步风格化图像中风格化目标对象的调整操作，得到风格化图像，所述调整操作包括针对风格化目标对象的尺寸调整操作和/或位置调整操作。
根据本公开的一方面，提供了一种互动式展示装置，所述互动式展示装置包括：图像处理模块和展示模块，所述图像处理模块包括图像采集单元和图像处理单元；其中，
所述图像采集单元，用于采集待处理图像；
所述图像处理单元，用于确定用于对所述待处理图像进行风格化处理的风格化模板，并根据所述风格化模板对所述待处理图像中的目标对象进行风格化处理，得到风格化目标对象，所述风格化目标对象与所述风格化模板的风格相同；
所述图像处理单元，还用于将所述风格化目标对象与所述风格化模板进行融合，得到风格化图像；
所述展示模块，用于展示所述风格化图像。
根据本公开的一方面，提供了一种图像处理装置，包括：
第一获取模块，用于获取待处理图像；
确定模块，用于确定用于对所述待处理图像进行风格化处理的风格化模板；
处理模块，用于根据所述风格化模板对所述待处理图像中的目标对象进行风格化处理，得到风格化目标对象，所述风格化目标对象与所述风格化模板的风格相同；
融合模块，用于将所述风格化目标对象与所述风格化模板进行融合，得到风格化图 像。
在一种可能的实现方式中，所述确定模块，还用于：
对所述待处理图像进行目标对象识别，得到所述待处理图像的目标对象识别结果，所述目标对象识别结果包括目标对象属性；
根据所述目标对象属性，确定用于对所述待处理图像进行风格化处理的风格化模板。
在一种可能的实现方式中，所述确定模块，还用于：
确定所述待处理图像与至少一个参考风格化模板的相似度，根据所述相似度从所述参考风格化模板中，确定用于对所述待处理图像进行风格化处理的风格化模板；或，
响应于针对参考风格化模板的选择操作，将选中的所述参考风格化模板确定为用于所述待处理图像进行风格化处理的风格化模板。
在一种可能的实现方式中，所述融合模块，还用于：
在所述风格化目标对象的尺寸满足尺寸调整条件的情况下，按照预置调整规则对所述目标对象进行调整，将调整后的风格化目标对象与所述风格化模板融合，得到风格化图像。
在一种可能的实现方式中，所述融合模块，还用于：
检测所述风格化模板中的模板对象的尺寸；
在所述风格化目标对象的尺寸与所述模板对象的尺寸不匹配的情况下，根据所述模板对象的尺寸调整所述风格化目标对象的尺寸。
在一种可能的实现方式中，所述融合模块，还用于：
根据所述风格化目标对象的尺寸，确定所述风格化目标对象在所述风格化模板中对应的位置；
在所述风格化模板中的所述位置处融合所述风格化目标对象，得到所述风格化图像。
在一种可能的实现方式中，所述装置还包括：
第二获取模块，用于向服务器发送所述模板图像，以使所述服务器对所述模板图像进行图像处理，得到参考风格化模板。
在一种可能的实现方式中，所述融合模块，还用于：
将所述风格化目标对象与所述风格化模板进行融合，得到初步风格化图像；
响应于针对所述初步风格化图像中风格化目标对象的调整操作，得到风格化图像，所述调整操作包括针对风格化目标对象的尺寸调整操作和/或位置调整操作。
根据本公开的一方面，提供了一种电子设备，包括：处理器；用于存储处理器可执行指令的存储器；其中，所述处理器被配置为调用所述存储器存储的指令，以执行上述方法。
根据本公开的一方面，提供了一种计算机可读存储介质，其上存储有计算机程序指令，所述计算机程序指令被处理器执行时实现上述方法。
根据本公开的一方面，提供了一种计算机程序产品，包括计算机可读代码，当所述计算机可读代码在电子设备中运行时，所述电子设备中的处理器执行用于实现上述方法。
在本公开实施例中，可以获取待处理图像，并确定用于对所述待处理图像进行风格化处理的风格化模板后，根据所述风格化模板对所述待处理图像中的目标对象进行风格化处理，得到风格化目标对象，所述风格化目标对象与所述风格化模板的风格相同。可以将所述风格化目标对象与所述风格化模板进行融合，得到风格化图像。根据本公开实施例提供的图像处理方法及装置、互动式展示装置和电子设备，不仅丰富了图像的处理方式，还缓解了由于目标对象的分割边缘效果不自然造成融合生硬的问题。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，而非限制本公开。根据下面参考附图对示例性实施例的详细说明，本公开的其它特征及方面将变得清楚。
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，这些附图示出了符合本公开的实施例，并与说明书一起用于说明本公开的技术方案。
图1示出根据本公开实施例的图像处理方法的流程图；
图2a～图2c示出根据本公开实施例的图像处理方法的示意图；
图3示出根据本公开实施例的图像处理方法的示意图；
图4示出根据本公开实施例的图像处理装置的框图；
图5示出根据本公开实施例的一种电子设备800的框图；
图6示出根据本公开实施例的一种电子设备1900的框图。
具体实施方式
以下将参考附图详细说明本公开的各种示例性实施例、特征和方面。附图中相同的附图标记表示功能相同或相似的元件。尽管在附图中示出了实施例的各种方面，但是除非特别指出，不必按比例绘制附图。
在这里专用的词“示例性”意为“用作例子、实施例或说明性”。这里作为“示例性”所说明的任何实施例不必解释为优于或好于其它实施例。
本文中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，本文中术语“至少一种”表示多种中的任意一种或多种中的至少两种的任意组合，例如，包括A、B、C中的至少一种，可以表示包括从A、B和C构成的集合中选择的任意一个或多个元素。
另外，为了更好地说明本公开，在下文的具体实施方式中给出了众多的具体细节。本领域技术人员应当理解，没有某些具体细节，本公开同样可以实施。在一些实例中，对于本领域技术人员熟知的方法、手段、元件和电路未作详细描述，以便于凸显本公开的主旨。
图1示出根据本公开实施例的图像处理方法的流程图，所述图像处理方法可以由终端 设备或服务器等电子设备执行，终端设备可以为用户设备(User Equipment，UE)、移动设备、用户终端、终端、蜂窝电话、无绳电话、个人数字处理(Personal Digital Assistant，PDA)、手持设备、计算设备、车载设备、可穿戴设备等，所述方法可以通过处理器调用存储器中存储的计算机可读指令的方式来实现。或者，可通过服务器执行所述方法。
如图1所示，所述图像处理方法可以包括：
在步骤S11中，获取待处理图像。
举例来说，可以通过图像采集设备(例如：手机、相机、摄像设备等具有图像采集功能的设备)采集待处理图像，或者，或者可以通过终端上传、下载等方式获取待处理图像，本公开实施例对于获取待处理图像的方式不做具体限定。
在步骤S12中，确定用于对所述待处理图像进行风格化处理的风格化模板。
举例来说，所述风格化模板可以为艺术作品的图像，例如：风格化模板可以为油画、素描、水墨画、雕塑或者雕刻等艺术作品对应的图像，相应地，这些风格化模板可分别呈现出油画风格、素描风格、水墨画风格、雕塑或雕刻风格等，或者，风格化模板也可以为其他风格的图像，例如：风格化模板可以为呈现漫画风格的图像，或者风格化模板可以为呈现电影风格的图像等等。
举例来说，可以响应于用户针对风格化模板的选择操作，确定用于对待处理图像进行风格化处理的风格化模板；或者，可以根据待处理图像，确定用于对待处理图像进行风格化处理的风格化模板。
示例性的，在本公开实施例由终端设备执行时，终端设备可以从服务器端获取并存储至少一个风格化模板，并在获取待处理图像后，从存储的至少一个风格化模板中确定用于对待处理图像进行风格化处理的风格化模板。
例如：终端设备中可以根据待处理图像确定用于对待处理图像进行风格化处理的风格化模板；或者，终端设备可以在显示界面上展示至少一个风格化模板，用户可以进行选择，终端设备响应于用户针对风格化模板的选择操作，确定被选中的风格化模板为用于对待处理图像进行风格化处理的风格化模板。
再示例性的，在本公开实施例由服务器执行时，服务器可以接收来自终端设备的风格化处理指示，该风格化处理指示中可以包括待处理图图像，服务器可以根据风格化处理指示从本地存储的风格化模板中确定用于对待处理图像进行风格化处理的风格化模板。
例如：服务器可以根据待处理图像确定用于对待处理图像进行风格化处理的风格化模板；或者，风格化处理指示中还包括用户所选择的风格化模板的模板图像标识信息，服务器可以确定该模板图像标识信息所标识的风格化模板，为用于对待处理图像进行风格化处理的风格化模板。
在步骤S13中，根据所述风格化模板对所述待处理图像中的目标对象进行风格化处理，得到风格化目标对象，所述风格化目标对象与所述风格化模板的风格相同。
举例来说，可以通过预训练的风格化模板对应的风格化处理网络，对待处理图像进 行风格化处理。其中，风格化处理网络为可以对应一张或多张风格相同风格化模板的神经网络，经过该风格化处理网络处理后的图像数据，其风格与风格化模板相同，或者，风格化处理网络也可以对应不同的风格化模板，本公开实施例对此不作限定。风格可以指图像在整体上呈现的有代表性的面貌。不同的图像可以呈现不同的风格，示例性的，可以通过图像中的提取的特征来反映图像的风格，并通过图像之间这些特征的相似性，来判断风格是否相同或不同。示例性的，风格化处理网络的训练过程可以在服务器端进行，即可以在服务器端根据各风格化模板训练与各风格化模板对应的风格化处理网络。通过风格化处理网络对待处理图像进行风格化处理，可以提高图像的处理效率和精度。
举例来说，在确定用于对待处理图像进行风格化处理的风格化模板后，可以确定该风格化模板对应的风格化处理网络，可以通过该风格化处理网络对待处理图像中的目标对象进行风格化处理，以得到风格化目标对象，该风格化目标对象与风格化模板图像的风格相同，例如：风格化模板为油画作品对应的图像，则风格化目标对象为油画纹理风格。
示例性的，可以通过该风格化模板对待处理图像进行风格化处理，得到风格化处理后的待处理图像，并对风格化处理后的待处理图像进行目标对象识别及分割，得到风格化目标对象。或者，还可以对待处理图像进行目标对象识别及分割，得到待处理图像中的目标对象，通过风格化模板对目标对象进行风格化处理，得到风格化目标对象。
需要说明的是，目标对象识别及分割过程采用预先训练的用于进行识别和分割的神经网络进行处理即可，本公开实施例不对进行目标对象识别和分割的神经网络进行限定。
在步骤S14中，将所述风格化目标对象与所述风格化模板进行融合，得到风格化图像。
举例来说，在得到风格化目标对象后，可以将该风格化目标对象融合至风格化模板中，得到风格化图像。例如：可以使风格化目标对象按照预置尺寸进行尺寸调整后，添加至风格化模板的预置位置处，或者可以根据风格化目标对象对应的目标对象在待处理图像中所处的位置，确定风格化目标对象在风格化模板中所处的位置，将风格化目标对象添加到该位置处。
示例性的，待处理图像为针对用户A采集的图像数据，风格化模板为一幅油画，则图像数据经过该油画对应的风格化处理网络处理后，图像数据中用户A的人体图像处理为该油画纹理风格，最终得到的风格化图像数据为该幅油画中包括用户A的油画纹理风格的人体图像。
需要说明的是，本公开实施例也可以对视频数据进行风格化处理，在处理视频数据时，可以通过上述图像处理方法对视频数据的至少一个视频帧进行风格化处理，得到至少一个视频帧对应的风格化视频帧，所有视频帧对应的风格化视频帧组成视频数据对应的风格化视频数据。
这样，可以获取待处理图像，并确定用于对所述待处理图像进行风格化处理的风格化模板后，根据所述风格化模板对所述待处理图像中的目标对象进行风格化处理，得到风格化目标对象，所述风格化目标对象与所述风格化模板的风格相同。可以将所述风格 化目标对象与所述风格化模板进行融合，得到风格化图像。根据本公开实施例提供的图像处理方法，不仅丰富了图像的处理方式，还缓解了由于目标对象的分割边缘效果不自然造成融合生硬的问题。
在一种可能的实现方式中，所述确定用于对所述待处理图像进行风格化处理的风格化模板，可以包括：
对所述待处理图像进行目标对象识别，得到所述待处理图像的目标对象识别结果，所述目标对象识别结果包括目标对象属性；
根据所述目标对象属性，确定用于对所述待处理图像进行风格化处理的风格化模板。
举例来说，可以对待处理图像进行目标对象识别(例如：可以通过用于对目标对象进行识别的识别网络，对待处理图像进行目标对象识别)，得到待处理图像的目标对象识别结果。目标对象识别结果中可以包括目标对象属性，目标对象属性可以包括至少一项目标对象的属性特征。
可以确定与目标对象属性相匹配的风格化模板，为用于对待处理图像进行风格化处理的风格化模板。示例性的，风格化处模板可以具有至少一个属性标签信息，在风格化模板存在与目标对象属性相匹配的属性标签信息的情况下，可以确定该风格化模板为用于对待处理图像进行风格化处理的风格化模板。
在一种可能的实现方式中，所述目标对象属性包括目标对象的年龄和/或性别、所述目标对象在所述待处理图像中的尺寸大小、所述目标对象的面部表情、所述目标对象的形体姿态、所述目标对象的色调中的至少一项。
示例性的，目标对象属性包括目标对象的年龄和/或性别，则可以确定属性标签与目标对象的年龄和/或性别相匹配的风格化模板，为用于对待处理图像进行风格化处理的风格化模板。例如：当目标对象的年龄为0-6岁时，可以查找属性标签包括：婴幼儿或者0-6岁的风格化模板，该风格化模板可以为包括婴幼儿或者动物等内容、风格比较温馨可爱的艺术作品所对应的图像。
或者，目标对象属性包括目标对象在多媒体数据中的尺寸大小，则可以确定属性标签与目标对象在待处理图像中的尺寸大小相匹配的风格化模板，为用于对待处理图像进行风格化处理的风格化模板。例如：当目标对象在待处理图像中的尺寸大小为a*b，则可以查找属性标签包括：尺寸为c*d的风格化模型，其中，c可以为(a-x)～(a+x)中的任意值，d可以为b(b-y)～(b+y)中的任意值(其中，x与y可以相同，也可以不同)。该风格化模型可以为包含有尺寸与目标对象尺寸a*b相似的人物的艺术作品所对应的图像、或者在预置位置处添加尺寸a*b的目标对象所呈现的视觉效果比较协调的艺术作品所对应的图像。
或者，目标对象属性包括目标对象的面部表情，则可以确定属性标签与目标对象的面部表情相匹配的风格化模板，为用于对待处理图像进行风格化处理的风格化模型。例如：当目标对象的面部表情为开心大笑，则可以查找属性标签与开心相匹配的风格化模型版，该风格化模板为风格比较轻快明朗的艺术作品所对应的图像等、或者风格化模板 为包括开心大笑人物的图像等。
或者，目标对象属性包括目标对象的形体姿态，则可以确定属性标签与目标对象的形体姿态相匹配的风格化模板，为用于对待处理图像进行风格化处理的风格化模板。例如：当目标对象的形体姿态为坐，则可以查找属性标签与坐相匹配的风格化模板(例如：属性标签包括坐、与坐相关的物品(椅子、沙发等)等)，该风格化模板包括坐姿的人物的图像、或者风格化模板为包括与坐姿有关的家居用品的图像。
或者，目标对象属性包括目标对象的色调，则可以确定属性标签与目标对象的色调相匹配的风格化模板，为用于对待处理图像进行风格化处理的风格化模板。例如：当目标对象的色调为灰暗色调，则可以查找属性标签与灰暗色调相匹配的风格化模板，该风格化模板的色调较为灰暗。
这样，可以根据目标对象属性自适应的匹配对应的风格化模板，可以提高待处理图像的处理效率和趣味性。
需要说明的是，当根据目标对象属性匹配到多个风格化模板时，可以响应于用户的选择操作，从中确定用于对待处理图像进行风格化处理的风格化模板；当根据目标对象属性未匹配到风格化模板时，可以响应于用户的选择操作，从全部风格化模板中确定用于对待处理图像进行风格化处理的风格化模板，或者根据全部风格化模板的历史被使用数据，将使用率较高的风格化模板推荐给用户。
在一种可能的实现方式中，上述确定用于对所述待处理图像进行风格化处理的风格化模板，可以包括：
确定所述待处理图像与至少一个参考风格化模板的相似度，根据所述相似度从所述参考风格化模板中，确定用于所述待处理图像进行风格化处理的风格化模板，或，响应于针对参考风格化模板的选择操作，将选中的所述参考风格化模板确定为用于所述待处理图像进行风格化处理的风格化模板。
举例来说，可以确定待处理图像与至少一个参考风格化模板的相似度(包括内容相似度、色彩相似度等)，根据待处理图像与至少一个参考风格化模板的相似度确定与待处理图像相匹配的风格化模板。例如：可以确定相似度最高的参考风格化模板为用于对待处理图像进行风格化处理的风格化模板。
或者，还可以根据待处理图像与至少一个参考风格化模板的相似度对参考风格化模板进行相似度由高到低的排序，按照排序在终端设备侧展示参考风格化模板，以供用户选择，用户选中的参考风格化模板即为用于所述待处理图像进行风格化处理的风格化模板。
或者，可以根据待处理图像进行内容解析，得到待处理图像的内容，确定待处理图像的内容的关联内容，根据待处理图像的内容和关联内容，确定与待处理图像的内容或者关联内容相匹配的风格化模板。例如：待处理图像的内容为目标对象坐着，关联内容为与坐相关的物品(椅子、沙发等)等，则可以匹配包含坐或者包含与坐相关的物品的风格化模板。在匹配的风格化模板数量多于一个时，可以终端设备侧展示该多个风格化 模板，以供用户选择，用户选中的风格化模板即为最终确定的用于对待处理图像进行风格化处理的风格化模板。
这样，可以根据目标对象属性自适应的匹配对应的风格化模板，可以提高待处理图像的处理效率和趣味性。
举例来说，可以在终端设备的显示界面的展示区域，展示至少一个参考风格化模板。用户可以根据喜好通过手动选择参考风格化模板来选择用于对待处理图像进行风格化处理的风格化模板。用户可以通过触摸或者点击等选中操作选择参考风格化模板。终端设备可以响应于用户针对参考风格化模板的选中操作，将选中的参考风格化模板确定为用于待处理图像进行风格化处理的风格化模板。
在一种可能的实现方式中，上述将所述风格化目标对象与所述风格化模板进行融合，得到风格化图像，可以包括：
在所述风格化目标对象的尺寸满足尺寸调整条件的情况下，按照预置调整规则对所述目标对象进行调整，将调整后的风格化目标对象与所述风格化模板融合，得到风格化图像。
举例来说，尺寸调整条件可以为用于对风格化目标对象的尺寸进行调整的限制条件，预置调整规则可以为与尺寸调整条件相对应的，用于对风格化目标对象进行尺寸调整的规则。
例如：预设第一尺寸阈值和第二尺寸阈值，第一尺寸阈值大于第二尺寸阈值。在风格化目标对象的尺寸大于第一尺寸阈值或者小于第二尺寸阈值时，可以将风格化目标对象的尺寸调整为第一尺寸阈值与第二尺寸阈值之间的任一值。或者，在风格化目标对象的尺寸大于第一尺寸阈值或者小于第二尺寸阈值时，可以根据风格化模板中人物或者物品的尺寸调整风格化目标对象的尺寸，使其与风格化模板中人物或者物品的尺寸相匹配，并将调整后的风格化目标图像与风格化模板融合，得到风格化图像。
在一种可能的实现方式中，上述在所述风格化目标对象的尺寸满足尺寸调整条件的情况下，按照预置调整规则对所述目标对象进行调整，可以包括：
检测所述风格化模板中的模板对象的尺寸；
在所述风格化目标对象的尺寸与所述模板对象的尺寸不匹配的情况下，根据所述模板对象的尺寸调整所述风格化目标对象的尺寸。
举例来说，可以检测风格化模板中的模板对象的尺寸，该模板对象可以为风格化模板中的人物、动物或者物品。可以预设模板对象与风格化目标对象的匹配关系，例如：在模板对象为人物时，在该人物尺寸与风格化目标对象的尺寸差值小于第一差值阈值时，可以确定该风格化目标对象与模板对象的尺寸相匹配，否则，确定该风格化目标对象与模板对象的尺寸不匹配。其中，第一差值阈值可以为根据人物年龄属性确定的值，例如：在模板对象与风格化对象为同一年龄属性(都是儿童、或者都是成年人等)时，确定的第一差值阈值较小；在模板对象与风格化对象为不同年龄属性时，确定的第一差值阈值较大。
或者，在模板对象为动物时，在该动物尺寸与风格化目标对象的尺寸差值小于第二差值阈值时，可以确定该风格化目标对象与模板对象的尺寸相匹配，否则，确定该风格化目标对象与模板对象的尺寸不匹配。其中，第二差值阈值可以为根据动物体型确定的值，例如：动物体型较小时，第二差值阈值设置的较大，动物体型较大时，第二差值阈值设置的较小。
或者，在模板对象为物品时，在该物品尺寸与风格化目标对象的尺寸差值小于第三差值阈值时，可以确定该风格化目标对象与模板对象的尺寸相匹配，否则，确定该风格化目标对象与模板对象的尺寸不匹配。其中，第三差值阈值可以为根据物品类型确定的值，例如：不同的物品类型设置不同的第三差值阈值，比如：衣柜对应的第三差值阈值大于椅子对应的第三差值阈值。
这样一来，可以自适应的调整风格化目标对象的尺寸，可以提高用户体验，且使得得到的风格化图像融合度更高。
在一种可能的实现方式中，上述将所述风格化目标对象与所述风格化模板进行融合，得到风格化图像，可以包括：
根据所述风格化目标对象的尺寸，确定所述风格化目标对象在所述风格化模板中对应的位置；
在所述风格化模板中的所述位置处融合所述风格化目标对象，得到所述风格化图像。
举例来说，针对风格化模板，可以预设定不同风格化目标对象的尺寸与位置之间的对应的关系，进而可以根据风格化目标对象的尺寸确定风格化目标对象在风格化模板中对应的位置。
例如：针对风景类的风格化模板，模板中呈现近处内容的位置处对应的风格化目标对象的尺寸较大，呈现远处的内容的位置处对应的风格化目标对象的尺寸较小；或者，针对包含人物的风格化模板，模板中该人物的尺寸与风格化目标对象的尺寸的差值越小，风格化目标对象对应的位置与该人物所处的位置越接近。
进而可以根据该风格化模板中位置与风格化目标对象的尺寸的对应关系及风格化目标对象的尺寸，确定该风格化目标对象的位置，进而可以将该风格化目标对象融合添加至该位置处。
这样一来，可以自适应的根据风格化目标对象的尺寸调整风格化目标对象在风格化图像中的位置，可以提高用户体验，且使得得到的风格化图像融合度更高。
在一种可能的实现方式中，所述方法还可以包括：
获取模板图像；
向服务器发送所述模板图像，以使所述服务器对所述模板图像进行图像处理，得到参考风格化模板。
举例来说，用户可以通过图像采集设备采集模板图像，或者可以通过终端上传、下载等方式获取模板图像。终端设备可以响应于用户对风格化模板的定制操作(对定制控件的触发操作或者相应的语音控制指令等)，向服务器发送模板定制指令，该模板定制指 令中可以包括模板图像。服务器可以响应于模板定制指令，对所述模板图像进行图像处理，得到参考风格化模板，例如：根据预设的训练集训练该模板图像对应的风格化处理网络。
示例性的，服务器可以通过风格化处理网络处理训练集中的样本图像，得到风格化处理后的样本图像，根据样本图像及风格化处理后的样本图像得到风格化处理网络的内容损失，根据风格化处理后的样本图像与模板图像得到风格化处理网络的风格损失。根据内容损失及风格损失(例如：可以进行加权求和操作)，可以得到风格化处理网络的网络损失，进而根据网络损失训练风格化处理网络。上述内容损失和风格损失的计算过程可以采用任一损失计算函数，函数中的变量可包括反映图像风格的特征信息，本公开实施例对此不作具体限定。
在完成模板图像的风格化处理网络的训练后，服务器可以将该模板图像作为参考风格化模板，并根据该参考风格化模板的风格化处理网络对待处理图像进行风格化处理；或者，模板定制指令之中还包括用户的账号信息等信息，服务器可以将参考风格化模板的风格化处理网络发送至该用户的账号信息所对应的终端设备中(或者服务器可以发送网络训练完成指示至该用户的账号信息所对应的终端设备中)，以使得用户可以通过参考风格化模板对应的风格化处理网络实现将待处理图像与参考风格化模板进行风格化融合。
例如：参照图2a至图2c及图3，用户在逛画展的时候喜欢一幅油画，想将自己的人像融入至该油画中，则可以采集该油画对应的图像作为模板图像，通过终端设备将模板图像发送至服务器进行对应的风格化处理网络的训练。在风格化处理网络的训练完成后，将该模板图像作为参考风格化模板，在该用户终端设备的显示界面中对于风格化模板的展示区域中，展示该参考风格化模板。通过终端设备获取包括用户头像的待处理图像后，终端设备可以响应于用户针对参考风格化模板的选中操作，可以通过参考风格化模板对于待处理图像中的用户人像进行风格化处理，得到风格化处理后的用户人像，风格化后的用户人像具有参考风格化模板的油画纹理风格，并将风格化后的用户人像与参考风格化模板合，得到风格化图像。
这样，用户可以定制参考风格化模板，可以满足用户的个性定制需求，提高用户体验。
在一种可能的实现方式中，将所述风格化目标对象与所述风格化模板进行融合，得到风格化图像，包括：
将所述风格化目标对象与所述风格化模板进行融合，得到初步风格化图像；
响应于针对所述初步风格化图像中风格化目标对象的调整操作，得到风格化图像，所述调整操作包括针对风格化目标对象的尺寸调整操作和/或位置调整操作。
举例来说，可以通过将风格化目标对象置于风格化模板的预置位置处，或者根据风格化目标对象对应的目标对象在待处理图像中的位置，将风格化目标对象置于风格化模板中，得到初步风格化图像。用户可以通过位置调整操作(例如：针对风格化目标对象 的拖动操作)，调整风格化目标对象在初步风格化图像中的位置；用户还可以通过风格化目标对象的尺寸调整操作(放大操作或者缩小操作)，调整风格化目标对象在初步风格化图像中的位置，以得到风格化图像。
示例性的，风格化模板中包括一个人物图像，用户可以通过位置调整操作将风格化目标对象调整至该人物图像位置处，并通过风格化目标对象的尺寸调整操作将风格化目标对象调整为与该人物图像尺寸相似，以将风格化模板中该人物图像替换为用户自己风格化后的人像；或者，风格化模板中包括一个椅子，用户可以通过位置调整操作将风格化目标对象调整至椅子位置处，并通过风格化目标对象的尺寸调整操作，将风格化目标对象与椅子大小的比例调整为符合正常人体与椅子大小的比例，以实现风格化目标对象坐在椅子上的视觉效果，可以实现用户与风格化模板的互动和交互，提高图像处理的趣味性。
本公开实施例还提供了一种互动式展示装置，所述互动式展示装置包括：图像处理模块和展示模块，所述图像处理模块包括图像采集单元和图像处理单元；其中，
所述图像采集单元，用于采集待处理图像；
所述图像处理单元，用于确定用于对所述待处理图像进行风格化处理的风格化模板，并根据所述风格化模板对所述待处理图像中的目标对象进行风格化处理，得到风格化目标对象，所述风格化目标对象与所述风格化模板的风格相同；
所述图像处理单元，还用于将所述风格化目标对象与所述风格化模板进行融合，得到风格化图像；
所述展示模块，用于展示所述风格化图像。
举例来说，该互动式展示装置可以为公共场所的展示装置，例如：可以为画展、雕塑展、博物馆等艺术展览场馆处的展示装置，通过该互动式展示装置，参展的用户可以与所展览的物品对应的图像进行互动融合。
以画展为例，该互动式显示装置可以通过图像采集单元采集待处理图像，例如：用户站在互动式显示装置前面，图像采集单元开始针对用户采集图像。
图像处理单元可以根据采集的待处理图像确定对待处理图像进行风格化处理的风格化模板，或者可以在展示模块上展示所有的风格化模板(展示的部分或者所有的画对应的图像)，进而响应于用户在展示模块上对于风格化模板的选择操作，确定选中的风格化模板为用于对待处理图像进行风格化处理的风格化模板，或者根据采集的待处理图像从风格化模板中确定用于对待处理图像进行风格化处理的风格化模板，具体过程可以参照前述实施例，本公开实施例对此不再赘述。
图像处理单元可以通过风格化模板将采集的待处理图像中的目标对象进行风格化处理后，得到风格化目标对象，并与风格化模板进行融合，得到风格化图像并通过展示模块进行展示，本公开实施例对风格化处理的具体细节不再赘述，参照前述实施例即可。
这样，根据本公开实施例提供的互动式展示装置，可以丰富用户与艺术作品的互动方式，提高了用户体验和趣味性。
上述根据风格化模板对待处理图像进行风格化处理，可以通过风格化模板对应的风格化网络实现，本公开实施例在此不再赘述，参照前述实施例即可。通过风格化处理网络对待处理图像进行风格化处理，可以提高图像的处理效率和精度。
在一种可能的实现方式中，所述互动式展示装置还可以包括通信模块，
所述通信模块，可以用于与目标终端设备建立连接，接收所述目标终端设备发送的待处理图像，或者将所述风格化图像发送至所述目标终端设备。
举例来说，互动式展示装置可以通过通信模块与目标终端设备建立连接。例如：互动式展示装置上显示有二维码信息，用户可以通过目标终端设备扫描二维码信息，以与通信模块建立连接。用户可以通过目标终端设备向互动式展示装置上传待处理图像进行风格化处理，终端设备也可以在待处理图像完成风格化处理后，将风格化图像发送至目标终端设备上。
在一种可能的实现方式中，所述互动式展示装置还可以包括定制模块，
所述定制模块，用于通过图像采集单元或者通信模块，获取模板图像；
所述通信模块，还用于向服务器发送所述第一模板图像，以使所述服务器对所述模板图像，进行图像处理，得到所述模板图像对应的风格化模板。举例来说，用户可以通过定制模块，定制风格化模板。例如：用户喜欢展出的一幅画，但是互动式展示装置中并没有该幅画对应的风格化模板，则用户可以采集该幅画的图像，将该图像作为模板图像通过互动式展示装置发送至服务器，以使得服务器根据预设的训练集和模板图像训练模板图像对应的风格化处理模型，进而得到该模板图像对应的风格化模板，可以通过该风格化模板对应的风格化处理模型处理针对用户采集的待处理图像，得到风格化目标对象，并将风格化目标对象与风格化模板融合，得到风格化图像。
示例性的，也可以对定制模块进行权限设置，例如：定制模块需要在管理员登录的情况下方可开启，这样可以避免用户随意进行定制，占用过多资源的情况。
可以理解，本公开提及的上述各个方法实施例，在不违背原理逻辑的情况下，均可以彼此相互结合形成结合后的实施例，限于篇幅，本公开不再赘述。本领域技术人员可以理解，在具体实施方式的上述方法中，各步骤的具体执行顺序应当以其功能和可能的内在逻辑确定。
此外，本公开还提供了图像处理装置、电子设备、计算机可读存储介质、程序，上述均可用来实现本公开提供的任一种图像处理方法，相应技术方案和描述和参见方法部分的相应记载，不再赘述。
图4示出根据本公开实施例的图像处理装置的框图，如图4所示，所述装置包括：
第一获取模块41，可以用于获取待处理图像；
确定模块42，可以用于确定用于对所述待处理图像进行风格化处理的风格化模板；
处理模块43，可以用于根据所述风格化模板对所述待处理图像中的目标对象进行风格化处理，得到风格化目标对象，所述风格化目标对象与所述风格化模板的风格相同；
融合模块44，可以用于将所述风格化目标对象与所述风格化模板进行融合，得到风 格化图像。
这样，可以获取待处理图像，并确定用于对所述待处理图像进行风格化处理的风格化模板后，根据所述风格化模板对所述待处理图像中的目标对象进行风格化处理，得到风格化目标对象，所述风格化目标对象与所述风格化模板的风格相同。可以将所述风格化目标对象与所述风格化模板进行融合，得到风格化图像。根据本公开实施例提供的图像处理装置，不仅丰富了图像的处理方式，还缓解了由于目标对象的分割边缘效果不自然造成融合生硬的问题。
在一种可能的实现方式中，所述确定模块，还可以用于：
对所述待处理图像进行目标对象识别，得到所述待处理图像的目标对象识别结果，所述目标对象识别结果包括目标对象属性；
根据所述目标对象属性，确定用于对所述待处理图像进行风格化处理的风格化模板。
在一种可能的实现方式中，所述确定模块，还可以用于：
确定所述待处理图像与至少一个参考风格化模板的相似度，根据所述相似度从所述参考风格化模板中，确定用于对所述待处理图像进行风格化处理的风格化模板；或，
响应于针对参考风格化模板的选择操作，将选中的所述参考风格化模板确定为用于所述待处理图像进行风格化处理的风格化模板。
在一种可能的实现方式中，所述融合模块，还可以用于：
在所述风格化目标对象的尺寸满足尺寸调整条件的情况下，按照预置调整规则对所述目标对象进行调整，将调整后的风格化目标对象与所述风格化模板融合，得到风格化图像。
在一种可能的实现方式中，所述融合模块，还可以用于：
检测所述风格化模板中的模板对象的尺寸；
在所述风格化目标对象的尺寸与所述模板对象的尺寸不匹配的情况下，根据所述模板对象的尺寸调整所述风格化目标对象的尺寸。
在一种可能的实现方式中，所述融合模块，还可以用于：
根据所述风格化目标对象的尺寸，确定所述风格化目标对象在所述风格化模板中对应的位置；
在所述风格化模板中的所述位置处融合所述风格化目标对象，得到所述风格化图像。
在一种可能的实现方式中，所述装置还可以包括：
第二获取模块，用于向服务器发送所述模板图像，以使所述服务器对所述模板图像进行图像处理，得到参考风格化模板。
在一种可能的实现方式中，所述融合模块，还可以用于：
将所述风格化目标对象与所述风格化模板进行融合，得到初步风格化图像；
响应于针对所述初步风格化图像中风格化目标对象的调整操作，得到风格化图像，所述调整操作包括针对风格化目标对象的尺寸调整操作和/或位置调整操作。
在一些实施例中，本公开实施例提供的装置具有的功能或包含的模块可以用于执行 上文方法实施例描述的方法，其具体实现可以参照上文方法实施例的描述，为了简洁，这里不再赘述。
本公开实施例还提出一种计算机可读存储介质，其上存储有计算机程序指令，所述计算机程序指令被处理器执行时实现上述方法。计算机可读存储介质可以是非易失性计算机可读存储介质。
本公开实施例还提出一种电子设备，包括：处理器；用于存储处理器可执行指令的存储器；其中，所述处理器被配置为调用所述存储器存储的指令，以执行上述方法。
本公开实施例还提供了一种计算机程序产品，包括计算机可读代码，当计算机可读代码在设备上运行时，设备中的处理器执行用于实现如上任一实施例提供的图像处理方法的指令。
本公开实施例还提供了另一种计算机程序产品，用于存储计算机可读指令，指令被执行时使得计算机执行上述任一实施例提供的图像处理方法的操作。
电子设备可以被提供为终端、服务器或其它形态的设备。
图5示出根据本公开实施例的一种电子设备800的框图。例如，电子设备800可以是移动电话，计算机，数字广播终端，消息收发设备，游戏控制台，平板设备，医疗设备，健身设备，个人数字助理等终端。
参照图5，电子设备800可以包括以下一个或多个组件：处理组件802，存储器804，电源组件806，多媒体组件808，音频组件810，输入/输出(I/O)的接口812，传感器组件814，以及通信组件816。
处理组件802通常控制电子设备800的整体操作，诸如与显示，电话呼叫，数据通信，相机操作和记录操作相关联的操作。处理组件802可以包括一个或多个处理器820来执行指令，以完成上述的方法的全部或部分步骤。此外，处理组件802可以包括一个或多个模块，便于处理组件802和其他组件之间的交互。例如，处理组件802可以包括多媒体模块，以方便多媒体组件808和处理组件802之间的交互。
存储器804被配置为存储各种类型的数据以支持在电子设备800的操作。这些数据的示例包括用于在电子设备800上操作的任何应用程序或方法的指令，联系人数据，电话簿数据，消息，图片，视频等。存储器804可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器(SRAM)，电可擦除可编程只读存储器(EEPROM)，可擦除可编程只读存储器(EPROM)，可编程只读存储器(PROM)，只读存储器(ROM)，磁存储器，快闪存储器，磁盘或光盘。
电源组件806为电子设备800的各种组件提供电力。电源组件806可以包括电源管理系统，一个或多个电源，及其他与为电子设备800生成、管理和分配电力相关联的组件。
多媒体组件808包括在所述电子设备800和用户之间的提供一个输出接口的屏幕。在一些实施例中，屏幕可以包括液晶显示器(LCD)和触摸面板(TP)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。所述触摸传感器可以不仅感测触 摸或滑动动作的边界，而且还检测与所述触摸或滑动操作相关的持续时间和压力。在一些实施例中，多媒体组件808包括一个前置摄像头和/或后置摄像头。当电子设备800处于操作模式，如拍摄模式或视频模式时，前置摄像头和/或后置摄像头可以接收外部的多媒体数据。每个前置摄像头和后置摄像头可以是一个固定的光学透镜系统或具有焦距和光学变焦能力。
音频组件810被配置为输出和/或输入音频信号。例如，音频组件810包括一个麦克风(MIC)，当电子设备800处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器804或经由通信组件816发送。在一些实施例中，音频组件810还包括一个扬声器，用于输出音频信号。
I/O接口812为处理组件802和外围接口模块之间提供接口，上述外围接口模块可以是键盘，点击轮，按钮等。这些按钮可包括但不限于：主页按钮、音量按钮、启动按钮和锁定按钮。
传感器组件814包括一个或多个传感器，用于为电子设备800提供各个方面的状态评估。例如，传感器组件814可以检测到电子设备800的打开/关闭状态，组件的相对定位，例如所述组件为电子设备800的显示器和小键盘，传感器组件814还可以检测电子设备800或电子设备800一个组件的位置改变，用户与电子设备800接触的存在或不存在，电子设备800方位或加速/减速和电子设备800的温度变化。传感器组件814可以包括接近传感器，被配置用来在没有任何的物理接触时检测附近物体的存在。传感器组件814还可以包括光传感器，如互补金属氧化物半导体(CMOS)或电荷耦合装置(CCD)图像传感器，用于在成像应用中使用。在一些实施例中，该传感器组件814还可以包括加速度传感器，陀螺仪传感器，磁传感器，压力传感器或温度传感器。
通信组件816被配置为便于电子设备800和其他设备之间有线或无线方式的通信。电子设备800可以接入基于通信标准的无线网络，如无线网络(WiFi)，第二代移动通信技术(2G)或第三代移动通信技术(3G)，或它们的组合。在一个示例性实施例中，通信组件816经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，所述通信组件816还包括近场通信(NFC)模块，以促进短程通信。例如，在NFC模块可基于射频识别(RFID)技术，红外数据协会(IrDA)技术，超宽带(UWB)技术，蓝牙(BT)技术和其他技术来实现。
在示例性实施例中，电子设备800可以被一个或多个应用专用集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、控制器、微控制器、微处理器或其他电子元件实现，用于执行上述方法。
在示例性实施例中，还提供了一种非易失性计算机可读存储介质，例如包括计算机程序指令的存储器804，上述计算机程序指令可由电子设备800的处理器820执行以完成上述方法。
图6示出根据本公开实施例的一种电子设备1900的框图。例如，电子设备1900可以被提供为一服务器。参照图6，电子设备1900包括处理组件1922，其进一步包括一个或多个处理器，以及由存储器1932所代表的存储器资源，用于存储可由处理组件1922的执行的指令，例如应用程序。存储器1932中存储的应用程序可以包括一个或一个以上的每一个对应于一组指令的模块。此外，处理组件1922被配置为执行指令，以执行上述方法。
电子设备1900还可以包括一个电源组件1926被配置为执行电子设备1900的电源管理，一个有线或无线网络接口1950被配置为将电子设备1900连接到网络，和一个输入输出(I/O)接口1958。电子设备1900可以操作基于存储在存储器1932的操作系统，例如微软服务器操作系统(Windows Server TM)，苹果公司推出的基于图形用户界面操作系统(Mac OS X TM)，多用户多进程的计算机操作系统(Unix TM),自由和开放原代码的类Unix操作系统(Linux TM)，开放原代码的类Unix操作系统(FreeBSD TM)或类似。
在示例性实施例中，还提供了一种非易失性计算机可读存储介质，例如包括计算机程序指令的存储器1932，上述计算机程序指令可由电子设备1900的处理组件1922执行以完成上述方法。
本公开可以是系统、方法和/或计算机程序产品。计算机程序产品可以包括计算机可读存储介质，其上载有用于使处理器实现本公开的各个方面的计算机可读程序指令。
计算机可读存储介质可以是可以保持和存储由指令执行设备使用的指令的有形设备。计算机可读存储介质例如可以是――但不限于――电存储设备、磁存储设备、光存储设备、电磁存储设备、半导体存储设备或者上述的任意合适的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括：便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、静态随机存取存储器(SRAM)、便携式压缩盘只读存储器(CD-ROM)、数字多功能盘(DVD)、记忆棒、软盘、机械编码设备、例如其上存储有指令的打孔卡或凹槽内凸起结构、以及上述的任意合适的组合。这里所使用的计算机可读存储介质不被解释为瞬时信号本身，诸如无线电波或者其他自由传播的电磁波、通过波导或其他传输媒介传播的电磁波(例如，通过光纤电缆的光脉冲)、或者通过电线传输的电信号。
这里所描述的计算机可读程序指令可以从计算机可读存储介质下载到各个计算/处理设备，或者通过网络、例如因特网、局域网、广域网和/或无线网下载到外部计算机或外部存储设备。网络可以包括铜传输电缆、光纤传输、无线传输、路由器、防火墙、交换机、网关计算机和/或边缘服务器。每个计算/处理设备中的网络适配卡或者网络接口从网络接收计算机可读程序指令，并转发该计算机可读程序指令，以供存储在各个计算/处理设备中的计算机可读存储介质中。
用于执行本公开操作的计算机程序指令可以是汇编指令、指令集架构(ISA)指令、机器指令、机器相关指令、微代码、固件指令、状态设置数据、或者以一种或多种编程语言的任意组合编写的源代码或目标代码，所述编程语言包括面向对象的编程语言—诸如Smalltalk、C++等，以及常规的过程式编程语言—诸如“C”语言或类似的编程语言。 计算机可读程序指令可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络—包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。在一些实施例中，通过利用计算机可读程序指令的状态信息来个性化定制电子电路，例如可编程逻辑电路、现场可编程门阵列(FPGA)或可编程逻辑阵列(PLA)，该电子电路可以执行计算机可读程序指令，从而实现本公开的各个方面。
这里参照根据本公开实施例的方法、装置(系统)和计算机程序产品的流程图和/或框图描述了本公开的各个方面。应当理解，流程图和/或框图的每个方框以及流程图和/或框图中各方框的组合，都可以由计算机可读程序指令实现。
这些计算机可读程序指令可以提供给通用计算机、专用计算机或其它可编程数据处理装置的处理器，从而生产出一种机器，使得这些指令在通过计算机或其它可编程数据处理装置的处理器执行时，产生了实现流程图和/或框图中的一个或多个方框中规定的功能/动作的装置。也可以把这些计算机可读程序指令存储在计算机可读存储介质中，这些指令使得计算机、可编程数据处理装置和/或其他设备以特定方式工作，从而，存储有指令的计算机可读介质则包括一个制造品，其包括实现流程图和/或框图中的一个或多个方框中规定的功能/动作的各个方面的指令。
也可以把计算机可读程序指令加载到计算机、其它可编程数据处理装置、或其它设备上，使得在计算机、其它可编程数据处理装置或其它设备上执行一系列操作步骤，以产生计算机实现的过程，从而使得在计算机、其它可编程数据处理装置、或其它设备上执行的指令实现流程图和/或框图中的一个或多个方框中规定的功能/动作。
附图中的流程图和框图显示了根据本公开的多个实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或指令的一部分，所述模块、程序段或指令的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或动作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
该计算机程序产品可以具体通过硬件、软件或其结合的方式实现。在一个可选实施例中，所述计算机程序产品具体体现为计算机存储介质，在另一个可选实施例中，计算机程序产品具体体现为软件产品，例如软件开发包(Software Development Kit，SDK)等等。
以上已经描述了本公开的各实施例，上述说明是示例性的，并非穷尽性的，并且也不限于所披露的各实施例。在不偏离所说明的各实施例的范围和精神的情况下，对于本 技术领域的普通技术人员来说许多修改和变更都是显而易见的。本文中所用术语的选择，旨在最好地解释各实施例的原理、实际应用或对市场中的技术的改进，或者使本技术领域的其它普通技术人员能理解本文披露的各实施例。

Claims (13)

  1. 一种图像处理方法，其中，所述方法包括：
    获取待处理图像；
    确定用于对所述待处理图像进行风格化处理的风格化模板；
    根据所述风格化模板对所述待处理图像中的目标对象进行风格化处理，得到风格化目标对象，所述风格化目标对象与所述风格化模板的风格相同；
    将所述风格化目标对象与所述风格化模板进行融合，得到风格化图像。
  2. 根据权利要求1所述的方法，所述确定用于对所述待处理图像进行风格化处理的风格化模板，包括：
    对所述待处理图像进行目标对象识别，得到所述待处理图像的目标对象识别结果，所述目标对象识别结果包括目标对象属性；
    根据所述目标对象属性，确定用于对所述待处理图像进行风格化处理的风格化模板。
  3. 根据权利要求1所述的方法，所述确定用于对所述待处理图像进行风格化处理的风格化模板，包括：
    确定所述待处理图像与至少一个参考风格化模板的相似度，根据所述相似度从所述参考风格化模板中，确定用于对所述待处理图像进行风格化处理的风格化模板；或，
    响应于针对参考风格化模板的选择操作，将选中的所述参考风格化模板确定为用于所述待处理图像进行风格化处理的风格化模板。
  4. 根据权利要求1至3中任一项所述的方法，所述将所述风格化目标对象与所述风格化模板进行融合，得到风格化图像，包括：
    在所述风格化目标对象的尺寸满足尺寸调整条件的情况下，按照预置调整规则对所述目标对象进行调整，将调整后的风格化目标对象与所述风格化模板融合，得到风格化图像。
  5. 根据权利要求4所述的方法，所述在所述风格化目标对象的尺寸满足尺寸调整条件的情况下，按照预置调整规则对所述目标对象进行调整，包括：
    检测所述风格化模板中的模板对象的尺寸；
    在所述风格化目标对象的尺寸与所述模板对象的尺寸不匹配的情况下，根据所述模板对象的尺寸调整所述风格化目标对象的尺寸。
  6. 根据权利要求1至3中任一项所述的方法，所述将所述风格化目标对象与所述风格化模板进行融合，得到风格化图像，包括：
    根据所述风格化目标对象的尺寸，确定所述风格化目标对象在所述风格化模板中对应的位置；
    在所述风格化模板中的所述位置处融合所述风格化目标对象，得到所述风格化图像。
  7. 根据权利要求3所述的方法，所述方法还包括：
    获取模板图像；
    向服务器发送所述模板图像，以使所述服务器对所述模板图像进行图像处理，得到参考风格化模板。
  8. 根据权利要求1至7中任一项所述的方法，将所述风格化目标对象与所述风格化模板进行融合，得到风格化图像，包括：
    将所述风格化目标对象与所述风格化模板进行融合，得到初步风格化图像；
    响应于针对所述初步风格化图像中风格化目标对象的调整操作，得到风格化图像，所述调整操作包括针对风格化目标对象的尺寸调整操作和/或位置调整操作。
  9. 一种互动式展示装置，其中，所述互动式展示装置包括：图像处理模块和展示模块，所述图像处理模块包括图像采集单元和图像处理单元；其中，
    所述图像采集单元，用于采集待处理图像；
    所述图像处理单元，用于确定用于对所述待处理图像进行风格化处理的风格化模板，并根据所述风格化模板对所述待处理图像中的目标对象进行风格化处理，得到风格化目标对象，所述风格化目标对象与所述风格化模板的风格相同；
    所述图像处理单元，还用于将所述风格化目标对象与所述风格化模板进行融合，得到风格化图像；
    所述展示模块，用于展示所述风格化图像。
  10. 一种图像处理装置，所述装置包括：
    第一获取模块，用于获取待处理图像；
    确定模块，用于确定用于对所述待处理图像进行风格化处理的风格化模板；
    处理模块，用于根据所述风格化模板对所述待处理图像中的目标对象进行风格化处理，得到风格化目标对象，所述风格化目标对象与所述风格化模板的风格相同；
    融合模块，用于将所述风格化目标对象与所述风格化模板进行融合，得到风格化图像。
  11. 一种电子设备，包括：
    处理器；
    用于存储处理器可执行指令的存储器；
    其中，所述处理器被配置为调用所述存储器存储的指令，以执行权利要求1至8中任意一项所述的方法。
  12. 一种计算机可读存储介质，其上存储有计算机程序指令，所述计算机程序指令被处理器执行时实现权利要求1至8中任意一项所述的方法。
  13. 一种计算机程序产品，包括计算机可读代码，当所述计算机可读代码在电子设备中运行时，所述电子设备中的处理器执行用于实现权利要求1-8中任一项所述的方法。
PCT/CN2021/090249 2020-08-21 2021-04-27 图像处理方法及装置、互动式展示装置和电子设备 WO2022037111A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010850797.XA CN111986076A (zh) 2020-08-21 2020-08-21 图像处理方法及装置、互动式展示装置和电子设备
CN202010850797.X 2020-08-21

Publications (1)

Publication Number Publication Date
WO2022037111A1 true WO2022037111A1 (zh) 2022-02-24

Family

ID=73442432

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/090249 WO2022037111A1 (zh) 2020-08-21 2021-04-27 图像处理方法及装置、互动式展示装置和电子设备

Country Status (2)

Country Link
CN (1) CN111986076A (zh)
WO (1) WO2022037111A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117057981A (zh) * 2023-10-10 2023-11-14 广州方图科技有限公司 一种图像处理方法、装置、电子设备及存储介质
EP4276738A4 (en) * 2021-02-09 2023-11-29 Beijing Zitiao Network Technology Co., Ltd. IMAGE DISPLAY METHOD AND APPARATUS, DEVICE AND MEDIUM

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111986076A (zh) * 2020-08-21 2020-11-24 深圳市慧鲤科技有限公司 图像处理方法及装置、互动式展示装置和电子设备
CN112488085A (zh) * 2020-12-28 2021-03-12 深圳市慧鲤科技有限公司 人脸融合方法、装置、设备及存储介质
CN113160039B (zh) * 2021-04-28 2024-03-26 北京达佳互联信息技术有限公司 图像风格迁移方法、装置、电子设备及存储介质
CN114037599B (zh) * 2021-09-16 2022-08-30 福建大娱号信息科技股份有限公司 一种基于自然环境场景信息的智能抠像方法、装置以及存储介质
CN115145442A (zh) * 2022-06-07 2022-10-04 杭州海康汽车软件有限公司 一种环境图像的显示方法、装置、车载终端及存储介质
CN115272146B (zh) * 2022-07-27 2023-04-07 天翼爱音乐文化科技有限公司 一种风格化图像生成方法、系统、设备及介质
CN117315148A (zh) * 2023-09-26 2023-12-29 北京智象未来科技有限公司 三维物体风格化方法、装置、设备、存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108805803A (zh) * 2018-06-13 2018-11-13 衡阳师范学院 一种基于语义分割与深度卷积神经网络的肖像风格迁移方法
CN110310222A (zh) * 2019-06-20 2019-10-08 北京奇艺世纪科技有限公司 一种图像风格迁移方法、装置、电子设备及存储介质
CN110458918A (zh) * 2019-08-16 2019-11-15 北京百度网讯科技有限公司 用于输出信息的方法和装置
US10552977B1 (en) * 2017-04-18 2020-02-04 Twitter, Inc. Fast face-morphing using neural networks
CN111127378A (zh) * 2019-12-23 2020-05-08 Oppo广东移动通信有限公司 图像处理方法、装置、计算机设备及存储介质
CN111986076A (zh) * 2020-08-21 2020-11-24 深圳市慧鲤科技有限公司 图像处理方法及装置、互动式展示装置和电子设备

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105184249B (zh) * 2015-08-28 2017-07-18 百度在线网络技术（北京）有限公司 用于人脸图像处理的方法和装置
US10147459B2 (en) * 2016-09-22 2018-12-04 Apple Inc. Artistic style transfer for videos
CN111028137B (zh) * 2018-10-10 2023-08-15 Oppo广东移动通信有限公司 图像处理方法、装置、电子设备和计算机可读存储介质
CN109523460A (zh) * 2018-10-29 2019-03-26 北京达佳互联信息技术有限公司 图像风格的迁移方法、迁移装置和计算机可读存储介质
CN110189246B (zh) * 2019-05-15 2023-02-28 北京字节跳动网络技术有限公司 图像风格化生成方法、装置及电子设备

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10552977B1 (en) * 2017-04-18 2020-02-04 Twitter, Inc. Fast face-morphing using neural networks
CN108805803A (zh) * 2018-06-13 2018-11-13 衡阳师范学院 一种基于语义分割与深度卷积神经网络的肖像风格迁移方法
CN110310222A (zh) * 2019-06-20 2019-10-08 北京奇艺世纪科技有限公司 一种图像风格迁移方法、装置、电子设备及存储介质
CN110458918A (zh) * 2019-08-16 2019-11-15 北京百度网讯科技有限公司 用于输出信息的方法和装置
CN111127378A (zh) * 2019-12-23 2020-05-08 Oppo广东移动通信有限公司 图像处理方法、装置、计算机设备及存储介质
CN111986076A (zh) * 2020-08-21 2020-11-24 深圳市慧鲤科技有限公司 图像处理方法及装置、互动式展示装置和电子设备

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP4276738A4 (en) * 2021-02-09 2023-11-29 Beijing Zitiao Network Technology Co., Ltd. IMAGE DISPLAY METHOD AND APPARATUS, DEVICE AND MEDIUM
CN117057981A (zh) * 2023-10-10 2023-11-14 广州方图科技有限公司 一种图像处理方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
CN111986076A (zh) 2020-11-24

Similar Documents

Publication Publication Date Title
WO2022037111A1 (zh) 图像处理方法及装置、互动式展示装置和电子设备
US20220207805A1 (en) Adding time-based captions to captured video within a messaging system
WO2018098968A9 (zh) 一种拍照方法、装置及终端设备
US11924540B2 (en) Trimming video in association with multi-video clip capture
EP4272212A1 (en) Ar content for multi-video clip capture
EP4272208A1 (en) Selecting audio for multi-video clip capture
WO2023076236A1 (en) Method and system for creating animated custom stickers
CN110209316B (zh) 类别标签显示方法、装置、终端及存储介质
EP4272209A1 (en) Trimming video for multi-video clip capture
EP4272455A1 (en) Adding time-based captions to captured video
EP4272405A1 (en) Camera mode for capturing multiple video clips
WO2022146798A1 (en) Selecting audio for multi-video clip capture
US20220319059A1 (en) User-defined contextual spaces
US20220319125A1 (en) User-aligned spatial volumes
WO2023076252A1 (en) Customized animation from video
EP4314999A1 (en) User-defined contextual spaces
EP4272059A1 (en) Electronic communication interface with haptic feedback response
EP4272210A1 (en) Trimming video within a messaging system
US11825276B2 (en) Selector input device to transmit audio signals
US11922587B2 (en) Dynamic augmented reality experience
US20220319124A1 (en) Auto-filling virtual content
US20220210336A1 (en) Selector input device to transmit media content items
US20220206582A1 (en) Media content items with haptic feedback augmentations
US20220317773A1 (en) Real-time communication interface with haptic and audio feedback response
US20230394770A1 (en) Input modalities for ar wearable devices

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: 21857212

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21857212

Country of ref document: EP

Kind code of ref document: A1