WO2025007948A1 - 一种图像处理方法、装置、计算机设备及存储介质 - Google Patents
一种图像处理方法、装置、计算机设备及存储介质 Download PDFInfo
- Publication number
- WO2025007948A1 WO2025007948A1 PCT/CN2024/103785 CN2024103785W WO2025007948A1 WO 2025007948 A1 WO2025007948 A1 WO 2025007948A1 CN 2024103785 W CN2024103785 W CN 2024103785W WO 2025007948 A1 WO2025007948 A1 WO 2025007948A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- editing
- target
- instruction
- description information
- image
- Prior art date
- Legal status (The legal status 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 status listed.)
- Ceased
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/30—Creation or generation of source code
- G06F8/34—Graphical or visual programming
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0481—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
- G06F3/04845—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range for image manipulation, e.g. dragging, rotation, expansion or change of colour
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0487—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser
- G06F3/0488—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/30—Creation or generation of source code
- G06F8/38—Creation or generation of source code for implementing user interfaces
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
Definitions
- the present disclosure relates to an image processing method, an apparatus, a computer device and a storage medium.
- the embodiments of the present disclosure at least provide an image processing method, apparatus, computer equipment, and storage medium.
- an embodiment of the present disclosure provides an image processing method, including:
- the target editing instruction is executed to process the image to be processed to obtain a target image that conforms to the editing description information, wherein the target editing parameters corresponding to the target editing instruction are determined based on the user's historical editing operations.
- the target editing parameters include a target editing position and/or a target editing force.
- the method further includes determining a target editing parameter corresponding to each editing instruction according to the following method:
- the initial editing parameters are counted to determine the target editing parameters corresponding to the editing instruction.
- the method further includes determining a target editing parameter corresponding to the target editing instruction according to the following method:
- the method further includes determining the target editing instruction corresponding to the editing description information according to the following method:
- the editing instruction corresponding to the instruction identifier selected by the selection operation is used as the target editing instruction corresponding to the editing description information.
- the method further includes determining the target editing instruction corresponding to the editing description information according to the following method:
- the plurality of editing instructions are integrated based on the weight information to obtain the target editing instruction.
- the parsing of the edit description information to determine a target edit instruction corresponding to the edit description information among a plurality of preset edit instructions includes:
- the editing description information is input into a pre-trained instruction recognition network to determine a target editing instruction corresponding to the editing description information among a plurality of pre-set editing instructions.
- the editing description information is text information
- the parsing of the editing description information to determine a target editing instruction corresponding to the editing description information among the preset multiple editing instructions includes:
- a target editing instruction corresponding to the editing description information is determined among the preset multiple editing instructions.
- the present disclosure also provides an image processing device, including:
- a first acquisition module is configured to acquire an image to be processed input by a user
- a second acquisition module is configured to acquire edit description information set for the image to be processed
- a parsing module configured to parse the editing description information and determine at least one target editing instruction corresponding to the editing description information among a plurality of pre-set editing instructions
- An execution module is configured to execute the target editing instruction to process the image to be processed according to the target editing parameters corresponding to the target editing instruction to obtain a target image that conforms to the editing description information, wherein the target editing parameters corresponding to the target editing instruction are determined based on the user's historical editing operations.
- the target editing parameters include a target editing position and/or a target editing force.
- the execution module is further configured to determine the target editing parameter corresponding to each editing instruction according to the following method:
- the initial editing parameters are counted to determine the target editing parameters corresponding to the editing instruction.
- the execution module is further configured to determine the target editing parameter corresponding to the target editing instruction according to the following method:
- the parsing module is further configured to determine the target editing instruction corresponding to the editing description information according to the following method:
- the editing instruction corresponding to the instruction identifier selected by the selection operation is used as the target editing instruction corresponding to the editing description information.
- the parsing module is further configured to determine the target editing instruction corresponding to the editing description information according to the following method:
- the plurality of editing instructions are integrated based on the weight information to obtain the target editing instruction.
- the parsing module when parsing the edit description information to determine a target edit instruction corresponding to the edit description information among a plurality of preset edit instructions, is configured to:
- the editing description information is input into a pre-trained instruction recognition network to determine a target editing instruction corresponding to the editing description information among a plurality of pre-set editing instructions.
- the editing description information is text information
- the parsing module when parsing the edit description information and determining a target edit instruction corresponding to the edit description information among a plurality of preset edit instructions, is used to:
- a target editing instruction corresponding to the editing description information is determined among the preset multiple editing instructions.
- an embodiment of the present disclosure further provides a computer device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the above-mentioned first aspect, or any possible implementation of the first aspect are performed.
- an embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored.
- a computer program is stored.
- the steps of the above-mentioned first aspect or any possible implementation of the first aspect are executed.
- FIG1 shows a flow chart of an image processing method provided by an embodiment of the present disclosure
- FIG2a shows a schematic diagram of an interface for obtaining an image to be processed and editing description information in the image processing method provided by an embodiment of the present disclosure
- FIG2b shows a schematic diagram of an image editing interface in the image processing method used in an embodiment of the present disclosure
- FIG3 shows a schematic diagram of an image processing device provided by an embodiment of the present disclosure
- FIG4 shows a schematic diagram of the structure of a computer device provided in an embodiment of the present disclosure.
- AIGC artificial intelligence
- the present disclosure provides an image processing method, device, computer equipment and storage medium. After obtaining the image to be processed input by the user, after obtaining the image to be processed input by the user and the editing description information for the image to be processed, at least one target editing instruction corresponding to the editing description information can be automatically selected, and the corresponding target editing parameters can be selected for the target editing instruction in combination with the user's historical editing operations, and the target editing instruction is executed according to the target editing parameters.
- the corresponding editing instruction can be quickly selected for the user to improve the image editing speed; on the other hand, the target editing parameters of the target editing instruction are determined based on the user's historical editing operations, so that after the editing of the image to be processed is completed, the user's editing habits can be adapted to meet the user's editing needs.
- a and/or B may represent three situations: A exists alone, A and B exist at the same time, and B exists alone.
- at least one herein represents any combination of at least two of any one or more of a plurality of.
- including at least one of A, B, and C may represent including any one or more elements selected from the set consisting of A, B, and C.
- a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information.
- the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.
- the prompt information in response to receiving an active request from the user, may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form.
- the pop-up window may also carry a selection control for the user to choose "agree” or “disagree” to provide personal information to the electronic device.
- the execution subject of the image processing method provided in the embodiment of the present disclosure is generally a computer device with certain computing capabilities, and the computer device includes, for example: a terminal device or a server or other processing device.
- the terminal device can be a user equipment (User Equipment, UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (Personal Digital Assistant, PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc.
- the image processing method can be implemented by a processor calling a computer-readable instruction stored in a memory.
- FIG. 1 is a flowchart of an image processing method provided by an embodiment of the present disclosure, the method includes steps 101 to 104, wherein:
- Step 101 Obtain an image to be processed input by a user.
- Step 102 Obtain editing description information set for the image to be processed.
- Step 103 parse the editing description information to determine at least one target editing instruction corresponding to the editing description information among a plurality of pre-set editing instructions.
- Step 104 execute the target editing instruction to process the image to be processed according to the target editing parameters corresponding to the target editing instruction to obtain a target image that conforms to the editing description information, wherein the target editing parameters corresponding to the target editing instruction are determined based on the user's historical editing operations.
- the image to be processed may refer to an image to be beautified.
- the image to be processed may be an image containing an entity to be beautified.
- the entity to be beautified may be the user himself or any other entity object.
- the image to be processed may be a natural landscape or other non-natural scene. Contains images of a specific entity.
- the obtaining of the image to be processed input by the user may refer to receiving the image to be processed uploaded by the user, and the image to be processed may be stored locally on the user side; alternatively, the obtaining of the image to be processed input by the user may refer to obtaining the image to be processed taken by the user.
- the method provided in the present disclosure may be applied to an application, and the user may use the "take photo" button of the application to call the camera of the device to take the image to be processed.
- the process of obtaining the image to be processed may be obtained after authorization by the user.
- the specific authorization process is described above and will not be repeated here.
- step 102 For step 102,
- the editing description information set for the image to be processed may refer to information for indicating how to edit the image to be processed.
- the editing description information may be information for intuitively describing the editing effect, such as “increase the brightness of the photo", “remove the table”, etc.
- the editing description information may be information for indirectly describing the editing effect, such as “edit the person in the photo to look cooler", “edit the photo to look warmer”, etc.
- the editing description information may be information for describing the problems existing in the image to be processed, such as "the photo is too dark", "the face in the picture is unclear”, etc.
- the editing description information set for the image to be processed may refer to text information set for the image to be processed.
- a first text box may be displayed on the interface for uploading the information to be processed, and the user may enter the editing description information in the second text box.
- the editing description information may be obtained synchronously when the image to be processed is obtained.
- the exemplary interface may be shown in Figure 2a.
- the image to be processed after acquiring the image to be processed, can be displayed on an image editing interface, as well as a second text box for inputting the editing description information, wherein the second text box can be a text input or a voice input; the image editing interface can also display a manual editing area, and the user can perform manual editing by triggering the manual editing area.
- the user can combine the automatic editing and manual editing methods to edit the image to be processed.
- the image editing interface is shown in FIG2b.
- the editing instruction can be It can be a command to edit the entire image, such as a command to add blush, a command to enlarge eyes, a command to slim the face, etc.; or it can be a command to edit the entire image, such as a command to increase the brightness of the image, a command to increase the contrast of the image, etc.
- the target editing instruction may refer to at least one instruction selected from a plurality of pre-set editing instructions and used to achieve the image effect described by the editing description information, or at least one instruction used to solve the image problem indicated by the editing description information.
- the editing description information when parsing the editing description information and determining at least one target editing instruction corresponding to the editing description information among a plurality of pre-set editing instructions, can be input into a pre-trained instruction recognition network to determine the target editing instruction corresponding to the editing description information among a plurality of pre-set editing instructions.
- the instruction recognition network may be trained in a supervised manner.
- the specific training process may be: obtaining a sample text and an instruction label corresponding to the sample text, wherein the instruction label is used to indicate the type of instruction corresponding to the sample text; then inputting the sample text into the instruction recognition network to be trained to determine the corresponding predicted instruction; and then training the instruction recognition network to be trained based on the predicted instruction and the instruction label.
- the instruction recognition network can be a large language model (Large Language Models, LLM).
- LLM Large Language Models
- the editing description information is text information.
- the keywords contained in the editing description information can be extracted, and then based on the correspondence between the pre-set keywords and the editing instructions, the target editing instruction corresponding to the editing description information among the plurality of pre-set editing instructions can be determined.
- the target editing instruction may be a "skin smoothing instruction”; if the keyword contained in the editing description information is "make expression more lively”, the target editing instruction may be a "big eyes instruction”; if the editing description information is "look cooler”, the target editing instruction may be a combination of a "slim face instruction”, a “slim chin instruction”, a “thin eyes instruction”, and a “reduce image saturation instruction”.
- a user may add a text description to the edited image and publish it.
- the user's method of editing the image may be applied to other users.
- the user may perform multiple operations on the image, and the multiple operations performed by the user can be considered as the historical editing operations; the editing tags corresponding to the multiple historical editing operations can be determined by text descriptions associated with the image, such as the topic tags carried when the image is published.
- the editing tag corresponding to the image can be determined based on the text description associated with the image, and the editing operation in the editing process corresponding to the image can be stored in correspondence with the editing tag.
- the editing description information can be matched with the editing tag, and the instruction corresponding to the editing operation stored in correspondence with the successfully matched editing tag is used as the target editing instruction.
- the preset condition may exemplarily refer to that the heat value exceeds a preset value, or that the user performing the editing operation is a target user (such as a photo editing expert, etc.).
- the editing description information is "the person looks cool”
- the keywords "person” and “cool” can be extracted from the editing description information
- a certain editing tag is "cool beauty”
- the instruction corresponding to the editing operation stored corresponding to the editing tag can be used as the target editing instruction.
- the target editing instruction may also be determined in combination with the user's selection.
- instruction identifiers for example, instruction names
- the editing instruction corresponding to the instruction identifier selected by the selection operation can be used as the target editing instruction corresponding to the editing description information.
- the instruction identifiers of multiple editing instructions can be displayed to the user, and the operation of determining the target editing instruction can be left to the user to select.
- the multiple editing instructions determined based on the editing description information may refer to multiple editing instructions that can satisfy the editing description information individually, that is, any editing instruction can satisfy the editing description information.
- any editing instruction can satisfy the editing description information.
- the editing instruction “skin resurfacing” and the editing instruction “acne removal” can both achieve the image effect described by the editing description information. Therefore, in this case, the instruction identifier of the editing instruction can be displayed, and the user can select the target editing instruction.
- the target editing instruction may be determined in combination with the user's historical editing records.
- Step b1 Obtain the user's historical editing records.
- Step b2 Determine weight information corresponding to multiple editing instructions that satisfy the editing description information based on the historical editing records.
- Step b3 Integrate the multiple editing instructions based on the weight information to obtain the target editing instruction.
- obtaining the user's historical editing records may refer to obtaining the number of times the user executes each editing instruction; for a certain editing instruction, the more times the user uses it in the historical editing process, the image edited based on the editing instruction can better meet the user's needs.
- the ratio of the number of executions of each editing instruction may be used as the weight information.
- the weight information of editing instruction A is 90%, and the weight information of editing instruction B is 10%.
- each editing instruction may be weighted and superimposed according to the corresponding weight information.
- the target editing instruction is editing instruction A*90%+editing instruction B*10%.
- the above-mentioned editing instructions are weighted and superimposed according to the corresponding weight information, which is not equivalent to the target editing strength in the target editing parameters.
- its corresponding target editing strength is unique, and when a target editing instruction is obtained by superimposing multiple editing instructions, the target editing strengths of the superimposed multiple editing instructions are the same.
- the target editing command is editing command A*90%+editing command B*10%
- editing If the strength is 50%, the target editing instruction is executed according to editing instruction A*90%*50%+editing instruction B*10%*50%.
- step 104 For step 104,
- the target editing parameter may refer to a relevant parameter of the target editing instruction when editing the image to be processed.
- the target editing parameter may include a target editing position and/or a target editing strength.
- the target editing position may refer to the position when the target editing instruction is executed in the image to be processed.
- the target editing position does not refer to the specific area coordinates in the image to be processed, but refers to the type of position to be identified in the image to be processed, such as the cheek area, eyebrow area, etc.
- the target editing strength may refer to the degree of execution of the target editing instruction, for example, the target editing strength when fully executed may be 100%, and the target editing strength when half executed may be 50%.
- its target editing parameter may be set separately.
- its corresponding target editing parameter may include “color”
- its corresponding target editing parameter may include “eyebrow shape”, etc.
- the parameter types of the target editing parameters of different editing instructions may not be completely the same.
- the editing intensity is generally the default. For example, if the editing instruction is "increase image brightness”, the editing intensity is generally the default increase of N brightness values, where N is a preset positive integer; or, if the editing instruction is "add blush", the editing position is generally the cheek position.
- the present disclosure proposes to determine the target editing parameters corresponding to the target editing instruction based on the user's historical editing operations.
- Step a1 for any editing instruction, determine the initial editing parameters corresponding to the editing instruction input by the user when editing different images to be processed.
- Step a2 Count the initial editing parameters to determine the target editing parameters corresponding to the editing instruction.
- the initial editing parameters may be of the same category as the target editing parameters, including editing position and/or editing strength.
- different pictures may be edited with different editing parameters due to different shooting scenes.
- the adjustment force may be smaller when adjusting the image brightness; and if the shooting scene of the picture is dark, the adjustment force may be smaller when adjusting the image brightness.
- the editing parameters after editing can be counted. For example, for the editing instruction of image brightness, the brightness of the adjusted image can be counted, and for the editing instruction of face thinning, the size of the adjusted facial area under each depth information can be counted.
- different users may have different editing needs. If the image to be processed includes multiple users at the same time, different users have different editing needs.
- the target editing parameters are determined according to the historical editing operations of a certain user. Then, directly editing all users according to the target editing parameters may not meet the needs of all users.
- a face identifier corresponding to the user face among the users to be processed may be identified, and then a target editing parameter corresponding to the target editing instruction under the face identifier may be determined.
- the facial identification contained in the image when each editing operation is performed can be synchronously recorded, and then when determining the target editing parameters corresponding to the target editing instructions, the target editing parameters corresponding to the target editing instructions under each facial identification can be determined.
- the same target editing parameter of the target editing instruction may have multiple parameter values.
- the target editing instruction is "add blush”
- the target editing parameter of "target editing position” there may be multiple values.
- user A's blush needs to be added on the cheeks
- user B's blush needs to be added on the chin and the tip of the nose.
- the target editing parameter corresponding to the target editing instruction when determining the target editing parameter corresponding to the target editing instruction, if the target editing instruction includes a person editing instruction, the user's face in the image to be processed may be identified. The corresponding face identification is then determined, and the target editing parameters corresponding to the character editing instruction are determined under the face identification. For non-character editing instructions, they can be directly executed according to the preset target editing parameters, or according to the target editing parameters determined based on a certain user's historical editing operations.
- a certain target editing instruction may be revoked.
- the editing effect of the target editing instruction can be revoked.
- the editing description information is "I want to add lipstick to a person's face and whiten it"
- the corresponding target editing instruction is "lipstick” + “whitening”
- the user can also enter "I want to remove the lipstick I just added”, then the editing effect of the target editing instruction "lipstick” can be undone.
- the editing description information can be executed multiple times. For example, after the user inputs the editing description information, the corresponding target editing instruction can be determined based on the above method, and the image to be processed can be processed according to the corresponding target editing parameters. After the processing is completed, the user can also input other editing description information, and based on the image to be processed that was processed last time, execute the target editing instruction corresponding to the newly input editing description information, repeat multiple times, and the final generated image is the target image.
- At least one target editing instruction corresponding to the editing description information can be automatically selected, and the corresponding target editing parameters can be selected for the target editing instruction in combination with the user's historical editing operations, and the target editing instruction is executed according to the target editing parameters.
- the corresponding editing instruction can be quickly selected for the user to improve the image editing speed; on the other hand, the target editing parameters of the target editing instruction are determined based on the user's historical editing operations, so that after the editing of the image to be processed is completed, the user's editing habits can be adapted to meet the user's editing needs.
- an image processing device corresponding to the image processing method is also provided in the embodiment of the present disclosure. Since the principle of solving the problem by the device in the embodiment of the present disclosure is similar to the above-mentioned image processing method in the embodiment of the present disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.
- FIG. 3 is a schematic diagram of the architecture of an image processing device provided by an embodiment of the present disclosure, wherein the device comprises: a first acquisition module 301, a second acquisition module 302, a parsing module 303 and an execution module 304; wherein,
- the first acquisition module 301 is used to acquire an image to be processed input by a user
- the second acquisition module 302 is used to acquire the edit description information set for the image to be processed
- a parsing module 303 configured to parse the edit description information and determine at least one target edit instruction corresponding to the edit description information among a plurality of preset edit instructions;
- the execution module 304 is used to execute the target editing instruction to process the image to be processed according to the target editing parameters corresponding to the target editing instruction to obtain a target image that conforms to the editing description information, wherein the target editing parameters corresponding to the target editing instruction are determined based on the user's historical editing operations.
- the target editing parameters include a target editing position and/or a target editing force.
- the execution module 304 is further configured to determine the target editing parameter corresponding to each editing instruction according to the following method:
- the initial editing parameters are counted to determine the target editing parameters corresponding to the editing instruction.
- the execution module 304 is further configured to determine the target editing parameter corresponding to the target editing instruction according to the following method:
- the parsing module 303 is further configured to determine the editing instructions corresponding to the editing description information according to the following method:
- the editing instruction corresponding to the instruction identifier selected by the selection operation is used as the target editing instruction corresponding to the editing description information.
- the parsing module 303 is further configured to determine the target editing instruction corresponding to the editing description information according to the following method:
- the plurality of editing instructions are integrated based on the weight information to obtain the target editing instruction.
- the parsing module 303 when parsing the edit description information to determine a target edit instruction corresponding to the edit description information among the preset multiple edit instructions, is configured to:
- the editing description information is input into a pre-trained instruction recognition network to determine a target editing instruction corresponding to the editing description information among a plurality of pre-set editing instructions.
- the editing description information is text information
- the parsing module 303 when parsing the edit description information and determining a target edit instruction corresponding to the edit description information among the preset multiple edit instructions, is used to:
- a target editing instruction corresponding to the editing description information is determined among the preset multiple editing instructions.
- the embodiment of the present disclosure also provides a computer device.
- a schematic diagram of the structure of the computer device 400 provided in the embodiment of the present disclosure is shown.
- the computer device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and mobile devices such as digital TVs, desktop computers, etc.
- the computer device shown in FIG4 is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.
- the computer device 400 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes according to a program stored in a read-only storage device (ROM) 402 or a program loaded from a storage device 408 to a random access storage device (RAM) 403.
- ROM read-only storage
- RAM random access storage device
- Various programs and data required for the operation of the computer device 400 are also stored in the RAM 403.
- the processing device 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404.
- An input/output (I/O) interface 405 is also connected to the bus 404.
- the following devices may be connected to the I/O interface 405: input devices 406 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 408 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 409.
- the communication devices 409 may allow the computer device 400 to communicate wirelessly or wired with other devices to exchange data.
- FIG. 4 shows a computer device 400 with various devices, it should be understood that it is not required to implement or have all the devices shown. More or fewer devices may be implemented or have instead.
- an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing a method for recommending words.
- the computer program can be downloaded and installed from a network through a communication device 409, or installed from a storage device 408, or installed from a ROM 402.
- the processing device 401 the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.
- the present disclosure also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the steps of the image processing method described in the above method embodiment are executed.
- the storage medium can be a volatile or non-volatile computer-readable storage medium.
- the present disclosure also provides a computer program product that carries a program code.
- the program code includes instructions that can be used to execute the steps of the image processing method described in the above method embodiment. For details, please refer to the above method embodiment, which will not be repeated here.
- the computer program product may be implemented in hardware, software or a combination thereof.
- the computer program product is embodied as a computer storage medium.
- the computer program product is embodied as a software product, such as a software development kit (SDK).
- SDK software development kit
- the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
- each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
- the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor.
- the computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure.
- the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Processing Or Creating Images (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
本公开提供了一种图像处理方法、装置、计算机设备及存储介质,包括:获取用户输入的待处理图像;获取针对所述待处理图像设置的编辑描述信息;解析所述编辑描述信息,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的至少一条目标编辑指令;按照与所述目标编辑指令对应的目标编辑参数,执行所述目标编辑指令对所述待处理图像进行处理,得到符合所述编辑描述信息的目标图像,其中,所述目标编辑指令对应的目标编辑参数是基于所述用户的历史编辑操作确定的。通过这种方法,可以实现对于图像的快速编辑,且编辑后的图像能够满足用户需求。
Description
本申请要求于2023年7月5日递交的中国专利申请第202310822207.6号的优先权,在此全文引用上述中国专利申请公开的内容以作为本申请的一部分。
本公开涉及一种图像处理方法、装置、计算机设备及存储介质。
随着图像美化技术的发展,市面上出现了越来越多的图像美化软件,并且各个图像美化软件中有各种各样的美化功能,用户在使用图像美化软件进行图像美化处理时,需要先理解美化功能的作用,再选择合适的美化功能进行美化处理。然而,由于美化功能较多,并且同一美化功能在不同的美化软件中可能有不同的名称,因此用户可能无法快速地选择到合适的美化功能进行图像美化,图像处理速度较低。
发明内容
本公开实施例至少提供一种图像处理方法、装置、计算机设备及存储介质。
第一方面,本公开实施例提供了一种图像处理方法,包括:
获取用户输入的待处理图像;
获取针对所述待处理图像设置的编辑描述信息;
解析所述编辑描述信息,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的至少一条目标编辑指令;
按照与所述目标编辑指令对应的目标编辑参数,执行所述目标编辑指令对所述待处理图像进行处理,得到符合所述编辑描述信息的目标图像,其中,所述目标编辑指令对应的目标编辑参数是基于所述用户的历史编辑操作确定的。
一种可能的实施方式中,所述目标编辑参数包括目标编辑位置,和/或,目标编辑力度。
一种可能的实施方式中,所述方法还包括根据以下方法确定各编辑指令对应的目标编辑参数:
针对任一编辑指令,确定用户在编辑不同待处理图像时,输入的与该编辑指令对应的初始编辑参数;
对所述初始编辑参数进行统计,确定该编辑指令对应的目标编辑参数。
一种可能的实施方式中,在所述待处理图像中包含用户人脸的情况下,所述方法还包括根据以下方法确定所述目标编辑指令对应的目标编辑参数:
识别所述待处理图像中用户人脸对应的人脸标识;
确定在该人脸标识下,与所述目标编辑指令对应的目标编辑参数。
一种可能的实施方式中,在基于编辑描述信息确定的编辑指令有多条的情况下,所述方法还包括根据以下方法确定与该编辑描述信息对应的所述目标编辑指令:
展示用于满足该编辑描述信息的多条编辑指令的指令标识;
响应针对任一指令标识的选择操作,将该选择操作选择的指令标识对应的编辑指令作为与该编辑描述信息对应的目标编辑指令。
一种可能的实施方式中,在满足同一编辑描述信息的编辑指令有多条的情况下,所述方法还包括根据以下方法确定与该编辑描述信息对应的所述目标编辑指令:
获取用户的历史编辑记录;
基于所述历史编辑记录确定满足该编辑描述信息的多条编辑指令分别对应的权重信息;
基于所述权重信息对所述多条编辑指令进行整合,得到所述目标编辑指令。
一种可能的实施方式中,所述解析所述编辑描述信息,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的目标编辑指令,包括:
将所述编辑描述信息输入至预先训练的指令识别网络中,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的目标编辑指令。
一种可能的实施方式中,所述编辑描述信息为文本信息;
所述解析所述编辑描述信息,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的目标编辑指令,包括:
提取所述编辑描述信息中所包含的关键词;
基于预先设置的关键词与编辑指令的对应关系,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的目标编辑指令。
第二方面,本公开实施例还提供一种图像处理装置,包括:
第一获取模块,被配置为获取用户输入的待处理图像;
第二获取模块,被配置为获取针对所述待处理图像设置的编辑描述信息;
解析模块,被配置为解析所述编辑描述信息,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的至少一条目标编辑指令;
执行模块,被配置为按照与所述目标编辑指令对应的目标编辑参数,执行所述目标编辑指令对所述待处理图像进行处理,得到符合所述编辑描述信息的目标图像,其中,所述目标编辑指令对应的目标编辑参数是基于所述用户的历史编辑操作确定的。
一种可能的实施方式中,所述目标编辑参数包括目标编辑位置,和/或,目标编辑力度。
一种可能的实施方式中,所述执行模块,还被配置为根据以下方法确定各编辑指令对应的目标编辑参数:
针对任一编辑指令,确定用户在编辑不同待处理图像时,输入的与该编辑指令对应的初始编辑参数;
对所述初始编辑参数进行统计,确定该编辑指令对应的目标编辑参数。
一种可能的实施方式中,在所述待处理图像中包含用户人脸的情况下,所述执行模块,还被配置为根据以下方法确定所述目标编辑指令对应的目标编辑参数:
识别所述待处理图像中用户人脸对应的人脸标识;
确定在该人脸标识下,与所述目标编辑指令对应的目标编辑参数。
一种可能的实施方式中,在基于编辑描述信息确定的编辑指令有多条的情况下,所述解析模块,还被配置为根据以下方法确定与该编辑描述信息对应的所述目标编辑指令:
展示用于满足该编辑描述信息的多条编辑指令的指令标识;
响应针对任一指令标识的选择操作,将该选择操作选择的指令标识对应的编辑指令作为与该编辑描述信息对应的目标编辑指令。
一种可能的实施方式中,在满足同一编辑描述信息的编辑指令有多条的情况下,所述解析模块,还被配置为根据以下方法确定与该编辑描述信息对应的所述目标编辑指令:
获取用户的历史编辑记录;
基于所述历史编辑记录确定满足该编辑描述信息的多条编辑指令分别对应的权重信息;
基于所述权重信息对所述多条编辑指令进行整合,得到所述目标编辑指令。
一种可能的实施方式中,所述解析模块,在解析所述编辑描述信息,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的目标编辑指令时,用于:
将所述编辑描述信息输入至预先训练的指令识别网络中,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的目标编辑指令。
一种可能的实施方式中,所述编辑描述信息为文本信息;
所述解析模块,在解析所述编辑描述信息,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的目标编辑指令时,用于:
提取所述编辑描述信息中所包含的关键词;
基于预先设置的关键词与编辑指令的对应关系,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的目标编辑指令。
第三方面,本公开实施例还提供一种计算机设备,包括:处理器、存储器和总线,所述存储器存储有所述处理器可执行的机器可读指令,当计算机设备运行时,所述处理器与所述存储器之间通过总线通信,所述机器可读指令被所述处理器执行时执行上述第一方面,或第一方面中任一种可能的实施方式中的步骤。
第四方面,本公开实施例还提供一种计算机可读存储介质,该计算机可读存储介质上存储有计算机程序,该计算机程序被处理器运行时执行上述第一方面,或第一方面中任一种可能的实施方式中的步骤。
为了更清楚地说明本公开实施例的技术方案,下面将对实施例中所需要使用的附图作简单地介绍,此处的附图被并入说明书中并构成本说明书中的一部分,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。应当理解,以下附图仅示出了本公开的某些实施例,因此不应被看作是对范围的限定,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他相关的附图。
图1示出了本公开实施例所提供的一种图像处理方法的流程图;
图2a示出了本公开实施例所提供的图像处理方法中,获取待处理图像和编辑描述信息的界面示意图;
图2b示出了本公开实施例所体用的图像处理方法中,图像编辑界面的界面示意图;
图3示出了本公开实施例所提供的一种图像处理装置的示意图;
图4示出了本公开实施例所提供的计算机设备的结构示意图。
为使本公开实施例的目的、技术方案和优点更加清楚,下面将结合本公开实施例中附图,对本公开实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本公开一部分实施例,而不是全部的实施例。通常在此处附图中描述和示出的本公开实施例的组件可以以各种不同的配置来布置和设计。因此,以下对在附图中提供的本公开的实施例的详细描述并非旨在限制要求保护的本公开的范围,而是仅仅表示本公开的选定实施例。基于本公开的实施例,本领域技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例,都属于本公开保护的范围。
随着图像美化技术的发展,市面上出现了越来越多的图像美化软件,并且各个图像美化软件中有各种各样的美化功能,用户在使用图像美化软件进行图像美化处理时,需要先理解美化功能的作用,再选择合适的美化功能进行美化处理。然而,由于美化功能较多,并且同一美化功能在不同的美化软件中可能有不同的名称,因此用户可能无法快速地选择到合适的美化功能进行图像美化,图像处理速度较低。
然而,随着生成式人工智能(Artificial Intelligence Generated Content,AIGC)技术的发展,部分人开始采用AI绘图的方式来进行图像美化。例如,用户可能会输入编辑需求,然后神经网络可以生成满足用户编辑需求的图像。在这种方式应用于图像美化上时,由于在进行图像美化时,一般是按照固定的方式进行美化,或者生成的图像内容占比过大导致与原图区别较大,因此可能无法适配不同用户的美化习惯。
基于上述研究,本公开提供了一种图像处理方法、装置、计算机设备及存储介质中,在获取到用户输入的待处理图像之后,可以在获取到用户输入的待处理图像以及针对待处理图像的编辑描述信息之后,可以自动选择出与编辑描述信息对应的至少一条目标编辑指令,并且还可以结合用户的历史编辑操作,为目标编辑指令选择对应的目标编辑参数,并按照所述目标编辑参数执行所述目标编辑指令。通过这种方法,一方面可以为用户快速选择对应的编辑指令,提升图像编辑速度;另一方面,目标编辑指令的目标编辑参数是基于用户的历史编辑操作确定的,由此在对待处理图像编辑完成之后,可以适配用户的编辑习惯,满足用户的编辑需求。
应注意到:相似的标号和字母在下面的附图中表示类似项,因此,一旦某一项在一个附图中被定义,则在随后的附图中不需要对其进行进一步定义和解释。
本文中术语“和/或”,仅仅是描述一种关联关系,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。
可以理解的是,在使用本公开各实施例公开的技术方案之前,均应当依据相关法律法规通过恰当的方式对本公开所涉及个人信息的类型、使用范围、使用场景等告知用户并获得用户的授权。
例如,在响应于接收到用户的主动请求时,向用户发送提示信息,以明确地提示用户,其请求执行的操作将需要获取和使用到用户的个人信息。从而,使得用户可以根据提示信息来自主地选择是否向执行本公开技术方案的操作的电子设备、应用程序、服务器或存储介质等软件或硬件提供个人信息。
作为一种可选的但非限定性的实现方式,响应于接收到用户的主动请求,向用户发送提示信息的方式例如可以是弹窗的方式,弹窗中可以以文字的方式呈现提示信息。此外,弹窗中还可以承载供用户选择“同意”或者“不同意”向电子设备提供个人信息的选择控件。
可以理解的是,上述通知和获取用户授权过程仅是示意性的,不对本公开的实现方式构成限定,其它满足相关法律法规的方式也可应用于本公开的实现方式中。
为便于对本实施例进行理解,首先对本公开实施例所公开的一种图像处理方法进行详细介绍,本公开实施例所提供的图像处理方法的执行主体一般为具有一定计算能力的计算机设备,该计算机设备例如包括:终端设备或服务器或其它处理设备,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、个人数字助理(Personal Digital Assistant,PDA)、手持设备、计算设备、车载设备、可穿戴设备等。在一些可能的实现方式中,该图像处理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。
参见图1所示,为本公开实施例提供的一种图像处理方法的流程图,所述方法包括步骤101~步骤104,其中:
步骤101、获取用户输入的待处理图像。
步骤102、获取针对所述待处理图像设置的编辑描述信息。
步骤103、解析所述编辑描述信息,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的至少一条目标编辑指令。
步骤104、按照与所述目标编辑指令对应的目标编辑参数,执行所述目标编辑指令对所述待处理图像进行处理,得到符合所述编辑描述信息的目标图像,其中,所述目标编辑指令对应的目标编辑参数是基于所述用户的历史编辑操作确定的。
以下是对上述步骤的详细说明。
针对步骤101、
所述待处理图像可以是指待进行美化操作的图像,示例性的,所述待处理图像可以是包含待美化实体的图像,所述待美化实体可以是所述用户本人,或者可以是任何其他的实体对象;又或者,所述待处理图像可以是自然景观等不
包含特定实体的图像。
所述获取用户输入的待处理图像可以是指接收用户上传的待处理图像,所述待处理图像可以存储在用户端本地;又或者,所述获取用户输入的待处理图像可以是指,获取用户拍摄的待处理图像,例如本公开所提供的方法可以应用于某一应用程序,用户可以通过该应用程序的“拍照”按钮,调用设备的摄像头拍摄待处理图像。
这里,获取待处理图像的过程可以是经过用户授权后获取的,具体的授权过程参照上方描述,在此不再赘述。
针对步骤102、
所述针对所述待处理图像设置的编辑描述信息可以是指,用于指示如何对待处理图像进行编辑的信息,示例性的,所述编辑描述信息可以为用于直观的描述编辑效果的信息,例如可以是“提高照片亮度”、“将桌子去掉”等。或者,所述编辑描述信息可以是间接的描述编辑效果的信息,例如可以是“将照片上的人修的看上去清冷一些”、“将照片修的温暖一些”等。又或者,所述编辑描述信息可以是用于描述所述待处理图像中存在的问题信息,例如可以是“照片太暗了”、“图片里的人脸不清楚”等。
一种可能的实施方式中,所述针对所述待处理图像设置的编辑描述信息,可以是指针对所述待处理图像设置的文本信息,例如在上传所述待处理信息的界面可以展示有第一文本框,用户可以在第二文本框中输入所述编辑描述信息,这样可以在获取所述待处理图像时,同步获取所述编辑描述信息,示例性的所述界面可以如图2a所示。
或者,在另外一种可能的实施方式中,可以在获取所述待处理图像之后,在图像编辑界面可以展示所述待处理图像,以及展示输入所述编辑描述信息的第二文本框,所述第二文本框可以是文字输入,也可以是语音输入;所述图像编辑界面还可以展示有手动编辑区域,用户可以通过触发手动编辑区域进行手动编辑。
这样,用户可以同时结合自动编辑以及手动编辑的方法,对所述待处理图像进行编辑。示例性的,所述图像编辑界面如图2b所示。
针对步骤103、
不同的编辑指令用于实现不同的编辑效果,例如所述编辑指令可以是局
部进行编辑的指令,如添加腮红指令、大眼指令、瘦脸指令等;或者可以是对图像整体进行编辑的指令,如提高图片亮度指令、增加图像对比度指令等。
所述目标编辑指令,可以是指从预先设置的多种编辑指令中筛选出的,用于实现所述编辑描述信息是描述的图像效果的至少一条指令,或者,用于解决所述编辑描述信息所指示的图像问题的至少一条指令。
一种可能的实施方式中,在解析所述编辑描述信息,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的至少一条目标编辑指令时,可以将所述编辑描述信息输入至预先训练的指令识别网络中,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的目标编辑指令。
所述指令识别网络在训练时,可以是有监督的训练。示例性的,具体的训练过程可以为:获取样本文本,以及样本文本对应的指令标签,所述指令标签用于指示用于与所述样本文本对应的指令类型;然后将所述样本文本输入至待训练的指令识别网络中,确定对应的预测指令;再基于所述预测指令和所述指令标签对所述待训练的指令识别网络进行训练。
可选地,所述指令识别网络可以是大语言模型(Large Language Models,LLM)。
或者,在另外一种可能的实施方式中,所述编辑描述信息为文本信息,在解析所述编辑描述信息,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的至少一条目标编辑指令时,可以提取所述编辑描述信息中所包含的关键词,然后基于预先设置的关键词与编辑指令的对应关系,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的目标编辑指令。
示例性的,若所述编辑描述信息中所包含的关键词为“祛斑祛痘”,则所述目标编辑指令可以为“磨皮指令”;若所述编辑描述信息中所包含的关键词为“让神态更加灵动”,则所述目标编辑指令可以为“大眼指令”;若编辑描述信息为“看上去清冷一些”,则所述目标编辑指令可以为“瘦脸指令”、“瘦下巴指令”、“眼睛变细指令”、“图片饱和度降低指令”的组合。
在另外一种可能的实施方式中,在从预先设置的多种编辑指令中,确定与编辑描述信息对应的至少一条目标编辑指令时,还可以结合多个用户的历史编辑操作、与所述多个历史编辑操作对应的编辑标签以及所述编辑描述信息所包含的关键词。
示例性的,若某个用户在对图像进行编辑之后,可以为编辑后的图像添加文字说明进行发布,在这种情况下,用户对于图像的编辑操作的方法可以应用到其他用户。
具体的,用户在对图像进行编辑时,可能会对图像进行多项操作,用户执行的多项操作可以认为是所述历史编辑操作;所述多个历史编辑操作对应的编辑标签可以是通过与图像关联的文字说明确定的,例如可以是发布图像时携带的话题标签。
针对任一满足预设条件的编辑后的图像,可以先基于该图像关联的文字说明,确定该图像对应的编辑标签,并将该图像对应的编辑过程中的编辑操作与所述编辑标签对应存储。当任一用户输入编辑描述信息之后,可以将编辑描述信息与所述编辑标签进行匹配,并将匹配成功的编辑标签对应存储的编辑操作对应的指令作为所述目标编辑指令。
所述预设条件示例性的可以是指热度值超过预设值,或者执行编辑操作的用户为目标用户(如修图专家等)。
示例性的,若编辑描述信息为“人看上去清冷一些”,则可以从编辑描述信息中提取关键词“人”、“清冷”;若某一编辑标签为“清冷系美女”,则可以将与该编辑标签对应存储的编辑操作对应的指令作为所述目标编辑指令。
一种可能的实施方式中,在基于所述编辑描述信息确定的编辑指令有多条的情况下,还可以结合用户的选择来确定目标编辑指令。
具体的,在基于所述编辑描述信息确定的编辑指令有多条的情况下,可以展示用于满足该编辑描述信息的多条编辑指令的指令标识(例如可以是指令名称),然后响应针对任一指令标识的选择操作,将该选择操作选择的指令标识对应的编辑指令作为与该编辑描述信息对应的目标编辑指令。
这里,若基于编辑描述信息确定的编辑指令有多条,则可能是因为解析所述编辑描述信息出错导致的,因此,为了提升图像编辑效果,可以将多条编辑指令的指令标识展示给用户,将确定目标编辑指令的操作交由用户选择。
而在另外一种可能的实施方式中,这里所述基于所述编辑描述信息确定的编辑指令有多条,可以是指有多条编辑指令均可以单独满足所述编辑描述信息,即任一条编辑指令均可以满足所述编辑描述信息,在这种情况下,由于确定的多条编辑指令所能实现的图像效果是一样的,因此无需重复执行多条
编辑指令以实现相同的图像效果。
示例性的,若所述编辑描述信息为“祛除脸上的痘痘”,则编辑指令“磨皮”和编辑指令“祛痘”均能实现所述编辑描述信息所描述的图像效果,因此在这种情况下可以展示编辑指令的指令标识,通过用户选择目标编辑指令。
在另外一种可能的实施方式中,在满足同一编辑描述信息的编辑指令有多条的情况下,还可以结合用户的历史编辑记录确定目标编辑指令。
具体的,可以通过如下步骤:
步骤b1、获取用户的历史编辑记录。
步骤b2、基于所述历史编辑记录确定满足该编辑描述信息的多条编辑指令分别对应的权重信息。
步骤b3、基于所述权重信息对所述多条编辑指令进行整合,得到所述目标编辑指令。
这里,所述获取用户的历史编辑记录,可以是指获取用户对于各项编辑指令的执行次数;对于某一项编辑指令,若用户在历史编辑过程中使用次数越多,则基于该项编辑指令编辑的图像更能符合用户的需求。
可选地,在基于所述历史编辑记录确定满足该编辑描述信息的多条编辑指令分别对应的权重信息时,可以将各项编辑指令的执行次数的比值作为所述权重信息。
示例性的,若满足同一编辑描述信息的编辑指令分别为编辑指令A和编辑指令B,编辑指令A的历史编辑记录中的执行次数为90次,编辑指令B的历史编辑记录中的执行次数为10次,则编辑指令A的权重信息为90%,编辑指令B的权重信息为10%。
在基于所述权重信息对所述多条编辑指令进行整合时,可以是将各项编辑指令按照对应的权重信息进行加权叠加。延续上例,所述目标编辑指令即为编辑指令A*90%+编辑指令B*10%。
这里,需要说明的是,上述编辑指令按照对应的权重信息进行加权叠加,并不等同于所述目标编辑参数中的目标编辑力度。对于任一目标编辑指令而言,其对应的目标编辑力度是唯一的,而当某一目标编辑指令是由多个编辑指令叠加得到的情况下,叠加的所述多个编辑指令的目标编辑力度相同。
延续上例,若目标编辑指令为编辑指令A*90%+编辑指令B*10%,编辑
力度为50%,则所述目标编辑指令在执行时,是按照编辑指令A*90%*50%+编辑指令B*10%*50%执行的。
针对步骤104、
所述目标编辑参数可以是指所述目标编辑指令在对所述待处理图像进行编辑时的相关参数,示例性的,所述目标编辑参数可以包括目标编辑位置,和/或,目标编辑力度。
所述目标编辑位置可以是指,在所述待处理图像中执行所述目标编辑指令时的位置,这里,所述目标编辑位置并非是指所述待处理图像中具体的区域坐标,而是指所述待处理图像中待识别的位置类型,例如可以是脸颊区域、眉毛区域等;所述目标编辑力度可以是指,执行所述目标编辑指令时的程度,例如完全执行时的目标编辑力度可以是100%,执行一半时的目标编辑力度可以是50%。
在一种可能的实施方式中,对于特殊性的编辑指令,其目标编辑参数可以单独进行设置,示例性的,对于编辑指令“口红”,其对应的目标编辑参数可以包括“颜色”,对于编辑指令“眉毛”,其对应的目标编辑参数可以包括“眉形”等。不同的编辑指令的目标编辑参数的参数类型可以不完全相同。
在AIGC中,编辑力度一般是默认的,例如若编辑指令为“提高图像亮度”,编辑力度一般为默认的提高N个亮度值,N为预设正整数;又或者,编辑指令为“添加腮红”,编辑位置一般为脸颊位置。
然而不同用户对于图像编辑需求可能是不一样的,例如用户A在添加腮红时一般是在脸颊添加腮红,用户B在添加腮红时,一般是在下巴和鼻头添加腮红;若按照相同的目标编辑参数执行目标编辑指令,可能无法满足用户的个性化编辑需求。因此,基于此,本公开提出了,基于用户的历史编辑操作确定目标编辑指令对应的目标编辑参数。
一种可能的实施方式中,在确定各编辑指令对应的目标编辑参数时,可以通过如下步骤:
步骤a1、针对任一编辑指令,确定用户在编辑不同待处理图像时,输入的与该编辑指令对应的初始编辑参数。
步骤a2、对所述初始编辑参数进行统计,确定该编辑指令对应的目标编辑参数。
这里,所述初始编辑参数可以与所述目标编辑参数的类别相同,包括编辑位置,和/或,编辑力度。
可选地,由于不同的图片在进行编辑时,可能由于拍摄场景不同,而执行不同的编辑参数。示例性的,对于提升图像亮度这一编辑指令,若图片的拍摄场景较亮,则在调整图像亮度时,调整的力度可能较小;而若图片的拍摄场景较暗,则在调整图像亮度时,调整的力度可能较小。
因此,在确定各编辑指令对应的目标编辑参数时,可以对编辑完成后的编辑参数进行统计。示例性的,对于图像亮度这一编辑指令,可以统计调整后的图像的亮度,对于瘦脸这一编辑指令,可以统计各深度信息下,调整后的面部区域的大小等。
一种可能的场景中,不同的用户的编辑需求可能不同,若待处理图像中同时包括多个用户,不同的用户有不同的编辑需求,目标编辑参数是按照某一个用户的历史编辑操作确定的,则直接按照该目标编辑参数对所有用户都进行编辑可能无法满足所有用户的需求。
因此,一种可能的实施方式中,可以识别待处理用户中用户人脸对应的人脸标识,然后确定在该人脸标识下,与所述目标编辑指令对应的目标编辑参数。
这里,在按照上述方法确定各编辑操作的目标编辑参数时,可以同步记录各编辑操作执行时,图像中所包含的人脸标识,然后在确定与目标编辑指令对应的目标编辑参数时,可以确定在各人脸标识下的目标编辑指令对应的目标编辑参数。
相应的,在所述待处理图像中包括多个用户人脸时,所述目标编辑指令的同一目标编辑参数可能有多个参数值,例如若目标编辑指令为“添加腮红”,则对于“目标编辑位置”这一目标编辑参数,可能有多个取值,例如用户A的腮红需要添加在脸颊,用户B的腮红需要添加在下巴和鼻头。
需要说明的是,上述需要对人脸标识进行区分,是因为不同的用户人脸在进行编辑时有不同的需求,而对于图像亮度、图像对比度等这种需要整体调整图像的编辑指令,可以按照某一个用户的目标编辑参数进行编辑。
又或者,在确定所述目标编辑指令对应的目标编辑参数时,在所述目标编辑指令包括人物编辑指令的情况下,可以再识别所述待处理图像中用户人脸
对应的人脸标识,然后在确定在该人脸标识下,与所述人物编辑指令对应的目标编辑参数,对于非人物编辑指令,可以直接按照预设的目标编辑参数,或者按照基于某一个用户的历史编辑操作确定的目标编辑参数执行。
在另外一种可能的实施方式中,当与所述编辑描述信息对应的目标编辑指令有多条的情况下,在执行多条目标编辑指令对待处理图像进行处理之后,还可以对某一目标编辑指令进行撤销。
具体的,可以在执行多条目标编辑指令之后,响应于用户再次输入的编辑描述信息,在确定再次输入的编辑描述信息对应的目标编辑指令为上一次执行的任一目标编辑指令,且再次输入的编辑描述信息中包含否定词的情况下,可以撤销该目标编辑指令的编辑效果。
示例性的,若编辑描述信息为“我想给人脸加个口红,并美白一下”,则其对应的目标编辑指令为“口红”+“美白”;而在执行目标编辑指令之后,用户还可以输入“我想去掉刚加的口红”,则可以撤销对于“口红”这一目标编辑指令的编辑效果。
一种可能的实施方式中,所述编辑描述信息可以执行多次,示例性的,若用户在输入编辑描述信息之后,可以基于上述方法确定对应的目标编辑指令,以及按照对应的目标编辑参数对所述待处理图像进行处理,在处理完成之后,用户还可以输入其他的编辑描述信息,并在上一次处理完成的待处理图像的基础上,再去执行新输入的编辑描述信息对应的目标编辑指令,重复多次,最终生成的图像为所述目标图像。
上述方法中,在获取到用户输入的待处理图像之后,可以在获取到用户输入的待处理图像以及针对待处理图像的编辑描述信息之后,可以自动选择出与编辑描述信息对应的至少一条目标编辑指令,并且还可以结合用户的历史编辑操作,为目标编辑指令选择对应的目标编辑参数,并按照所述目标编辑参数执行所述目标编辑指令。通过这种方法,一方面可以为用户快速选择对应的编辑指令,提升图像编辑速度;另一方面,目标编辑指令的目标编辑参数是基于用户的历史编辑操作确定的,由此在对待处理图像编辑完成之后,可以适配用户的编辑习惯,满足用户的编辑需求。
本领域技术人员可以理解,在具体实施方式的上述方法中,各步骤的撰写顺序并不意味着严格的执行顺序而对实施过程构成任何限定,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。
基于同一发明构思,本公开实施例中还提供了与图像处理方法对应的图像处理装置,由于本公开实施例中的装置解决问题的原理与本公开实施例上述图像处理方法相似,因此装置的实施可以参见方法的实施,重复之处不再赘述。
参照图3所示,为本公开实施例提供的一种图像处理装置的架构示意图,所述装置包括:第一获取模块301、第二获取模块302、解析模块303以及执行模块304;其中,
第一获取模块301,用于获取用户输入的待处理图像;
第二获取模块302,用于获取针对所述待处理图像设置的编辑描述信息;
解析模块303,用于解析所述编辑描述信息,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的至少一条目标编辑指令;
执行模块304,用于按照与所述目标编辑指令对应的目标编辑参数,执行所述目标编辑指令对所述待处理图像进行处理,得到符合所述编辑描述信息的目标图像,其中,所述目标编辑指令对应的目标编辑参数是基于所述用户的历史编辑操作确定的。
一种可能的实施方式中,所述目标编辑参数包括目标编辑位置,和/或,目标编辑力度。
一种可能的实施方式中,所述执行模块304,还用于根据以下方法确定各编辑指令对应的目标编辑参数:
针对任一编辑指令,确定用户在编辑不同待处理图像时,输入的与该编辑指令对应的初始编辑参数;
对所述初始编辑参数进行统计,确定该编辑指令对应的目标编辑参数。
一种可能的实施方式中,在所述待处理图像中包含用户人脸的情况下,所述执行模块304,还用于根据以下方法确定所述目标编辑指令对应的目标编辑参数:
识别所述待处理图像中用户人脸对应的人脸标识;
确定在该人脸标识下,与所述目标编辑指令对应的目标编辑参数。
一种可能的实施方式中,在基于编辑描述信息确定的编辑指令有多条的情况下,所述解析模块303,还用于根据以下方法确定与该编辑描述信息对应
的所述目标编辑指令:
展示用于满足该编辑描述信息的多条编辑指令的指令标识;
响应针对任一指令标识的选择操作,将该选择操作选择的指令标识对应的编辑指令作为与该编辑描述信息对应的目标编辑指令。
一种可能的实施方式中,在满足同一编辑描述信息的编辑指令有多条的情况下,所述解析模块303,还用于根据以下方法确定与该编辑描述信息对应的所述目标编辑指令:
获取用户的历史编辑记录;
基于所述历史编辑记录确定满足该编辑描述信息的多条编辑指令分别对应的权重信息;
基于所述权重信息对所述多条编辑指令进行整合,得到所述目标编辑指令。
一种可能的实施方式中,所述解析模块303,在解析所述编辑描述信息,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的目标编辑指令时,用于:
将所述编辑描述信息输入至预先训练的指令识别网络中,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的目标编辑指令。
一种可能的实施方式中,所述编辑描述信息为文本信息;
所述解析模块303,在解析所述编辑描述信息,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的目标编辑指令时,用于:
提取所述编辑描述信息中所包含的关键词;
基于预先设置的关键词与编辑指令的对应关系,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的目标编辑指令。
关于装置中的各模块的处理流程、以及各模块之间的交互流程的描述可以参照上述方法实施例中的相关说明,这里不再详述。
基于同一技术构思,本公开实施例还提供了一种计算机设备。参照图4所示,为本公开实施例提供的计算机设备400的结构示意图。本公开实施例中的计算机设备可以包括但不限于诸如移动电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字TV、台式计算机等等
的固定终端,或者各种形式的服务器,如独立服务器或者服务器集群。图4示出的计算机设备仅仅是一个示例,不应对本公开实施例的功能和使用范围带来任何限制。
如图4所示,计算机设备400可以包括处理装置(例如中央处理器、图形处理器等)401,其可以根据存储在只读存储装置(ROM)402中的程序或者从存储装置408加载到随机访问存储装置(RAM)403中的程序而执行各种适当的动作和处理。在RAM 403中,还存储有计算机设备400操作所需的各种程序和数据。处理装置401、ROM 402以及RAM 403通过总线404彼此相连。输入/输出(I/O)接口405也连接至总线404。
通常,以下装置可以连接至I/O接口405:包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置406;包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置407;包括例如磁带、硬盘等的存储装置408;以及通信装置409。通信装置409可以允许计算机设备400与其他设备进行无线或有线通信以交换数据。虽然图4示出了具有各种装置的计算机设备400,但是应理解的是,并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。
特别地,根据本公开的实施例,上文参考流程图描述的过程可以被实现为计算机软件程序。例如,本公开的实施例包括一种计算机程序产品,其包括承载在计算机可读介质上的计算机程序,该计算机程序包含用于执行词语的推荐方法的程序代码。在这样的实施例中,该计算机程序可以通过通信装置409从网络上被下载和安装,或者从存储装置408被安装,或者从ROM 402被安装。在该计算机程序被处理装置401执行时,执行本公开实施例的方法中限定的上述功能。
本公开实施例还提供一种计算机可读存储介质,该计算机可读存储介质上存储有计算机程序,该计算机程序被处理器运行时执行上述方法实施例中所述的图像处理方法的步骤。其中,该存储介质可以是易失性或非易失的计算机可读取存储介质。
本公开实施例还提供一种计算机程序产品,该计算机产品承载有程序代码,所述程序代码包括的指令可用于执行上述方法实施例中所述的图像处理方法的步骤,具体可参见上述方法实施例,在此不再赘述。
其中,上述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。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的系统和装置的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。在本公开所提供的几个实施例中,应该理解到,所揭露的系统、装置和方法,可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,又例如,多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些通信接口,装置或单元的间接耦合或通信连接,可以是电性,机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外,在本公开各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个处理器可执行的非易失的计算机可读取存储介质中。基于这样的理解,本公开的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行本公开各个实施例所述方法的全部或部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是:以上所述实施例,仅为本公开的具体实施方式,用以说
明本公开的技术方案,而非对其限制,本公开的保护范围并不局限于此,尽管参照前述实施例对本公开进行了详细的说明,本领域的普通技术人员应当理解:任何熟悉本技术领域的技术人员在本公开揭露的技术范围内,其依然可以对前述实施例所记载的技术方案进行修改或可轻易想到变化,或者对其中部分技术特征进行等同替换;而这些修改、变化或者替换,并不使相应技术方案的本质脱离本公开实施例技术方案的精神和范围,都应涵盖在本公开的保护范围之内。因此,本公开的保护范围应所述以权利要求的保护范围为准。
Claims (11)
- 一种图像处理方法,包括:获取用户输入的待处理图像;获取针对所述待处理图像设置的编辑描述信息;解析所述编辑描述信息,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的至少一条目标编辑指令;按照与所述目标编辑指令对应的目标编辑参数,执行所述目标编辑指令对所述待处理图像进行处理,得到符合所述编辑描述信息的目标图像,其中,所述目标编辑指令对应的目标编辑参数是基于所述用户的历史编辑操作确定的。
- 根据权利要求1所述的方法,其中,所述目标编辑参数包括目标编辑位置,和/或,目标编辑力度。
- 根据权利要求1或2所述的方法,还包括根据以下方法确定各编辑指令对应的目标编辑参数:针对任一编辑指令,确定用户在编辑不同待处理图像时,输入的与该编辑指令对应的初始编辑参数;对所述初始编辑参数进行统计,确定该编辑指令对应的目标编辑参数。
- 根据权利要求3所述的方法,其中,在所述待处理图像中包含用户人脸的情况下,所述方法还包括根据以下方法确定所述目标编辑指令对应的目标编辑参数:识别所述待处理图像中用户人脸对应的人脸标识;确定在该人脸标识下,与所述目标编辑指令对应的目标编辑参数。
- 根据权利要求1所述的方法,其中,在基于编辑描述信息确定的编辑指令有多条的情况下,所述方法还包括根据以下方法确定与该编辑描述信息对应的所述目标编辑指令:展示用于满足该编辑描述信息的多条编辑指令的指令标识;响应针对任一指令标识的选择操作,将该选择操作选择的指令标识对应的编辑指令作为与该编辑描述信息对应的目标编辑指令。
- 根据权利要求1所述的方法,其中,在满足同一编辑描述信息的编辑 指令有多条的情况下,所述方法还包括根据以下方法确定与该编辑描述信息对应的所述目标编辑指令:获取用户的历史编辑记录;基于所述历史编辑记录确定满足该编辑描述信息的多条编辑指令分别对应的权重信息;基于所述权重信息对所述多条编辑指令进行整合,得到所述目标编辑指令。
- 根据权利要求1所述的方法,其中,所述解析所述编辑描述信息,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的目标编辑指令,包括:将所述编辑描述信息输入至预先训练的指令识别网络中,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的目标编辑指令。
- 根据权利要求1所述的方法,其中,所述编辑描述信息为文本信息;所述解析所述编辑描述信息,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的目标编辑指令,包括:提取所述编辑描述信息中所包含的关键词;基于预先设置的关键词与编辑指令的对应关系,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的目标编辑指令。
- 一种图像处理装置,包括:第一获取模块,被配置为获取用户输入的待处理图像;第二获取模块,被配置为获取针对所述待处理图像设置的编辑描述信息;解析模块,被配置为解析所述编辑描述信息,确定预先设置的多种编辑指令中,与所述编辑描述信息对应的至少一条目标编辑指令;执行模块,被配置为按照与所述目标编辑指令对应的目标编辑参数,执行所述目标编辑指令对所述待处理图像进行处理,得到符合所述编辑描述信息的目标图像,其中,所述目标编辑指令对应的目标编辑参数是基于所述用户的历史编辑操作确定的。
- 一种计算机设备,包括:处理器、存储器和总线,其中,所述存储器存储有所述处理器可执行的机器可读指令,当计算机设备运行时,所述处理器与所述存储器之间通过总线通信,所述机器可读指令被所述处理器执行时执 行如权利要求1至8任一项所述的图像处理方法的步骤。
- 一种计算机可读存储介质,其中,该计算机可读存储介质上存储有计算机程序,该计算机程序被处理器运行时执行如权利要求1至8任一项所述的图像处理方法的步骤。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310822207.6A CN119311258A (zh) | 2023-07-05 | 2023-07-05 | 一种图像处理方法、装置、计算机设备及存储介质 |
| CN202310822207.6 | 2023-07-05 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2025007948A1 true WO2025007948A1 (zh) | 2025-01-09 |
Family
ID=94171251
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2024/103785 Ceased WO2025007948A1 (zh) | 2023-07-05 | 2024-07-05 | 一种图像处理方法、装置、计算机设备及存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN119311258A (zh) |
| WO (1) | WO2025007948A1 (zh) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107798652A (zh) * | 2017-10-31 | 2018-03-13 | 广东欧珀移动通信有限公司 | 图像处理方法、装置、可读存储介质和电子设备 |
| CN107862654A (zh) * | 2017-11-30 | 2018-03-30 | 广东欧珀移动通信有限公司 | 图像处理方法、装置、计算机可读存储介质和电子设备 |
| CN107995415A (zh) * | 2017-11-09 | 2018-05-04 | 深圳市金立通信设备有限公司 | 一种图像处理方法、终端及计算机可读介质 |
| CN109255761A (zh) * | 2018-08-23 | 2019-01-22 | 北京金山安全软件有限公司 | 一种图像处理方法、装置及电子设备 |
| US20200319756A1 (en) * | 2019-04-04 | 2020-10-08 | Canon Kabushiki Kaisha | Image processing apparatus, method therefor, and storage medium storing program |
| CN112785488A (zh) * | 2019-11-11 | 2021-05-11 | 宇龙计算机通信科技(深圳)有限公司 | 一种图像处理方法、装置、存储介质及终端 |
| CN115311128A (zh) * | 2022-06-21 | 2022-11-08 | 网易(杭州)网络有限公司 | 一种图像处理方法及相关设备 |
-
2023
- 2023-07-05 CN CN202310822207.6A patent/CN119311258A/zh active Pending
-
2024
- 2024-07-05 WO PCT/CN2024/103785 patent/WO2025007948A1/zh not_active Ceased
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107798652A (zh) * | 2017-10-31 | 2018-03-13 | 广东欧珀移动通信有限公司 | 图像处理方法、装置、可读存储介质和电子设备 |
| CN107995415A (zh) * | 2017-11-09 | 2018-05-04 | 深圳市金立通信设备有限公司 | 一种图像处理方法、终端及计算机可读介质 |
| CN107862654A (zh) * | 2017-11-30 | 2018-03-30 | 广东欧珀移动通信有限公司 | 图像处理方法、装置、计算机可读存储介质和电子设备 |
| CN109255761A (zh) * | 2018-08-23 | 2019-01-22 | 北京金山安全软件有限公司 | 一种图像处理方法、装置及电子设备 |
| US20200319756A1 (en) * | 2019-04-04 | 2020-10-08 | Canon Kabushiki Kaisha | Image processing apparatus, method therefor, and storage medium storing program |
| CN112785488A (zh) * | 2019-11-11 | 2021-05-11 | 宇龙计算机通信科技(深圳)有限公司 | 一种图像处理方法、装置、存储介质及终端 |
| CN115311128A (zh) * | 2022-06-21 | 2022-11-08 | 网易(杭州)网络有限公司 | 一种图像处理方法及相关设备 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119311258A (zh) | 2025-01-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12425716B2 (en) | Content capture with audio input feedback | |
| US12063321B2 (en) | Modular camera interface with context-based display elements utilizing first and second lens | |
| CN114787813A (zh) | 上下文敏感化身字幕 | |
| JP2019145108A (ja) | 顔に対応する3次元アバターを用いて顔の動きが反映された3dアバターを含むイメージを生成する電子装置 | |
| US11445148B1 (en) | Video teleconference curated user profile picture | |
| CN110148191A (zh) | 视频虚拟表情生成方法、装置及计算机可读存储介质 | |
| WO2019233256A1 (zh) | 人脸贴图生成方法、装置、可读存储介质及移动终端 | |
| CN114630057B (zh) | 确定特效视频的方法、装置、电子设备及存储介质 | |
| JP2022518520A (ja) | 画像変形の制御方法、装置およびハードウェア装置 | |
| CN110298326A (zh) | 一种图像处理方法及装置、存储介质与终端 | |
| WO2025067533A1 (zh) | 一种文字处理方法、装置、计算机设备、存储介质及计算机程序产品 | |
| CN119723240A (zh) | 图像数据集生成方法、装置、设备及计算机可读存储介质 | |
| CN117786154A (zh) | 图像生成方法、系统、装置及存储介质 | |
| WO2025036359A1 (zh) | 图像处理方法、装置、计算机设备及存储介质 | |
| CN108810401A (zh) | 引导拍照的方法及系统 | |
| WO2025007948A1 (zh) | 一种图像处理方法、装置、计算机设备及存储介质 | |
| CN112488650A (zh) | 会议气氛调节方法、电子设备及相关产品 | |
| CN118632087A (zh) | 多媒体资源生成方法、装置、电子设备及存储介质 | |
| CN112149599A (zh) | 表情追踪方法、装置、存储介质和电子设备 | |
| WO2024245248A1 (zh) | 虚拟形象生成方法及相关设备 | |
| CN118152617A (zh) | 为文本配置图像的方法、装置、电子设备及存储介质 | |
| CN113486730A (zh) | 一种基于人脸识别的智能提醒方法及相关装置 | |
| CN117112087B (zh) | 一种桌面卡片的排序方法、电子设备以及介质 | |
| CN111462279A (zh) | 图像显示方法、装置、设备及可读存储介质 | |
| JP2026062126A (ja) | システム |
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: 24835426 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |