WO2020037676A1 - 三维人脸图像生成方法、装置及电子设备 - Google Patents

三维人脸图像生成方法、装置及电子设备 Download PDF

Info

Publication number
WO2020037676A1
WO2020037676A1 PCT/CN2018/102329 CN2018102329W WO2020037676A1 WO 2020037676 A1 WO2020037676 A1 WO 2020037676A1 CN 2018102329 W CN2018102329 W CN 2018102329W WO 2020037676 A1 WO2020037676 A1 WO 2020037676A1
Authority
WO
WIPO (PCT)
Prior art keywords
face
dimensional
information
feature point
convolutional neural
Prior art date
Application number
PCT/CN2018/102329
Other languages
English (en)
French (fr)
Inventor
李建亿
朱利明
Original Assignee
太平洋未来科技（深圳）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 太平洋未来科技（深圳）有限公司 filed Critical 太平洋未来科技（深圳）有限公司
Priority to PCT/CN2018/102329 priority Critical patent/WO2020037676A1/zh
Priority to CN201811020071.2A priority patent/CN109255827A/zh
Publication of WO2020037676A1 publication Critical patent/WO2020037676A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T15/00—3D [Three Dimensional] image rendering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06V40/172—Classification, e.g. identification

Definitions

  • the present invention relates to the technical field of three-dimensional face image generation, and in particular, to a method, an apparatus, and an electronic device for generating a three-dimensional face image.
  • Three-dimensional face reconstruction has been widely used in medical, education, and entertainment fields.
  • the inventors found that in the process of three-dimensional face reconstruction, a three-dimensional model was assembled using multiple images and multiple angles.
  • the reconstruction process is cumbersome and complicated, and it is necessary to use multiple images.
  • the dense correspondence between pixels is established in the range facial pose image, which results in a large difference in the 3D simulation of the same individual, and at the same time leads to a long reconstruction time and high cost.
  • portable electronic devices such as mobile phones are increasingly using three-dimensional face reconstruction technology for entertainment purposes.
  • Two-dimensional face images are mainly obtained through the camera of the electronic device, and the reconstruction effect of the three-dimensional face images in the later period depends in part on the previous camera.
  • the device obtains the quality of the image, and the quality of the obtained image depends in part on the processing effect of the shake when shooting.
  • the current mobile phones mainly perform anti-shake processing through software, and the hardware has not been targeted for improvement.
  • a method, an apparatus, and an electronic device for generating a three-dimensional face image according to the embodiments of the present invention are used to solve at least the foregoing problems in related technologies.
  • One aspect of the embodiments of the present invention provides a method for generating a three-dimensional face image, including: identifying a face in an acquired image, and obtaining first feature point information of the face, the feature point of the portrait uniquely identifying the person Face; obtaining first three-dimensional face model parameter information according to the first face feature point information and a pre-trained convolutional neural network model; comparing the pre-obtained three-dimensional average person according to the first three-dimensional face model parameter information The face model is processed to obtain a three-dimensional face image corresponding to the face.
  • the training method of the convolutional neural network model includes: constructing a convolutional neural network model composed of a two-layer hourglass-type convolutional neural network; obtaining a data set for training the convolutional neural network model, where The data set includes several two-dimensional face images and three-dimensional portrait scan data corresponding to the two-dimensional face images; preprocessing the two-dimensional face images to obtain second facial feature point information; Face feature point information is input to the convolutional neural network model to obtain the second three-dimensional face model parameter information; the cross-entropy loss function is used to optimize the parameters of the convolutional neural network until the second three-dimensional face model parameter The loss function of the information and the 3D portrait scan data converges to a preset threshold.
  • the first three-dimensional face model parameter information includes: face shape information, face expression information, and face pose information.
  • processing the previously obtained three-dimensional average face model according to the three-dimensional face model parameter information to obtain a three-dimensional face image corresponding to the face includes: according to the face shape information and the face information
  • the facial expression information processes the 3D average face model to obtain an initial 3D face model; and adjusts the initial 3D face image according to the facial posture information to obtain a 3D face corresponding to the face image.
  • the step of identifying the face in the image and obtaining the first feature point information of the face includes using a feature point recognition algorithm to obtain a first preset number of feature points, and determining the two-dimensional coordinates of the feature point information. Position; first face feature point information representing a second preset number of pixels around the feature point is obtained according to the two-dimensional coordinate position.
  • the image is acquired by an image acquisition device
  • the image acquisition device includes a lens, an autofocus voice coil motor, a mechanical image stabilizer, and an image sensor
  • the lens is fixed on the autofocus voice coil motor.
  • the lens is used to acquire an image
  • the image sensor transmits the image acquired by the lens to the identification module
  • the autofocus voice coil motor is mounted on the mechanical image stabilizer
  • the processing module is based on the The feedback of the lens shake detected by the gyroscope drives the action of the mechanical image stabilizer to achieve lens shake compensation.
  • the mechanical image stabilizer includes a movable plate, a base plate, and a compensation mechanism.
  • Each of the movable plate and the base plate is provided with a through hole through which the lens passes, and the auto-focusing voice coil motor is installed at
  • the movable plate is mounted on the substrate, and the size of the substrate is larger than the movable plate.
  • the compensation mechanism drives the movable plate and the movable plate under the driving of the processing module.
  • the lens moves to achieve lens shake compensation;
  • the compensation mechanism includes a first compensation component, a second compensation component, a third compensation component, and a fourth compensation component installed around the substrate, wherein the first compensation component and The third compensation component is disposed opposite to each other, the second compensation component is disposed opposite to the fourth compensation component, and a line between the first compensation component and the third compensation component is connected to the first compensation component and the first compensation component.
  • the lines between the three compensation components are perpendicular to each other; the first compensation component, the second compensation component, the third compensation component, and the fourth compensation component all include a driving member, a rotating shaft, and a one-way bearing.
  • the driving member is controlled by the processing module, and the driving member is drivingly connected to the rotating shaft to drive the rotating shaft to rotate;
  • the rotating shaft is connected to the inner ring of the one-way bearing to Driving the inner ring of the one-way bearing to rotate;
  • the rotating ring gear is sleeved on the one-way bearing and connected to the outer ring of the one-way bearing, and an outer surface of the rotating ring gear is provided with a ring in its circumferential direction External teeth
  • the bottom surface of the movable plate is provided with a plurality of rows of strip grooves arranged at even intervals, the strip grooves are engaged with the external teeth, and the external teeth can slide along the length direction of the strip grooves ;
  • the rotatable direction of the one-way bearing of the first compensation component is opposite to the rotatable direction of the one-way bearing of the third compensation component, and the rotatable direction of the one-way bearing of the second compensation component is different from that The rotatable direction of the one-way
  • the driving member is a micro motor, the micro motor is electrically connected to the processing module, and a rotary output end of the micro motor is connected to the rotating shaft; or the driving member includes a memory alloy wire and a crank A connecting rod, one end of the memory alloy wire is fixed on the fixing plate and connected with the processing module through a circuit, and the other end of the memory alloy wire is connected with the rotating shaft through the crank connecting rod to drive The rotation shaft rotates.
  • the image acquisition device is provided on a mobile phone
  • the mobile phone includes a bracket, the bracket includes a mobile phone mount and a retractable support rod;
  • the mobile phone mount includes a retractable connection plate and two opposite ends of the connection plate.
  • a folding plate group one end of the supporting rod is connected with the middle of the connecting plate through a damping hinge;
  • the folding plate group includes a first plate body, a second plate body and a third plate body, wherein the first plate One of the opposite ends of the body is hinged to the connection plate, and the other of the opposite ends of the first plate body is hinged to one of the opposite ends of the second plate body; the first The other end of the opposite ends of the two plates is hinged to one of the opposite ends of the third plate;
  • the second plate is provided with an opening for the corner of the mobile phone to be inserted; and the mobile phone mount is used to install a mobile phone.
  • the first plate body, the second plate body, and the third plate body are folded in a right triangle state, the second plate body is a hypotenuse of a right triangle, and the first plate body and the third plate body are A right-angled side of a right triangle, wherein the first A side plate and a side surface of the connecting plate bonded side by side, one of the opposite ends of the third plate member and the other end opposite ends of the first plate against body.
  • one side of the third plate body is provided with a first connection portion, and a side surface of the connection plate that is in contact with the third plate body is provided with a first fit that is matched with the first connection portion.
  • a second connection portion is provided on one end of the opposite ends of the first plate body, and a second connection is provided on the other end of the opposite ends of the third plate body to cooperate with the second connection portion.
  • the other end of the support rod is detachably connected with a base.
  • Another aspect of the embodiments of the present invention provides a three-dimensional face image generating device, including:
  • a recognition module for obtaining a face image and recognizing a face in the image, and obtaining first face feature point information, the portrait feature point is used to uniquely identify the face; an output module is used to The first face feature point information and a pre-trained convolutional neural network model to obtain the first three-dimensional face model parameter information; a processing module configured to perform, on the previously obtained three-dimensional average person, according to the first three-dimensional face model parameter information; The face model is processed to obtain a three-dimensional face image corresponding to the face.
  • the device further includes a training module, the training module includes: a building unit for building a convolutional neural network model composed of a two-layer hourglass-type convolutional neural network; and an obtaining unit for obtaining The data set of the convolutional neural network model, the data set includes a plurality of two-dimensional face images and three-dimensional portrait scan data corresponding to the two-dimensional face images; a pre-processing unit is configured to process the two-dimensional face images Performing preprocessing to obtain second face feature point information; an input unit for inputting the second face feature point information to the convolutional neural network model to obtain second 3D face model parameter information; an optimization unit for The parameters of the convolutional neural network are optimized by using a cross entropy loss function until the second 3D face model parameter information and the loss function of the 3D portrait scan data converge to a preset threshold.
  • the training module includes: a building unit for building a convolutional neural network model composed of a two-layer hourglass-type convolutional neural network; and an obtaining unit
  • the first three-dimensional face model parameter information includes: face shape information, face expression information, and face pose information.
  • the processing module is specifically configured to process the three-dimensional average face model according to the face shape information and the facial expression information to obtain an initial three-dimensional face model; according to the face posture information Adjusting the initial three-dimensional face image to obtain a three-dimensional face image corresponding to the face.
  • the recognition module is specifically configured to use a feature point recognition algorithm to obtain a first preset number of feature points, determine a two-dimensional coordinate position of the feature point information, and obtain a representative feature based on the two-dimensional coordinate position.
  • Another aspect of the embodiments of the present invention provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein,
  • the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute any one of the three-dimensional human faces in the embodiment of the present invention.
  • Image generation method
  • the above electronic device may be the image acquisition device for acquiring a face image.
  • the method, device, and electronic device for generating a three-dimensional face image do not need to acquire multiple images from multiple angles, and only need a single image to generate a three-dimensional face image; using a convolutional neural network Images can automatically generate more accurate and realistic facial expressions and poses, without the support of hardware, and reduce costs in many ways. At the same time, by improving the anti-shake structure of the image acquisition device, the image acquisition quality is improved.
  • FIG. 1 is a flowchart of a three-dimensional face image generation method according to an embodiment of the present invention
  • step S101 is a specific flowchart of step S101 provided by an embodiment of the present invention.
  • step S103 is a specific flowchart of step S103 provided by an embodiment of the present invention.
  • FIG. 4 is a structural diagram of a three-dimensional face image generating device according to an embodiment of the present invention.
  • FIG. 5 is a structural diagram of a three-dimensional face image generating device according to an embodiment of the present invention.
  • FIG. 6 is a schematic diagram of a hardware structure of an electronic device for executing a method for generating a three-dimensional face image provided by an embodiment of the method of the present invention
  • FIG. 7 is a structural diagram of an image acquisition device according to an embodiment of the present invention.
  • FIG. 8 is a structural diagram of an optical image stabilizer provided by an embodiment of the present invention.
  • FIG. 9 is an enlarged view of part A of FIG. 8; FIG.
  • FIG. 10 is a schematic bottom view of a movable plate of a micro memory alloy optical image stabilizer provided by an embodiment of the present invention.
  • FIG. 11 is a structural diagram of a stent provided by an embodiment of the present invention.
  • FIG. 12 is a schematic state diagram of a stent according to an embodiment of the present invention.
  • FIG. 13 is a schematic view of another state of a stent according to an embodiment of the present invention.
  • FIG. 14 is a structural state diagram when the mounting base and the mobile phone are connected according to an embodiment of the present invention.
  • FIG. 1 is a flowchart of a three-dimensional face image generating method according to an embodiment of the present invention. As shown in FIG. 1, a method for generating a three-dimensional face image according to an embodiment of the present invention includes:
  • S101 Recognize a human face in an acquired image, and obtain first facial feature point information, where the personal feature point is used to uniquely identify the human face.
  • the obtained face image includes an image of a non-face part, such as a background environment image, and so the face image in the image needs to be identified.
  • an image in an image acquired through a real-time shooting manner may be identified, and an image in an image stored locally on the terminal may be identified.
  • the first face feature point information includes, but is not limited to, coordinate parameter values of the face feature points in the image and texture parameters (that is, texture parameters of the RGB features).
  • the range of the face image can be identified according to the edge information and / or color information of the image.
  • the key point by identifying a pre-defined key point, based on the detected key point Determine first face feature point information.
  • the eyebrows, eyes, nose, face, and mouth in the face image are each composed of several key points, that is, the eyebrows, eyes, and nose in the face image can be determined by the coordinate positions of the key points. , Face and mouth position and texture.
  • the step of identifying the face in the image and obtaining the first feature point information of the face includes the steps of identifying a first preset number of feature points and determining the feature points.
  • the facial feature point recognition algorithm in the prior art is used to obtain the first facial feature point information.
  • the training of facial feature point recognition algorithms usually includes the following steps: First, obtain a certain number of training sets, which are images that carry human facial feature point information; second, use the training set to train to form the initial regression function r0 and the initial Training set; again, use this initial training set and initial regression function r0 to iterate to form the next training set and regression function rn; each iteration of the regression function uses a gradient boosting algorithm to learn, so when the nth training set and the training set When the facial feature point information meets the convergence conditions, the corresponding regression function rn is the facial feature point recognition algorithm after training.
  • Face detection is performed on the image to obtain the position of the face in the image, and a range rectangle is used to identify the range of the face, for example (left, top, right, bottom).
  • the first preset number of feature points and the coordinates (x i , y i ) of each first face feature point are obtained through the regression function in the trained feature point recognition algorithm for the input portrait photo recognition, where i represents the recognition
  • the first preset number of obtained i-th feature points may be 68, including key points of eyebrows, eyes, nose, mouth, and face.
  • the second preset number may be 6, 8 or the like, which is not limited in the present invention.
  • S102 Obtain first three-dimensional face model parameter information according to the first face feature point information and a pre-trained convolutional neural network model.
  • the CNN is a deep feedforward artificial neural network.
  • the basic structure of CNN includes two layers. One is a feature extraction layer. The input of each neuron is connected to the local acceptance domain of the previous layer and the local features are extracted. Once the local feature is extracted, it is connected to other features. The positional relationship between them is also determined; the second is the feature mapping layer.
  • Each computing layer of the network consists of multiple feature maps. Each feature map is a plane, and the weights of all neurons on the plane are equal.
  • Convolutional neural networks usually include one-dimensional convolutional neural networks, two-dimensional convolutional neural networks, and three-dimensional convolutional neural networks. A large number of mathematical models of these convolutional neural networks have been introduced in the prior art. The type of convolutional neural network is limited.
  • training the convolutional neural network model can include the following steps:
  • S202 Obtain a data set for training the convolutional neural network model, where the data set includes several two-dimensional face images and three-dimensional portrait scan data corresponding to the two-dimensional face images.
  • the data set can be obtained first, and then the convolutional neural network model can be constructed, and the volume and neural network model can also be constructed first. There are no restrictions here.
  • the method for obtaining the input sample data set in this step includes downloading an image directly from the Internet as the input sample data set, and artificially taking the image as the input sample data set, where the artificially taken image may include images of people of different races. , Images of people with different light and shadow effects.
  • the 3D portrait scan data mainly includes the pose information of the face (such as the tilt angle, deflection angle, and rotation angle of the face, the shape parameters of the face feature points, and the expression parameters of the face feature points.
  • S203 Preprocess the two-dimensional face image to obtain second facial feature point information.
  • step S101 can be used to obtain the second face feature point information of the two-dimensional face image, that is, the second face feature point coordinates (x i , y i ) and the texture corresponding to the feature point can be obtained.
  • the second face feature point information is input to the convolutional neural network model each time.
  • the second face feature point information can reflect the current face shape information and is output as the second three-dimensional face model parameter.
  • the algorithm uses a convolutional neural network to fit the mapping function from input to output.
  • the network structure includes 4 convolutional layers, 3 pooling layers, and 2 fully connected layers. By concatenating multiple convolutional neural networks until convergence on the training set, it is updated according to the currently predicted face shape and used as the input of the next level of convolutional neural network.
  • the first two convolutional layers of the network extract facial features through weight-sharing methods, and the last two convolutional layers extract facial features through local perception, further returning a feature vector in a 256-dimensional space and outputting a feature in a 234-dimensional space.
  • Vector the second three-dimensional face model parameter p.
  • face pose parameters [f, pitch, yaw, roll, t 2dx , t 2dy ], shape parameters ⁇ id , and expression parameters ⁇ exp .
  • f is a scale factor
  • pitch is a tilt angle
  • yaw is a deflection angle
  • roll is a rotation angle
  • t 2dx and t 2dy are offset terms.
  • the loss function is a reflection of the degree of fit of the model data. When the result of the fit is worse, the value of the loss function will be larger.
  • the parameter p k will be obtained after an initial parameter change, and a neural network Net K is trained according to the above three-dimensional portrait scan data.
  • the prediction parameter p is continuously updated p k .
  • the network is expressed mathematically as follows:
  • S103 Process a three-dimensional average face model according to the first three-dimensional face model parameter information to obtain a three-dimensional face image corresponding to the face.
  • Faces have more in common. Normal human faces have one nose, two eyes, one mouth, and two ears. The order from top to bottom and left to right is unchanged. Therefore, you can first build a three-dimensional average face model because of the similarity of the faces. Larger, you can always change from one normal face to another normal face, and calculate the amount of change to change the average face model, so this is also the basis for 3D face reconstruction.
  • this step may be implemented by the following sub-steps:
  • Step S1031 Process the three-dimensional average face model according to the face shape information and the facial expression information to obtain an initial three-dimensional face model.
  • S is the initial three-dimensional face model
  • S 0 is the average face model
  • a id is the base vector of the shape
  • ⁇ id is the shape parameter
  • a exp is the base vector of the expression
  • ⁇ exp is the expression parameter.
  • a exp and A exp can be obtained in advance by existing algorithms.
  • the initial three-dimensional face model projects the face model onto the image plane through a weak perspective projection to obtain a three-dimensional face image corresponding to the face, and the formula is expressed as follows:
  • V (p) F * Pr * R (S 0 + A id ⁇ id + A exp ⁇ exp ) + t 2d
  • V (p) is the reconstructed three-dimensional face image corresponding to the face
  • f is a scale factor
  • Pr is a right-angle projection matrix
  • R is a rotation matrix.
  • the tilt angle (pitch), deflection angle (yaw), The rotation angle (roll) is obtained based on the pose information of the human face in the two-dimensional image identified by the feature points.
  • the method for generating a three-dimensional face image provided by the embodiment of the present invention can generate a three-dimensional face image by using only a single image; a convolutional neural network image can automatically generate more accurate and realistic face expressions and poses without the need for Hardware support reduces costs in many ways.
  • FIG. 4 is a structural diagram of a three-dimensional face image generating device according to an embodiment of the present invention. As shown in FIG. 4, the device specifically includes: an identification module 100, an output module 200, and a processing module 300. among them,
  • a recognition module 100 is configured to recognize a face in an acquired image, and obtain first feature point information of the face, the feature point of the portrait uniquely identifying the face; an output module 200, configured to identify the face according to the first Face feature point information and pre-trained convolutional neural network model to obtain first three-dimensional face model parameter information; a processing module 300 is configured to process the three-dimensional average face model according to the first three-dimensional face model parameter information To obtain a three-dimensional face image corresponding to the face.
  • the three-dimensional face image generating device provided by the embodiment of the present invention is specifically configured to execute the method provided by the embodiment shown in FIG. 1, and its implementation principles, methods, and functional uses are similar to the embodiment shown in FIG. 1, and are not repeated here. To repeat.
  • FIG. 5 is a structural diagram of a three-dimensional face image generating device according to an embodiment of the present invention. As shown in FIG. 5, the device specifically includes: a training module 400, a recognition module 200, an output module 300, and a processing module 400. among them,
  • the training module 400 includes: a building unit 410 for building a convolutional neural network model composed of a two-layer hourglass convolutional neural network; and an obtaining unit 420 for obtaining a data set for training the convolutional neural network model,
  • the data set includes several two-dimensional face images and three-dimensional portrait scan data corresponding to the two-dimensional face images;
  • a pre-processing unit 430 is configured to pre-process the two-dimensional face images to obtain a second face feature Point information;
  • an input unit 440 configured to input the second facial feature point information into the convolutional neural network model to obtain second three-dimensional face model parameter information;
  • an optimization unit 450 configured to use a cross entropy loss function to The parameters of the convolutional neural network are optimized until the second 3D face model parameter information and the loss function of the 3D portrait scan data converge to a preset threshold.
  • a recognition module 200 for recognizing a human face in an image and acquiring first feature point information of the human face, the feature point for the portrait uniquely identifying the face; an output module 300 for recognizing the first person based on the first person Face feature point information and a pre-trained convolutional neural network model to obtain first three-dimensional face model parameter information; a processing module 400 is configured to process a three-dimensional average face model according to the first three-dimensional face model parameter information, A three-dimensional face image corresponding to the human face is obtained.
  • the first three-dimensional face model parameter information includes: face shape information, face expression information, and face pose information.
  • the processing module 400 is specifically configured to process the three-dimensional average face model according to the face shape information and the facial expression information to obtain an initial three-dimensional face model; and according to the face posture information Adjusting the initial three-dimensional face image to obtain a three-dimensional face image corresponding to the face.
  • the recognition module 200 is specifically configured to use a feature point recognition algorithm to obtain a first preset number of feature points, determine a two-dimensional coordinate position of the feature point information, and obtain a representative feature based on the two-dimensional coordinate position.
  • a feature point recognition algorithm to obtain a first preset number of feature points, determine a two-dimensional coordinate position of the feature point information, and obtain a representative feature based on the two-dimensional coordinate position.
  • the three-dimensional face image generating device provided by the embodiment of the present invention is specifically configured to execute the method provided by the embodiment shown in FIG. 1 to FIG. 3, and its implementation principles, methods, and functional uses are similar to the embodiment shown in FIG. 1-3 , Will not repeat them here.
  • the above-mentioned three-dimensional face image generating device may be used as one of the software or hardware functional units, which may be independently provided in the above-mentioned electronic device, or may be used as one of the functional modules integrated in the processor to execute the embodiments of the present invention 3D face image generation method.
  • FIG. 6 is a schematic diagram of a hardware structure of an electronic device for executing a method for generating a three-dimensional face image provided by an embodiment of the method of the present invention.
  • the electronic device includes:
  • One or more processors 610 and a memory 620 are taken as an example in FIG. 6.
  • the device for performing the three-dimensional face image generating method may further include: an input device 630 and an output device 630.
  • the processor 610, the memory 620, the input device 630, and the output device 640 may be connected through a bus or other methods. In FIG. 6, the connection through the bus is taken as an example.
  • the memory 620 is a non-volatile computer-readable storage medium, and can be used to store non-volatile software programs, non-volatile computer executable programs, and modules, such as the three-dimensional face image generation in the embodiment of the present invention.
  • the program instruction / module corresponding to the method.
  • the processor 610 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions, and modules stored in the memory 620, that is, the three-dimensional face image generating method is implemented.
  • the memory 620 may include a storage program area and a storage data area, where the storage program area may store an operating system and an application program required for at least one function; the storage data area may store a three-dimensional face image generating device according to an embodiment of the present invention. Use the created data, etc.
  • the memory 620 may include a high-speed random access memory 620, and may further include a non-volatile memory 620, such as at least one magnetic disk memory 620, a flash memory device, or other non-volatile solid-state memory 620.
  • the memory 620 may optionally include a memory 620 remotely disposed with respect to the processor 66, and these remote memories 620 may be connected to the three-dimensional face image generating device through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
  • the input device 630 may receive inputted numeric or character information, and generate key signal inputs related to user settings and function control of the three-dimensional face image generating device.
  • the input device 630 may include a device such as a pressing module.
  • the one or more modules are stored in the memory 620, and when executed by the one or more processors 610, execute the three-dimensional face image generation method.
  • the electronic devices in the embodiments of the present invention exist in various forms, including but not limited to:
  • Mobile communication equipment This type of equipment is characterized by mobile communication functions, and its main goal is to provide voice and data communication.
  • Such terminals include: smart phones (such as iPhone), multimedia phones, feature phones, and low-end phones.
  • Ultra-mobile personal computer equipment This type of equipment belongs to the category of personal computers, has computing and processing functions, and generally has the characteristics of mobile Internet access.
  • Such terminals include: PDA, MID and UMPC devices, such as iPad.
  • Portable entertainment equipment This type of equipment can display and play multimedia content.
  • Such devices include: audio and video players (such as iPod), handheld game consoles, e-books, as well as smart toys and portable car navigation devices.
  • an image acquisition device for acquiring an image is provided on the electronic device, and a software or hardware image stabilizer is often provided on the image acquisition device to ensure the quality of the acquired image.
  • Most of the existing image stabilizers are powered by coils that generate Loren magnetic force in the magnetic field to drive the lens.
  • the lens needs to be driven in at least two directions, which means that multiple coils need to be arranged, which will give the whole.
  • the miniaturization of the structure brings certain challenges, and it is easy to be affected by external magnetic fields, which affects the anti-shake effect. Therefore, the Chinese patent published as CN106131435A provides a miniature optical anti-shake camera module, which realizes memory alloy wires through temperature changes.
  • the control chip of the micro memory alloy optical anti-shake actuator can control the change of the driving signal to change the temperature of the memory alloy wire. Control the elongation and shortening of the memory alloy wire, and calculate the position and moving distance of the actuator based on the resistance of the memory alloy wire. When the micro memory alloy optical image stabilization actuator moves to the specified position, the resistance of the memory alloy wire at this time is fed back. By comparing the deviation of this resistance value and the target value, the movement on the micro memory alloy optical image stabilization actuator can be corrected. deviation.
  • the above technical solution can compensate the lens for the shake in the first direction, but when the subsequent shake in the second direction occurs, it is too late due to the memory alloy wire. Deformation in an instant, so it is easy to cause untimely compensation, and it is impossible to accurately realize lens shake compensation for multiple shakes and continuous shakes in different directions. Therefore, it is necessary to improve its structure in order to obtain better image quality and facilitate subsequent 3D Image generation.
  • this embodiment improves the anti-shake device and designs it as a mechanical anti-shake device 3000.
  • the specific structure is as follows:
  • the mechanical image stabilizer 3000 of this embodiment includes a movable plate 3100, a base plate 3200, and a compensation mechanism 3300.
  • Each of the movable plate 3100 and the base plate 3200 is provided with a through hole through which the lens 1000 passes.
  • An autofocus voice coil motor 2000 is mounted on the movable plate 3100, and the movable plate 3100 is mounted on the base plate 3200.
  • the size of the base plate 3200 is larger than the movable plate 3100, and the movable plate 3100 passes above it.
  • the auto-focusing voice coil motor limits its up and down movement, and the compensation mechanism 3300 drives the movable plate 3100 and the lens 1000 on the movable plate 3100 to move under the driving of the processing module to achieve shake compensation of the lens 1000.
  • the compensation mechanism 3300 in this embodiment includes a first compensation component 3310, a second compensation component 3320, a third compensation component 3330, and a fourth compensation component 3340 installed around the substrate 3200.
  • a compensation component 3310 and the third compensation component 3330 are disposed opposite to each other, the second compensation component 3320 is disposed opposite to the fourth compensation component 3340, and a connection line between the first compensation component 3310 and the third compensation component 3330
  • the connection lines between the first compensation component 3310 and the third compensation component 3330 are perpendicular to each other, that is, a compensation component, a second compensation component 3320, and a third compensation component 3330 are respectively arranged in the front, rear, left, and right directions of the movable plate 3100.
  • the first compensation component 3310 can make the movable plate 3100 move forward
  • the third compensation component 3330 can make the movable plate 3100 move backward
  • the second compensation component 3320 can make the movable plate 3100 move left
  • the fourth compensation component 3340 can make The movable plate 3100 moves to the left
  • the first compensation component 3310 can cooperate with the second compensation component 3320 or the fourth compensation component 3340 to realize the operation of the movable plate 3100 in an inclined direction.
  • the third component 3330 may be compensated 1000 compensation and the second compensation component 3320 or the fourth compensation component 3340 cooperate to achieve movement of the movable plate 3100 to the tilt direction, the lens implemented in the respective direction of jitter.
  • the first compensation component 3310, the second compensation component 3320, the third compensation component 3330, and the fourth compensation component 3340 in this embodiment each include a driving member 3301, a rotating shaft 3302, a one-way bearing 3303, and a rotating ring gear 3304.
  • the driving member 3301 is controlled by the processing module, and the driving member 3301 is drivingly connected to the rotating shaft 3302 to drive the rotating shaft 3302 to rotate.
  • the rotating shaft 3302 is connected to the inner ring of the one-way bearing 3303 to drive the inner ring of the one-way bearing 3303 to rotate.
  • the rotating ring gear 3304 is sleeved on the one-way bearing 3303 and is connected to the one-way bearing 3303.
  • the outer ring of the one-way bearing 3303 is fixedly connected.
  • the outer surface of the rotating ring gear 3304 is provided with a ring of external teeth along its circumferential direction.
  • the shaped groove 3110 is meshed with the external teeth, and the external teeth can slide along the length direction of the strip groove 3110; wherein the rotatable direction of the one-way bearing 3303 of the first compensation component 3310 and the external teeth.
  • the rotation direction of the one-way bearing 3303 of the third compensation component 3330 is opposite, and the rotation direction of the one-way bearing 3303 of the second compensation component 3320 is opposite to the rotation direction of the one-way bearing 3303 of the fourth compensation component 3340.
  • One-way bearing 3303 is a bearing that can rotate freely in one direction and lock in the other direction.
  • the driving member 3301 of the first compensation component 3310 causes the rotating shaft 3302 to drive
  • the inner ring of the one-way bearing 3303 rotates.
  • the one-way bearing 3303 is locked. Therefore, the inner ring of the one-way bearing 3303 can drive the outer ring to rotate, which in turn drives the rotating ring gear 3304 to rotate.
  • the engagement of the groove 3110 drives the movable plate 3100 to move in a direction that can compensate for shake.
  • the third compensation component 3330 can be used to drive the movable plate 3100 to rotate.
  • the one-way bearing 3303 of the first compensation component 3310 is in a rotatable state, so the ring gear on the first compensation component 3310 follows the movable plate 3100, and will not affect the activity Reset of board 3100.
  • the one-way bearing 3303 and the rotating ring gear 3304 can reduce the overall thickness of the entire mechanical vibration stabilizer 3000 by concealing parts of the one-way bearing 3303 and the rotating ring gear 3304 in the mounting holes.
  • a part of the entire compensation component is directly placed in the mounting hole.
  • the driving member 3301 in this embodiment may be a micro motor, the micro motor is electrically connected to the processing module, a rotation output end of the micro motor is connected to the rotating shaft 3302, and the micro motor is controlled To the processing module.
  • the driving member 3301 is composed of a memory alloy wire and a crank connecting rod. One end of the memory alloy wire is fixed on the fixing plate and is connected to the processing module through a circuit. The other end of the memory alloy wire passes The crank link is connected to the rotating shaft 3302 to drive the rotating shaft 3302 to rotate.
  • the processing module calculates the elongation of the memory alloy wire according to the feedback from the gyroscope, and drives the corresponding circuit to the shape memory alloy.
  • the temperature of the wire is increased, and the shape memory alloy wire is stretched to drive the crank link mechanism.
  • the crank of the crank link mechanism drives the rotation shaft 3302 to rotate the inner ring of the one-way bearing 3303.
  • the inner The ring drives the outer ring to rotate, and the rotating ring gear 3304 drives the movable plate 3100 through the strip groove 3110.
  • the following describes the working process of the mechanical image stabilizer 3000 of this embodiment in detail in combination with the above structure.
  • the movable plate 3100 needs to be compensated for forward motion, and then Left motion compensation once.
  • the gyroscope feeds the detected lens 1000 shake direction and distance in advance to the processing module.
  • the processing module calculates the required movement distance of the movable plate 3100, and then drives the first compensation component 3310.
  • the driving member 3301 causes the rotating shaft 3302 to drive the inner ring of the one-way bearing 3303.
  • the one-way bearing 3303 is locked, so the inner ring can drive the outer ring to rotate, which in turn drives the rotating ring gear 3304 to rotate, and the rotating ring gear 3304 passes
  • the strip groove 3110 drives the movable plate 3100 to move forward, and then the third compensation component 3330 drives the movable plate 3100 to reset.
  • the gyroscope feeds back the detected lens 1000 shake direction and distance to the processing module in advance, and the processing module calculates the motion distance required for the motion board 3100 to drive the second compensation component 3320.
  • the driving member 3301 causes the rotating shaft 3302 to drive the inner ring of the one-way bearing 3303.
  • the one-way bearing 3303 is locked, so the inner ring can drive the outer ring to rotate, which in turn drives the rotating ring gear 3304 to rotate, and the rotating ring gear 3304 passes
  • the strip groove 3110 drives the movable plate 3100 to move forward, and because the external teeth of the ring gear 3304 can slide along the length direction of the strip groove 310, when the movable plate 3100 moves to the left, the movable plate 3100 and the first compensation
  • the sliding fitting between the component 3310 and the third compensation component 3330 does not affect the leftward movement of the movable plate 3100.
  • the fourth compensation component 3340 is used to drive the movable plate 3100 to reset.
  • the above is just two simple jitters.
  • the basic working process is the same as the principle described above.
  • the detection feedback of the shape memory alloy resistance and the detection feedback of the gyroscope are existing technologies, and are not described here too.
  • the mechanical compensator provided by this embodiment not only is not affected by external magnetic fields and has a good anti-shake effect, but also can accurately compensate the lens 1000 in the case of multiple shakes, and the compensation is timely and accurate. Greatly improved the quality of the acquired images, and simplified the difficulty of subsequent 3D image processing.
  • the electronic device in this embodiment is specifically a mobile phone with the image acquisition device, and the mobile phone includes a stand.
  • the purpose of the mobile phone including a stand is because of the uncertainty of the image acquisition environment, it is necessary to use the stand to support and fix the mobile phone in order to obtain more stable image quality.
  • the bracket 6000 in this embodiment includes a mobile phone mounting base 6100 and a retractable supporting rod 6200.
  • the supporting rod 6200 and the middle portion of the mobile phone mounting base 6100 pass through a damping hinge.
  • the bracket 6000 may form a selfie stick structure
  • the bracket 6000 may form a mobile phone bracket 6000 structure.
  • the applicant found that the combination of the mobile phone mounting base 6100 and the support pole 6200 takes up a lot of space. Even if the support pole 6200 is retractable, the mobile phone mounting base 6100 cannot undergo structural changes and the volume will not be further reduced. Putting it in a pocket or a small bag causes the inconvenience of carrying the bracket 6000. Therefore, in this embodiment, a second step improvement is performed on the bracket 6000, so that the overall accommodation of the bracket 6000 is further improved.
  • the mobile phone mounting base 6100 of this embodiment includes a retractable connection plate 6110 and a folding plate group 6120 installed at opposite ends of the connection plate 6110.
  • the support rod 6200 and the connection plate 6110 The middle part is connected by a damping hinge;
  • the folding plate group 6120 includes a first plate body 6121, a second plate body 6122, and a third plate body 6123, wherein one of the two opposite ends of the first plate body 6121 is connected to the first plate body 6121.
  • the connecting plate 6110 is hinged, the other end of the opposite ends of the first plate body 6121 is hinged to one of the opposite ends of the second plate body 6122, and the opposite ends of the second plate body 6122 are The other end is hinged to one of opposite ends of the third plate body 6123; the second plate body 6122 is provided with an opening 6130 for inserting a corner of the mobile phone.
  • the first plate body 6121, the second plate body 6122 and the third plate body 6123 are folded into a right triangle state, and the second plate body 6122 is a hypotenuse of a right-angled triangle, and the first plate body 6121 and the third plate 6123 are right-angled sides of a right triangle, wherein one side of the third plate body 6123 and one of the connection plate 6110 The sides are attached side by side, and the other end of the opposite ends of the third plate body 6123 and one of the opposite ends of the first plate body 6121 abut against each other.
  • This structure can make the three folding plates in a self-locking state, and When the two corners of the lower part of the mobile phone are inserted into the two openings 6130 on both sides, the lower sides of the mobile phone 5000 are located in two right-angled triangles.
  • the mobile phone 5000 can be completed through the joint work of the mobile phone, the connecting plate 6110, and the folding plate group 6120.
  • the triangle state cannot be opened under external force.
  • the triangle state of 6120 pieces of folding plate group can only be released after the mobile phone is pulled out from the opening 6130.
  • the connecting plate 6110 When the mobile phone mounting base 6100 is not in working state, the connecting plate 6110 is reduced to a minimum length, and the folding plate group 6120 and the connecting plate 6110 are folded to each other.
  • the user can fold the mobile phone mounting base 6100 to a minimum volume, and due to the support
  • the scalability of the lever 6200 allows the entire bracket 6000 to be accommodated in the smallest volume, which improves the collection of the bracket 6000. Users can even put the bracket 6000 directly into their pockets or small handbags, which is very convenient.
  • a first connection portion is also provided on one side of the third plate body 6123, and a side surface where the connection plate 6110 is in contact with the third plate body 6123 is provided with the first connection portion.
  • a first mating portion that mates with a connecting portion.
  • the first connecting portion of this embodiment is a convex strip or protrusion (not shown in the figure), and the first matching portion is a card slot (not shown in the figure) opened on the connecting plate 6110.
  • This structure not only improves the stability when the 6120 pieces of the folding plate group are in a triangle state, but also facilitates the connection between the 6120 pieces of the folding plate group and the connecting plate 6110 when the mobile phone mounting base 6100 needs to be folded to a minimum state.
  • a second connection portion is also provided at one end of the opposite ends of the first plate body 6121, and the other end of the opposite ends of the third plate body 6123 is provided with the second connection portion.
  • the second connecting portion is a second matching portion that is matched with the second fitting portion, and the second connecting portion and the second fitting portion are engaged and connected.
  • the second connecting portion may be a protrusion (not shown in the figure), and the second mating portion is an opening 6130 or a card slot (not shown in the figure) that cooperates with the protrusion.
  • a base (not shown in the figure) can be detachably connected to the other end of the support rod 6200.
  • the support rod 6200 can be stretched to A certain length and place the bracket 6000 on a plane through the base, and then place the mobile phone in the mobile phone mounting base 6100 to complete the fixing of the mobile phone; and the detachable connection of the support bar 6200 and the base can make the two can be carried separately, further The accommodating of the bracket 6000 and the convenience of carrying are improved.
  • the device embodiments described above are only schematic, and the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, which may be located in One place, or can be distributed to multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the objective of the solution of this embodiment. Those of ordinary skill in the art can understand and implement without creative labor.
  • An embodiment of the present invention provides a non-transitory computer-readable storage storage medium, where the computer storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by an electronic device, the electronic device is caused.
  • the three-dimensional face image generation method in any of the foregoing method embodiments is performed on the above.
  • An embodiment of the present invention provides a computer program product, wherein the computer program product includes a computer program stored on a non-transitory computer-readable storage medium, the computer program includes program instructions, and when the program instructions When executed by an electronic device, the electronic device is caused to execute the three-dimensional face image generating method in any of the foregoing method embodiments.
  • each embodiment can be implemented by means of software plus a necessary universal hardware platform, and of course, also by hardware.
  • the above-mentioned technical solution in essence or a part that contributes to the existing technology may be embodied in the form of a software product, and the computer software product may be stored in a computer-readable storage medium, the computer-readable record A medium includes any mechanism for storing or transmitting information in a form readable by a computer (eg, a computer).
  • machine-readable media include read-only memory (ROM), random-access memory (RAM), magnetic disk storage media, optical storage media, flash storage media, electrical, optical, acoustic, or other forms of propagation signals (e.g., carrier waves , Infrared signals, digital signals, etc.), the computer software product includes a number of instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute various embodiments or certain parts of the embodiments Methods.

Abstract

一种三维人脸图像生成方法、装置及电子设备，所述方法包括：对图像中的人脸进行识别，获取第一人脸特征点信息，所述人像特征点用于唯一标识所述人脸（S101）；根据所述第一人脸特征点信息和预先训练的卷积神经网络模型，得到第一三维人脸模型参数信息（S102）；根据所述第一三维人脸模型参数信息对三维平均人脸模型进行处理，得到所述人脸对应的三维人脸图像（S103）。通过上述方法及装置，无需采集多角度多张图像，仅需单张图像即可生成三维人脸图像；采用卷积神经网络图像，可自动生成更准确和更逼真的人脸表情和姿态，且无需硬件的支持，多方面降低成本。

Description

三维人脸图像生成方法、装置及电子设备 技术领域
本发明涉及三维人脸图像生成技术领域，尤其涉及一种三维人脸图像生成方法、装置及电子设备。
背景技术
三维人脸重建在医疗、教育、娱乐等领域目前已经得到了非常广泛的应用。发明人在实现本发明的过程中发现，在三维人脸重建的过程中，利用多张图像多个角度来拼合成三维模型，但由于需要大量的图像，所以重建过程繁琐复杂，需要在多张大范围面部姿态图像中建立像素之间的密集对应，而导致同一个个体的3D模拟差异较大，同时导致重建的时间长，成本高。此外，手机等便携电子设备出于娱乐的目的越来越多使用三维人脸重建技术，获取二维人脸图像主要通过电子设备的摄像头，而后期三维人脸图像的重建效果部分取决于前期摄像装置获取图像的质量，而获取图像质量又部分的取决于拍摄时对抖动的处理效果，目前的手机主要通过软件进行防抖处理，硬件并未有针对性的改进。
发明内容
本发明实施例提供的三维人脸图像生成方法、装置及电子设备，用以至少解决相关技术中的上述问题。
本发明实施例一方面提供了一种三维人脸图像生成方法，包括：对获取图像中的人脸进行识别，获取第一人脸特征点信息，所述人像特征点用于唯一标识所述人脸；根据所述第一人脸特征点信息和预先训练的卷积神经网络模型，得到第一三维人脸模型参数信息；根据所述第一三维人脸模型参数信息对预先获得的三维平均人脸模型进行处理，得到所述人脸对应的三维人脸图像。
进一步地，所述卷积神经网络模型的训练方法包括：搭建由两层沙漏型卷积神经网络组成的卷积神经网络模型；获取用于训练所述卷积神经网络模型的数据集，所述数据集中包括若干二维人脸图像和所述二维人脸图像对应的三维人像扫描数据；对所述二维人脸图像进行预处理得到第二人脸特征点信息；将所述第二人脸特征点信息输入至所述卷积神经网络模型得到第二三维人脸模型参数信息；利用交叉熵损失函数对所述卷积神经网络的参数进行优化，直至所述第二三维人脸模型参数信息与所述三维人像扫描数据的损失函数收敛到预设阈值。
进一步地，所述第一三维人脸模型参数信息包括：人脸形状信息、人脸表情信息和人脸姿态信息。
进一步地，所述根据所述三维人脸模型参数信息对预先获得的三维平均人脸模型进行处理，得到所述人脸对应的三维人脸图像，包括：根据所述人脸形状信息和所述人脸表情信息对所述三维平均人脸模型进行处理，得到初始三维人脸模型；根据所述人脸姿态信息对所述初始三维人脸图像进行调整，得到所述人脸对应的三维人脸图像。
进一步地，所述对图像中的人脸进行识别，获取第一人脸特征点信息，包括：使用特征点识别算法得到第一预设数量的特征点，确定所述特征点信息的二维坐标位置；根据所述二维坐标位置得到代表所述特征点周围第二预设数量像素的第一人脸特征点信息。
进一步地，通过图像获取设备获取所述图像，所述图像获取设备包括镜头、自动聚焦音圈马达、机械防抖器以及图像传感器，所述镜头固装在所述自动聚焦音圈马达上，所述镜头用于获取图像，所述图像传感器将所述镜头获取的图像传输至所述识别模块，所述自动聚焦音圈马达安装在所述机械防抖器上，所述处理模块根据镜头内的陀螺仪检测到的镜头抖动的反馈驱动所述机械防抖器的动作，实现镜头的抖动补偿。
进一步地，所述机械防抖器包括活动板、基板以及补偿机构，所述活动板和所述基板的中部均设有所述镜头穿过的通孔，所述自动聚焦音圈马达安装在所述活动板上，所述活动板安装在所述基板上，且所述基板的尺寸大于所述活动板，所述补偿机构在所述处理模块的驱动下带动所述活动板和活动板上的镜头动作，以实现镜头的抖动补偿；所述补偿机构包括安装在所述基板四周的第一补偿组件、第二补偿组件、第三补偿组件以及第四补偿组件，其中所述第一补偿组件和所述第三补偿组件相对设置，所述第二补偿组件与所述第四补偿组件相对设置，所述第一补偿组件与第三补偿组件之间的连线与所述第一补偿组件与第三补偿组件之间的连线相互垂直；所述第一补偿组件、第二补偿组件、第三补偿组件以及第四补偿组件均包括驱动件、转轴、单向轴承以及转动齿圈；所述驱动件受控于所述处理模块，所述驱动件与所述转轴传动连接，以带动所述转轴转动；所述转轴与所述单向轴承的内圈相连接，以带动所述单向轴承的内圈转动；所述转动齿圈套设在所述单向轴承上并与所述单向轴承的外圈相连接，所述转动齿圈的外表面沿其周向设有一圈外齿，所述活动板的底面设有多排均匀间隔布设的条形槽，所述条形槽与所述外齿相啮合，且所述外齿可沿所述条形槽的长度方向滑动；其中，所述第一补偿组件的单向轴承的可转动方向与所述第三补偿组件的单向轴承的可转动方向相反，所述第二补偿组件的单向轴承的可转动方向与所述第四补偿组件的单向轴承的可转动方向相反。
进一步地，所述固定板的四周开设有四个贯穿的安装孔，所述安装孔上安装有 所述单向轴承和所述转动齿圈。
进一步地，所述驱动件为微型电机，所述微型电机与所述处理模块电连接，所述微型电机的转动输出端与所述转轴相连接；或，所述驱动件包括记忆合金丝和曲柄连杆，所述记忆合金丝一端固定于所述固定板上，并与所述处理模块通过电路相连接，所述记忆合金丝另一端通过所述曲柄连杆与所述转轴相连接，以带动所述转轴转动。
进一步地，所述图像获取设备设置于手机上，手机包括支架，所述支架包括手机安装座和可伸缩的支撑杆；所述手机安装座包括可伸缩的连接板和安装于连接板相对两端的折叠板组，所述支撑杆的一端与所述连接板中部通过阻尼铰链相连接；所述折叠板组包括第一板体、第二板体及第三板体，其中，所述第一板体的相对两端中的一端与所述连接板相铰接，所述第一板体的相对两端中的另一端与所述第二板体的相对两端中的一端相铰接；所述第二板体相对两端的另一端与所述第三板体相对两端中的一端相铰接；所述第二板体设有供手机边角插入的开口；所述手机安装座用于安装手机时，所述第一板体、第二板体和第三板体折叠呈直角三角形状态，所述第二板体为直角三角形的斜边，所述第一板体和所述第三板体为直角三角形的直角边，其中，所述第三板体的一个侧面与所述连接板的一个侧面并排贴合，所述第三板体相对两端中的另一端与所述第一板体相对两端中的一端相抵。
进一步地，所述第三板体的一个侧面设有第一连接部，所述连接板与所述第三板体相贴合的侧面设有与所述第一连接部相配合的第一配合部，所述支架手机安装座用于安装手机时，所述第一连接部和所述第一配合部卡合连接。
进一步地，所述第一板体相对两端中的一端设有第二连接部，所述第三板体相对两端中的另一端设有与所述第二连接部相配合的第二配合部，所述支架手机安装座用于安装手机时，所述第二连接部和所述第二配合部卡合连接。
进一步地，所述支撑杆的另一端可拆卸连接有底座。
本发明实施例的另一方面提供了一种三维人脸图像生成装置，包括：
识别模块，用于获取人脸图像并对图像中的人脸进行识别，获取第一人脸特征点信息，所述人像特征点用于唯一标识所述人脸；输出模块，用于根据所述第一人脸特征点信息和预先训练的卷积神经网络模型，得到第一三维人脸模型参数信息；处理模块，用于根据所述第一三维人脸模型参数信息对预先获得的三维平均人脸模型进行处理，得到所述人脸对应的三维人脸图像。
进一步地，所述装置还包括训练模块，所述训练模块包括：搭建单元，用于搭建由两层沙漏型卷积神经网络组成的卷积神经网络模型；获取单元，用于获取用于训练所述卷积神经网络模型的数据集，所述数据集中包括若干二维人脸图像和所述二维人脸图像对应的三维人像扫描数据；预处理单元，用于对所述二维人脸图像进行预处理得到第二人脸特征点信息；输入单元，用于将所述第二人脸特征点信息输入至所 述卷积神经网络模型得到第二三维人脸模型参数信息；优化单元，用于利用交叉熵损失函数对所述卷积神经网络的参数进行优化，直至所述第二三维人脸模型参数信息与所述三维人像扫描数据的损失函数收敛到预设阈值。
进一步地，所述第一三维人脸模型参数信息包括：人脸形状信息、人脸表情信息和人脸姿态信息。
进一步地，所述处理模块具体用于，根据所述人脸形状信息和所述人脸表情信息对所述三维平均人脸模型进行处理，得到初始三维人脸模型；根据所述人脸姿态信息对所述初始三维人脸图像进行调整，得到所述人脸对应的三维人脸图像。
进一步地，所述识别模块具体用于，使用特征点识别算法得到第一预设数量的特征点，确定所述特征点信息的二维坐标位置；根据所述二维坐标位置得到代表所述特征点周围第二预设数量像素的第一人脸特征点信息。
本发明实施例的又一方面提供一种电子设备，包括：至少一个处理器；以及，与所述至少一个处理器通信连接的存储器；其中，
所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行本发明实施例上述任一项三维人脸图像生成方法。
上述电子设备可以是用于获取人脸图像的所述图像获取设备。
由以上技术方案可见，本发明实施例提供的三维人脸图像生成方法、装置及电子设备，无需采集多角度多张图像，仅需单张图像即可生成三维人脸图像；采用卷积神经网络图像，可自动生成更准确和更逼真的人脸表情和姿态，且无需硬件的支持，多方面降低成本。同时，通过改进图像获取设备的防抖结构，改善了图像获取质量。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明实施例中记载的一些实施例，对于本领域普通技术人员来讲，还可以根据这些附图获得其他的附图。
图1为本发明一个实施例提供的三维人脸图像生成方法流程图；
图2为本发明一个实施例提供的步骤S101的具体流程图；
图3为本发明一个实施例提供的步骤S103的具体流程图；
图4为本发明一个实施例提供的三维人脸图像生成装置结构图；
图5为本发明一个实施例提供的三维人脸图像生成装置结构图；
图6为执行本发明方法实施例提供的用于执行三维人脸图像生成方法的电子设 备的硬件结构示意图；
图7为本发明一个实施例提供的图像获取设备的结构图；
图8为本发明一个实施例提供的光学防抖器的结构图；
图9为图8的A部放大图；
图10为本发明一个实施例提供的微型记忆合金光学防抖器的活动板的底面示意图；
图11为本发明一个实施例提供的支架的结构图；
图12为本发明一个实施例提供的支架的一个状态示意图；
图13为本发明一个实施例提供的支架的另一个状态示意图；
图14为本发明一个实施例提供的安装座与手机相连接时的结构状态图。
具体实施方式
为了使本领域的人员更好地理解本发明实施例中的技术方案，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅是本发明实施例一部分实施例，而不是全部的实施例。基于本发明实施例中的实施例，本领域普通技术人员所获得的所有其他实施例，都应当属于本发明实施例保护的范围。
本发明实施例的执行主体为电子设备，所述电子设备包括但不限于手机、平板电脑、笔记本电脑、带摄像头的台式电脑等。下面结合附图，对本发明的一些实施方式作详细说明。在不冲突的情况下，下述的实施例及实施例中的特征可以相互结合。图1为本发明实施例提供的三维人脸图像生成方法流程图。如图1所示，本发明实施例提供的三维人脸图像生成方法，包括：
S101，对获取图像中的人脸进行识别，获取第一人脸特征点信息，所述人像特征点用于唯一标识所述人脸。
通常情况下，获取的人脸图像中会包含非人脸部分的图像，例如背景环境图像等，因此需要对图像中的人脸图像进行识别。在进行本步骤时，可以识别通过实时拍摄的方式获取的图像中的图像，也可以识别保存于终端本地的图像中的图像。第一人脸特征点信息包括但不限于人脸特征点在图像中的坐标参数值以及纹理参数(即RGB特征的纹理参数)。
许多识别人脸图像的识别方法，例如可以根据图像的边缘信息和/或颜色信息等识别出人脸图像的范围，在本实施例中，通过识别预先定义的关键点，基于检测到的关键点确定第一人脸特征点信息。例如，人脸图像中的眉毛、眼睛、鼻子、脸庞和嘴巴等分别有若干个所述关键点组成，即通过所述关键点的坐标位置能够确定所述人脸图像中的眉毛、眼睛、鼻子、脸庞和嘴巴的位置及纹理。
作为本步骤的一种可选实施方式，所述对图像中的人脸进行识别，获取第一人脸特征点信息，包括以下步骤：识别第一预设数量的特征点，确定所述特征点信息的二维坐标位置；根据所述特征点信息的二维坐标位置获得代表所述特征点周围第二预设数量像素的第一人脸特征点信息。
具体的：
利用现有技术中的人脸特征点识别算法来获取第一人脸特征点信息。对于人脸特征点识别算法的训练通常包括如下步骤：首先，获取一定数量的训练集，该训练集中为携带有人脸特征点信息的图像；其次，利用该训练集训练形成初始回归函数r0和初始训练集；再次，利用该初始训练集和初始回归函数r0迭代形成下一次训练集和回归函数rn；每次迭代回归函数均使用梯度提升算法进行学习，从而当第n次训练集与训练集中的人脸特征点信息满足收敛条件时，则其对应的回归函数rn即为训练完成的人脸特征点识别算法。
对图像进行人脸检测，得到人脸在图像中的位置，用范围矩形框标识人脸的范围，例如(左，上，右，下)。通过训练好的特征点识别算法中的回归函数对输入人像照片识别得到第一预设数量的特征点、以及每个第一人脸特征点坐标(x i，y i)，其中，i代表识别得到的第i个特征点，第一预设数量可以是68个,包括眉毛,眼睛,鼻子,嘴巴,脸庞的关键点。对每个第一人脸特征点，根据其坐标(x i，y i)形成一个代表该特征点周围第二预设数量像素的纹理参数(R i，G i，B i)。可选地，该第二预设数量可以是6个、8个等，本发明在此不做限定。
S102，根据所述第一人脸特征点信息和预先训练的卷积神经网络模型，得到第一三维人脸模型参数信息。
具体地，卷积神经网络CNN是一种深度前馈人工神经网络。CNN的基本结构包括两层，其一为特征提取层，每个神经元的输入与前一层的局部接受域相连，并提取该局部的特征，一旦该局部特征被提取后，它与其它特征间的位置关系也随之确定下来；其二是特征映射层，网络的每个计算层由多个特征映射组成，每个特征映射是一个平面，平面上所有神经元的权值相等。卷积神经网络通常包括一维卷积神经网络、二维卷积神经网络和三维卷积神经网络，现有技术已有这些卷积神经网络数学模型的大量介绍，此处不再赘述，也不对卷积神经网络的类型进行限定。
如图2所示，对卷积神经网络模型的训练可以包括如下步骤：
S201，搭建由两层沙漏型卷积神经网络组成的卷积神经网络模型。
S202，获取用于训练所述卷积神经网络模型的数据集，所述数据集中包括若干二维人脸图像和所述二维人脸图像对应的三维人像扫描数据。
需要说明是，步骤S1021和步骤S1022没有先后顺序的限制，可以先获取数据集、再进行卷积神经网络模型的搭建，也可以先进行卷及神经网络模型的搭建、在获取数据集，本发明在此不做限制。
具体来说，本步骤中获取输入样本数据集的方式包括从互联网上直接下载图像作为输入样本数据集，以及人为拍摄图像作为输入样本数据集，其中人为拍摄的图像可以包括不同种族的人的图像、不同光影效果的人的图像。三维人像扫描数据主要包括人脸的姿态信息(比如人脸的倾斜角度、偏转角度、转动角度等、人脸特征点的形状参数以及人脸特征点的表情参数。
S203，对所述二维人脸图像进行预处理得到第二人脸特征点信息。
具体地，可以利用步骤S101中介绍的方法得到二维人脸图像的第二人脸特征点信息，即获取得到第二人脸特征点坐标(x i，y i)以及该特征点对应的纹理参数(R i，G i，B i)，其中，i代表识别得到的第i个特征点。
S204，将所述第二人脸特征点信息输入至所述卷积神经网络模型得到第二三维人脸模型参数信息。
在本步骤中，每次输入给卷积神经网络模型的是第二人脸特征点信息，该第二人脸特征点信息可以反映当前人脸形状的信息，输出为第二三维人脸模型参数p。该算法使用卷积神经网络拟合从输入到输出的映射函数，网络结构包含了4个卷积层，3个池化层和2个全连接层。通过级联多个卷积神经网络直至在训练集上收敛，根据当前预测的人脸形状更新，并作为下一级卷积神经网络的输入。
该网络的前两个卷积层通过权值共享的方法抽取面部特征，后两个卷积层通过局部感知抽取面部特征，进一步回归一个256维空间的特征向量，输出的一个234维空间的特征向量，第二三维人脸模型参数p。其中包括人脸姿态参数[f,pitch,yaw,roll,t 2dx,t 2dy]，形状参数α id，表情参数α exp。其中，f是比例因子、pitch为倾斜角度、yaw为偏转角度、roll为转动角度，t 2dx、t 2dy是偏置项。
S205，利用交叉熵损失函数对所述卷积神经网络的参数进行优化，直至所述第二三维人脸模型参数信息与所述三维人像扫描数据的损失函数收敛到预设阈值。
在深度学习中，损失函数是模型数据拟合程度的反映，当拟合的结果越差，损失函数的值就会越大。总体上来看，在经过k(k＝0,1,...K)次迭后，经过一个初始化的参数的变化后会得到参数p k，根据上述三维人像扫描数据训练一个神经网络Net K来预测参数p，不断的更新p k。该网络用数学公式表示如下：
Δp k＝Net K(I，PNCC(p k))
经过网络模型的每一次迭代都会得到一个更好的参数p k+1＝p k+Δp k作为下一层网络的输入，其中的结构和Net K一样，直至p k+1与所述三维人像扫描数据的损失函数收敛到预设阈值，说明卷积神经网络模型训练完成。本实施例使用的交叉熵损失函数优化法属于本领域常用算法，具体过程在此不再赘述。
S103，根据所述第一三维人脸模型参数信息对三维平均人脸模型进行处理，得到所述人脸对应的三维人脸图像。
人脸共性较多。正常人脸都是有一个鼻子、两只眼睛、一个嘴巴、两只耳朵， 从上到下，从左到右顺序都不变，所以可以首先建三维平均人脸模型，因为人脸的相似性较大，总是可以从一张正常人脸变化到另外一张正常人脸，通过计算变化量来改变平均人脸模型，所以这也就是三维人脸重建的基础。
具体地，如图3所示，本步骤可以通过如下子步骤实现：
步骤S1031，根据所述人脸形状信息和所述人脸表情信息对所述三维平均人脸模型进行处理，得到初始三维人脸模型。
具体地，可以根据如下公式进行处理：
S＝S 0+A id*α id+A exp*α exp
上式中S是初始三维人脸模型，S 0是平均人脸模型，A id是形状的基向量，α id是形状参数，A exp是表情的基向量，α exp是表情参数。A exp和A exp可通过现有算法预先求得。
S1032，根据所述人脸姿态信息对所述初始三维人脸图像进行调整，得到所述人脸对应的三维人脸图像。
具体地，初始三维人脸模型通过弱透视投影将人脸模型投影到图像平面上，得到所述人脸对应的三维人脸图像，公式表示如下：
V(p)＝F*Pr*R(S 0+A idα id+A expα exp)+t 2d
上式中V(p)就是重建的所述人脸对应的三维人脸图像，f是比例因子，Pr是直角投影矩阵，R是旋转矩阵，由倾斜角度(pitch)、偏转角度(yaw)、转动角度(roll)组成，是根据特征点识别到的二维图像中人脸的姿态信息得到的。
本发明实施例提供的三维人脸图像生成方法，仅需单张图像即可生成三维人脸图像；采用卷积神经网络图像，可自动生成更准确和更逼真的人脸表情和姿态，且无需硬件的支持，多方面降低成本。
图4为本发明实施例提供的三维人脸图像生成装置结构图。如图4所示，该装置具体包括：识别模块100，输出模块200和处理模块300。其中，
识别模块100，用于对获取图像中的人脸进行识别，获取第一人脸特征点信息，所述人像特征点用于唯一标识所述人脸；输出模块200，用于根据所述第一人脸特征点信息和预先训练的卷积神经网络模型，得到第一三维人脸模型参数信息；处理模块300，用于根据所述第一三维人脸模型参数信息对三维平均人脸模型进行处理，得到所述人脸对应的三维人脸图像。
本发明实施例提供的三维人脸图像生成装置具体用于执行图1所示实施例提供的所述方法，其实现原理、方法和功能用途等与图1所示实施例类似，在此不再赘述。
图5为本发明实施例提供的三维人脸图像生成装置结构图。如图5所示，该装置具体包括：训练模块400、识别模块200，输出模块300和处理模块400。其中，
训练模块400包括：搭建单元410，用于搭建由两层沙漏型卷积神经网络组成的卷积神经网络模型；获取单元420，用于获取用于训练所述卷积神经网络模型的数据集，所述数据集中包括若干二维人脸图像和所述二维人脸图像对应的三维人像扫描数据；预处理单元430，用于对所述二维人脸图像进行预处理得到第二人脸特征点信息；输入单元440，用于将所述第二人脸特征点信息输入至所述卷积神经网络模型得到第二三维人脸模型参数信息；优化单元450，用于利用交叉熵损失函数对所述卷积神经网络的参数进行优化，直至所述第二三维人脸模型参数信息与所述三维人像扫描数据的损失函数收敛到预设阈值。
识别模块200，用于对图像中的人脸进行识别，获取第一人脸特征点信息，所述人像特征点用于唯一标识所述人脸；输出模块300，用于根据所述第一人脸特征点信息和预先训练的卷积神经网络模型，得到第一三维人脸模型参数信息；处理模块400，用于根据所述第一三维人脸模型参数信息对三维平均人脸模型进行处理，得到所述人脸对应的三维人脸图像。
可选地，所述第一三维人脸模型参数信息包括：人脸形状信息、人脸表情信息和人脸姿态信息。
可选地，处理模块400具体用于，根据所述人脸形状信息和所述人脸表情信息对所述三维平均人脸模型进行处理，得到初始三维人脸模型；根据所述人脸姿态信息对所述初始三维人脸图像进行调整，得到所述人脸对应的三维人脸图像。
可选地，识别模块200具体用于，使用特征点识别算法得到第一预设数量的特征点，确定所述特征点信息的二维坐标位置；根据所述二维坐标位置得到代表所述特征点周围第二预设数量像素的第一人脸特征点信息，具体参见方法实施例。
本发明实施例提供的三维人脸图像生成装置具体用于执行图1-图3所示实施例提供的所述方法，其实现原理、方法和功能用途和图1-图3所示实施例类似，在此不再赘述。
上述这些本发明实施例的三维人脸图像生成装置可以作为其中一个软件或者硬件功能单元，独立设置在上述电子设备中，也可以作为整合在处理器中的其中一个功能模块，执行本发明实施例的三维人脸图像生成方法。
图6为执行本发明方法实施例提供的用于执行三维人脸图像生成方法的电子设备的硬件结构示意图。根据图6所示，该电子设备包括：
一个或多个处理器610以及存储器620，图6中以一个处理器610为例。
执行所述的三维人脸图像生成方法的设备还可以包括：输入装置630和输出装置630。
处理器610、存储器620、输入装置630和输出装置640可以通过总线或者其他方式连接，图6中以通过总线连接为例。
存储器620作为一种非易失性计算机可读存储介质，可用于存储非易失性软件 程序、非易失性计算机可执行程序以及模块，如本发明实施例中的所述三维人脸图像生成方法对应的程序指令/模块。处理器610通过运行存储在存储器620中的非易失性软件程序、指令以及模块，从而执行服务器的各种功能应用以及数据处理，即实现所述三维人脸图像生成方法。
存储器620可以包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需要的应用程序；存储数据区可存储根据本发明实施例提供的三维人脸图像生成装置的使用所创建的数据等。此外，存储器620可以包括高速随机存取存储器620，还可以包括非易失性存储器620，例如至少一个磁盘存储器620件、闪存器件、或其他非易失性固态存储器620件。在一些实施例中，存储器620可选包括相对于处理器66远程设置的存储器620，这些远程存储器620可以通过网络连接至所述三维人脸图像生成装置。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
输入装置630可接收输入的数字或字符信息，以及产生与三维人脸图像生成装置的用户设置以及功能控制有关的键信号输入。输入装置630可包括按压模组等设备。
所述一个或者多个模块存储在所述存储器620中，当被所述一个或者多个处理器610执行时，执行所述三维人脸图像生成方法。
本发明实施例的电子设备以多种形式存在，包括但不限于:
(1)移动通信设备:这类设备的特点是具备移动通信功能，并且以提供话音、数据通信为主要目标。这类终端包括:智能手机(例如iPhone)、多媒体手机、功能性手机，以及低端手机等。
(2)超移动个人计算机设备:这类设备属于个人计算机的范畴，有计算和处理功能，一般也具备移动上网特性。这类终端包括:PDA、MID和UMPC设备等，例如iPad。
(3)便携式娱乐设备:这类设备可以显示和播放多媒体内容。该类设备包括:音频、视频播放器(例如iPod)，掌上游戏机，电子书，以及智能玩具和便携式车载导航设备。
(4)其他具有数据交互功能的电子装置。
优选的，所述电子设备上设置有用于获取图像的图像获取设备，图像获取设备上为保证获取图像的质量往往设置有软件或硬件防抖器。现有的防抖器大多由通电线圈在磁场中产生洛伦磁力驱动镜头移动，而要实现光学防抖，需要在至少两个方向上驱动镜头，这意味着需要布置多个线圈，会给整体结构的微型化带来一定挑战，而且容易受外界磁场干扰，进而影响防抖效果，因此公开号为CN106131435A的中国专利提供了一种微型光学防抖摄像头模组，其通过温度变化实现记忆合金丝的拉伸和缩短，以此拉动自动聚焦音圈马达移动，实现镜头的抖动补偿，微型记忆合金光学防抖致动器的控制芯片可以控制驱动信号的变化来改变记忆合金丝的温度，以此控制记忆合金丝的伸长和缩短，并且根据记忆合金丝的电阻来计算致动器的位置和移 动距离。当微型记忆合金光学防抖致动器上移动到指定位置后反馈记忆合金丝此时的电阻，通过比较这个电阻值与目标值的偏差，可以校正微型记忆合金光学防抖致动器上的移动偏差。
但是申请人发现，由于抖动的随机性和不确定性，仅仅依靠上述技术方案的结构是无法实现在多次抖动发生的情况下能够对镜头进行精确的补偿，这是由于形状记忆合金的升温和降温均需要一定的时间，当抖动向第一方向发生时，上述技术方案可以实现镜头对第一方向抖动的补偿，但是当随之而来的第二方向的抖动发生时，由于记忆合金丝来不及在瞬间变形，因此容易造成补偿不及时，无法精准实现对多次抖动和不同方向的连续抖动的镜头抖动补偿，因此需要对其结构上进行改进，以期获得更好的图像质量，从而便于后续三维图像的生成。
结合附图8-10所示，本实施例对学防抖器进行改进，将其设计为机械防抖器3000，其具体结构如下：
本实施例的所述机械防抖器3000包括活动板3100、基板3200以及补偿机构3300，所述活动板3100和所述基板3200的中部均设有所述镜头1000穿过的通孔，所述自动聚焦音圈马达2000安装在所述活动板3100上，所述活动板3100安装在所述基板3200上，且所述基板3200的尺寸大于所述活动板3100，所述活动板3100通过其上方的自动聚焦音圈马达限位其上下的移动，所述补偿机构3300在所述处理模块的驱动下带动所述活动板3100和活动板3100上的镜头1000动作，以实现镜头1000的抖动补偿。
具体的，本实施例的所述补偿机构3300包括安装在所述基板3200四周的第一补偿组件3310、第二补偿组件3320、第三补偿组件3330以及第四补偿组件3340，其中所述第一补偿组件3310和所述第三补偿组件3330相对设置，所述第二补偿组件3320与所述第四补偿组件3340相对设置，所述第一补偿组件3310与第三补偿组件3330之间的连线与所述第一补偿组件3310与第三补偿组件3330之间的连线相互垂直，即一补偿组件、第二补偿组件3320、第三补偿组件3330分别布设在活动板3100的前后左右四个方位，第一补偿组件3310可使得活动板3100向前运动，第三补偿组件3330可使得活动板3100向后运动，第二补偿组件3320可使得活动板3100向左运动，第四补偿组件3340可使得活动板3100向左运动，而且第一补偿组件3310可以与第二补偿组件3320或者第四补偿组件3340相配合实现活动板3100向倾斜方向的运动，第三补偿组件3330也可以与第二补偿组件3320或者第四补偿组件3340相配合实现活动板3100向倾斜方向的运动，实现可以对镜头1000在各个抖动方向上的补偿。
具体的，本实施例的所述第一补偿组件3310、第二补偿组件3320、第三补偿组件3330以及第四补偿组件3340均包括驱动件3301、转轴3302、单向轴承3303以及转动齿圈3304。所述驱动件3301受控于所述处理模块，所述驱动件3301与所述转 轴3302传动连接，以带动所述转轴3302转动。所述转轴3302与所述单向轴承3303的内圈相连接，以带动所述单向轴承3303的内圈转动；所述转动齿圈3304套设在所述单向轴承3303上并与所述单向轴承3303的外圈固定连接，所述转动齿圈3304的外表面沿其周向设有一圈外齿，所述活动板3100的底面设有多排均匀间隔布设的条形槽3110，所述条形槽3110与所述外齿相啮合，且所述外齿可沿所述条形槽3110的长度方向滑动；其中，所述第一补偿组件3310的单向轴承3303的可转动方向与所述第三补偿组件3330的单向轴承3303的可转动方向相反，所述第二补偿组件3320的单向轴承3303的可转动方向与所述第四补偿组件3340的单向轴承3303的可转动方向相反。
单向轴承3303是在一个方向上可以自由转动，而在另一个方向上锁死的一种轴承，当需要使得活动板3100向前移动时，第一补偿组件3310的驱动件3301使得转轴3302带动单向轴承3303的内圈转动，此时，单向轴承3303处于锁死状态，因此单向轴承3303的内圈可以带动外圈转动，进而带动转动齿圈3304转动，转动齿圈3304通过与条形槽3110的啮合带动活动板3100向可以补偿抖动的方向运动；当抖动补偿后需要活动板3100复位时，可以通过第三补偿组件3330带动活动板3100转动，第三补偿组件3330的运行过程过程与第一补偿组件3310同理，此时，第一补偿组件3310的单向轴承3303处于可转动状态，因此第一补偿组件3310上的齿圈为与活动板3100随动状态，不会影响活动板3100的复位。
优选的，为了降低整个机械防抖器3000的整体厚度，本实施例在所述固定板的四周开设有四个贯穿的安装孔(图中未示出)，所述安装孔上安装有所述单向轴承3303和所述转动齿圈3304，通过将单向轴承3303和转动齿圈3304的部分隐藏在安装孔内，以降低整个机械防抖器3000的整体厚度。或者直接将整个补偿组件的部分置于所述安装孔内。
具体，本实施例的所述驱动件3301可以是微型电机，所述微型电机与所述处理模块电连接，所述微型电机的转动输出端与所述转轴3302相连接，所述微型电机受控于所述处理模块。或者，所述驱动件3301由记忆合金丝和曲柄连杆组成，所述记忆合金丝一端固定于所述固定板上，并与所述处理模块通过电路相连接，所述记忆合金丝另一端通过所述曲柄连杆与所述转轴3302相连接，以带动所述转轴3302转动，具体为处理模块根据陀螺仪的反馈计算出记忆合金丝的伸长量，并驱动相应的电路对该形状记忆合金丝进行升温，该形状记忆合金丝伸长带动曲柄连杆机构运动，曲柄连杆机构的曲柄带动转轴3302转动，使得单向轴承3303的内圈转动，单向轴承3303处于锁死状态时，内圈带动外圈转动，转动齿圈3304通过条形槽3110带动活动板3100运动。
下面结合上述结构对本实施例的机械防抖器3000的工作过程进行详细的描述，以镜头1000两次抖动为例，两次抖动方向相反，且需要使得活动板3100向前运动补 偿一次，并随后向左运动补偿一次。需要活动板3100向前运动补偿时，陀螺仪事先将检测到的镜头1000抖动方向和距离反馈给所述处理模块，处理模块计算出需要活动板3100的运动距离，进而驱动第一补偿组件3310的驱动件3301使得转轴3302带动单向轴承3303的内圈转动，此时，单向轴承3303处于锁死状态，因此内圈可以带动外圈转动，进而带动转动齿圈3304转动，转动齿圈3304通过条形槽3110带动活动板3100向前运动，随后第三补偿组件3330带动活动板3100复位。需要活动板3100向左运动补偿时，陀螺仪事先将检测到的镜头1000抖动方向和距离反馈给所述处理模块，处理模块计算出需要活动板3100的运动距离，进而驱动第二补偿组件3320的驱动件3301使得转轴3302带动单向轴承3303的内圈转动，此时，单向轴承3303处于锁死状态，因此内圈可以带动外圈转动，进而带动转动齿圈3304转动，转动齿圈3304通过条形槽3110带动活动板3100向前运动，而且由于转动齿圈3304的外齿可沿所述条形槽3110的长度方向滑动，在活动板3100向左运动时，活动板3100与第一补偿组件3310和第三补偿组件3330之间为滑动配合，不会影响活动板3100向左运动，在补偿结束后，再通过第四补偿组件3340带动活动板3100复位。
当然上述仅仅为简单的两次抖动，当发生多次抖动时，或者抖动的方向并非往复运动时，可以通过驱动多个补偿组件以补偿抖动，其基础工作过程与上述描述原理相同，这里不过多赘述，另外关于形状记忆合金电阻的检测反馈、陀螺仪的检测反馈等均为现有技术，这里也不过多描述。
结合上述说明可知，本实施例提供的机械补偿器不仅不会受到外界磁场干扰，防抖效果好，而且可以实现在多次抖动发生的情况下能够对镜头1000进行精确的补偿，补偿及时准确，大大改善改了获取图像的质量，简化了后续三维图像的处理难度。
进一步地，本实施例的电子设备具体为带有所述图像获取设备的手机，该手机包括支架。手机包含支架的目的是由于图像获取环境的不确定性，因此需要使用支架对手机进行支撑和固定，以期获得更稳定的图像质量。
另外，申请人发现，现有的手机支架仅仅具有支撑手机的功能，而不具有自拍杆的功能，因此申请人对支架做出第一步改进，将手机支架6000和支撑杆6200相结合，结合附图11所示，本实施例的所述支架6000包括手机安装座6100和可伸缩的支撑杆6200，支撑杆6200与手机安装座6100的中部(具体为下述基板3200的中部)通过阻尼铰链相连接，使得支撑杆6200在转动至图12的状态时，支架6000可形成自拍杆结构，而支撑杆6200在转动至图13的状态时，支架6000可形成手机支架6000结构。
而结合上述支架结构申请人又发现，手机安装座6100与支撑杆6200结合后占用空间较大，即使支撑杆6200可伸缩，但是手机安装座6100无法进行结构的变化，体积不会进一步缩小，无法将其放入衣兜或者小型的包内，造成支架6000携带不便的问题，因此本实施例对支架6000做出第二步改进，使得支架6000的整体收容性得到 进一步的提高。
结合图12-14所示，本实施例的所述手机安装座6100包括可伸缩的连接板6110和安装于连接板6110相对两端的折叠板组6120，所述支撑杆6200与所述连接板6110中部通过阻尼铰链相连接；所述折叠板组6120包括第一板体6121、第二板体6122及第三板体6123，其中，所述第一板体6121的相对两端中的一端与所述连接板6110相铰接，所述第一板体6121的相对两端中的另一端与所述第二板体6122的相对两端中的一端相铰接；所述第二板体6122相对两端的另一端与所述第三板体6123相对两端中的一端相铰接；所述第二板体6122设有供手机边角插入的开口6130。
结合附图14所示，所述手机安装座6100用于安装手机时，所述第一板体6121、第二板体6122和第三板体6123折叠呈直角三角形状态，所述第二板体6122为直角三角形的斜边，所述第一板体6121和所述第三板体6123为直角三角形的直角边，其中，所述第三板体6123的一个侧面与所述连接板6110的一个侧面并排贴合，所述第三板体6123相对两端中的另一端与所述第一板体6121相对两端中的一端相抵，该结构可以使得三个折叠板处于自锁状态，并且将手机下部的两个边角插入到两侧的两个开口6130时，手机5000的下部两侧位于两个直角三角形内，通过手机、连接板6110和折叠板组6120件的共同作可以完成手机5000的固定，三角形状态在外力情况下无法打开，只有从开口6130抽出手机后才能解除折叠板组6120件的三角形状态。
而在手机安装座6100不处于工作状态时，将连接板6110缩小至最小长度，并且将折叠板组6120件与连接板6110相互折叠，用户可以将手机安装座6100折叠呈最小体积，而由于支撑杆6200的可伸缩性，因此可以将整个支架6000收容呈体积最小的状态，提高了支架6000的收荣幸，用户甚至可以直接将支架6000放入衣兜或小的手包内，十分方便。
优选的，本实施例还在所述第三板体6123的一个侧面设有第一连接部，所述连接板6110与所述第三板体6123相贴合的侧面设有与所述第一连接部相配合的第一配合部，所述支架6000手机安装座6100用于安装手机时，所述第一连接部和所述第一配合部卡合连接。具体的，本实施例的第一连接部为一个凸条或凸起(图中未示出)，第一配合部为开设在连接板6110上的卡槽(图中未示出)。该结构不仅提高了折叠板组6120件处于三角形状态时的稳定性，而且在需要将手机安装座6100折叠至最小状态时也便于折叠板组6120件与连接板6110的连接。
优选的，本实施例还在所述第一板体6121相对两端中的一端设有第二连接部，所述第三板体6123相对两端中的另一端设有与所述第二连接部相配合的第二配合部，所述支架6000手机安装座6100用于安装手机时，所述第二连接部和所述第二配合部卡合连接。第二连接部可以是凸起(图中未示出)，第二配合部为与凸起相配合的开口6130或卡槽(图中未示出)。该结构提高了叠板组件处于三角形状态时的稳定性
另外，本实施例还可以在所述支撑杆6200的另一端可拆卸连接有底座(图中未示出)，在需要固定手机并且使手机5000具有一定高度时，可以将支撑杆6200拉伸呈一定长度，并通过底座将支架6000置于一个平面上，再将手机放置到手机安装座6100内，完成手机的固定；而支撑杆6200和底座的可拆卸连接可以使得两者可以单独携带，进一步提高了支架6000的收容性和携带的方便性。
以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的模块可以是或者也可以不是物理上分开的，作为模块显示的部件可以是或者也可以不是物理模块，即可以位于一个地方，或者也可以分布到多个网络模块上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性的劳动的情况下，即可以理解并实施。
本发明实施例提供了一种非暂态计算机可读存存储介质，所述计算机存储介质存储有计算机可执行指令，其中，当所述计算机可执行指令被电子设备执行时，使所述电子设备上执行上述任意方法实施例中的三维人脸图像生成方法。
本发明实施例提供了一种计算机程序产品，其中，所述计算机程序产品包括存储在非暂态计算机可读存储介质上的计算机程序，所述计算机程序包括程序指令，其中，当所述程序指令被电子设备执行时，使所述电子设备执行上述任意方法实施例中的三维人脸图像生成方法。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到各实施方式可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件。基于这样的理解，上述技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品可以存储在计算机可读存储介质中，所述计算机可读记录介质包括用于以计算机(例如计算机)可读的形式存储或传送信息的任何机制。例如，机器可读介质包括只读存储器(ROM)、随机存取存储器(RAM)、磁盘存储介质、光存储介质、闪速存储介质、电、光、声或其他形式的传播信号(例如，载波、红外信号、数字信号等)等，该计算机软件产品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)执行各个实施例或者实施例的某些部分所述的方法。
最后应说明的是：以上实施例仅用以说明本发明实施例的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的精神和范围。

Claims (10)

  1. 一种三维人脸图像生成方法，其特征在于，包括：
    对获取图像中的人脸进行识别，获取第一人脸特征点信息，所述人像特征点用于唯一标识所述人脸；
    根据所述第一人脸特征点信息和预先训练的卷积神经网络模型，得到第一三维人脸模型参数信息；
    根据所述第一三维人脸模型参数信息对预先获得的三维平均人脸模型进行处理，得到所述人脸对应的三维人脸图像。
  2. 根据权利要求1所述的方法，其特征在于，所述卷积神经网络模型的训练过程包括如下步骤：
    搭建由两层沙漏型卷积神经网络组成的卷积神经网络模型；
    获取用于训练所述卷积神经网络模型的数据集，所述数据集中包括若干二维人脸图像和所述二维人脸图像对应的三维人像扫描数据；
    对所述二维人脸图像进行预处理得到第二人脸特征点信息；
    将所述第二人脸特征点信息输入至所述卷积神经网络模型得到第二三维人脸模型参数信息；
    利用交叉熵损失函数对所述卷积神经网络的参数进行优化，直至所述第二三维人脸模型参数信息与所述三维人像扫描数据的损失函数收敛到预设阈值。
  3. 根据权利要求1或2所述的方法，其特征在于，所述第一三维人脸模型参数信息包括：人脸形状信息、人脸表情信息和人脸姿态信息。
  4. 根据权利要求3所述的方法，其特征在于，所述根据所述三维人脸模型参数信息对预先获得的三维平均人脸模型进行处理，得到所述人脸对应的三维人脸图像，包括：
    根据所述人脸形状信息和所述人脸表情信息对所述三维平均人脸模型进行处理，得到初始三维人脸模型；
    根据所述人脸姿态信息对所述初始三维人脸图像进行调整，得到所述人脸对应的三维人脸图像。
  5. 根据权利要求1或2所述的方法，其特征在于，所述对图像中的人脸进行识别，获取第一人脸特征点信息，包括：
    识别第一预设数量的特征点，确定所述特征点信息的二维坐标位置；
    根据所述二维坐标位置获得代表所述特征点周围第二预设数量像素的第一人脸特征点信息。
  6. 一种三维人脸图像生成装置，其特征在于，包括：
    识别模块，用于对获取图像中的人脸进行识别，获取第一人脸特征点信息，所 述人像特征点用于唯一标识所述人脸；
    输出模块，用于根据所述第一人脸特征点信息和预先训练的卷积神经网络模型，得到第一三维人脸模型参数信息；
    处理模块，用于根据所述第一三维人脸模型参数信息对预先获得的三维平均人脸模型进行处理，得到所述人脸对应的三维人脸图像。
  7. 根据权利要求6所述的装置，其特征在于，所述装置还包括卷积神经网络模型训练模块，所述卷积神经网络模型训练模块包括：
    搭建单元，用于搭建由两层沙漏型卷积神经网络组成的卷积神经网络模型；
    获取单元，用于获取用于训练所述卷积神经网络模型的数据集，所述数据集中包括若干二维人脸图像和所述二维人脸图像对应的三维人像扫描数据；
    预处理单元，用于对所述二维人脸图像进行预处理得到第二人脸特征点信息；
    输入单元，用于将所述第二人脸特征点信息输入至所述卷积神经网络模型得到第二三维人脸模型参数信息；
    优化单元，用于利用交叉熵损失函数对所述卷积神经网络的参数进行优化，直至所述第二三维人脸模型参数信息与所述三维人像扫描数据的损失函数收敛到预设阈值。
  8. 根据权利要求6或7所述的装置，其特征在于，所述第一三维人脸模型参数信息包括：人脸形状信息、人脸表情信息和人脸姿态信息。
  9. 根据权利要求8所述的装置，其特征在于，所述处理模块具体用于，根据所述人脸形状信息和所述人脸表情信息对所述三维平均人脸模型进行处理，得到初始三维人脸模型；根据所述人脸姿态信息对所述初始三维人脸图像进行调整，得到所述人脸对应的三维人脸图像。
  10. 一种电子设备，其特征在于，包括：至少一个处理器；以及，
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行权利要求1至5中任一项所述的三维人脸图像生成方法。
PCT/CN2018/102329 2018-08-24 2018-08-24 三维人脸图像生成方法、装置及电子设备 WO2020037676A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2018/102329 WO2020037676A1 (zh) 2018-08-24 2018-08-24 三维人脸图像生成方法、装置及电子设备
CN201811020071.2A CN109255827A (zh) 2018-08-24 2018-09-03 三维人脸图像生成方法、装置及电子设备

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/102329 WO2020037676A1 (zh) 2018-08-24 2018-08-24 三维人脸图像生成方法、装置及电子设备

Publications (1)

Publication Number Publication Date
WO2020037676A1 true WO2020037676A1 (zh) 2020-02-27

Family

ID=65050494

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/102329 WO2020037676A1 (zh) 2018-08-24 2018-08-24 三维人脸图像生成方法、装置及电子设备

Country Status (2)

Country Link
CN (1) CN109255827A (zh)
WO (1) WO2020037676A1 (zh)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111428579A (zh) * 2020-03-03 2020-07-17 平安科技（深圳）有限公司 人脸图像的获取方法与系统
CN111860101A (zh) * 2020-04-24 2020-10-30 北京嘀嘀无限科技发展有限公司 一种人脸关键点检测模型的训练方法及装置
CN111968203A (zh) * 2020-06-30 2020-11-20 北京百度网讯科技有限公司 动画驱动方法、装置、电子设备及存储介质
CN112614213A (zh) * 2020-12-14 2021-04-06 杭州网易云音乐科技有限公司 人脸表情确定方法、表情参数确定模型、介质及设备
RU2757563C1 (ru) * 2021-02-19 2021-10-18 Самсунг Электроникс Ко., Лтд. Способ визуализации 3d портрета человека с измененным освещением и вычислительное устройство для него
CN113963425A (zh) * 2021-12-22 2022-01-21 北京的卢深视科技有限公司 人脸活体检测系统的测试方法、装置及存储介质
CN116091704A (zh) * 2023-03-15 2023-05-09 广州思涵信息科技有限公司 一种远程人体三维图像重构方法
US11823327B2 (en) 2020-11-19 2023-11-21 Samsung Electronics Co., Ltd. Method for rendering relighted 3D portrait of person and computing device for the same

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109978930B (zh) * 2019-03-27 2020-11-10 杭州相芯科技有限公司 一种基于单幅图像的风格化人脸三维模型自动生成方法
CN110533777B (zh) * 2019-08-01 2020-09-15 北京达佳互联信息技术有限公司 三维人脸图像修正方法、装置、电子设备和存储介质
CN110795584B (zh) * 2019-09-19 2022-03-25 深圳云天励飞技术有限公司 一种用户标识生成方法、装置及终端设备
CN111144284B (zh) * 2019-12-25 2021-03-30 支付宝(杭州)信息技术有限公司 深度人脸图像的生成方法、装置、电子设备及介质
CN113128292A (zh) * 2019-12-31 2021-07-16 Tcl集团股份有限公司 一种图像识别方法、存储介质及终端设备
CN112884881B (zh) * 2021-01-21 2022-09-27 魔珐(上海)信息科技有限公司 三维人脸模型重建方法、装置、电子设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104573628A (zh) * 2014-12-02 2015-04-29 苏州福丰科技有限公司 一种三维人脸识别方法
CN106067190A (zh) * 2016-05-27 2016-11-02 俞怡斐 一种基于单幅图像的快速人脸三维模型生成和变换方法
CN107122705A (zh) * 2017-03-17 2017-09-01 中国科学院自动化研究所 基于三维人脸模型的人脸关键点检测方法
CN107292950A (zh) * 2017-06-08 2017-10-24 深圳市唯特视科技有限公司 一种基于深度神经网络的端到端三维人脸重建方法

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108229268A (zh) * 2016-12-31 2018-06-29 商汤集团有限公司 表情识别及卷积神经网络模型训练方法、装置和电子设备
CN108230235B (zh) * 2017-07-28 2021-07-02 北京市商汤科技开发有限公司 一种视差图生成系统、方法及存储介质
CN108197602B (zh) * 2018-01-30 2020-05-19 厦门美图之家科技有限公司 一种卷积神经网络生成方法及表情识别方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104573628A (zh) * 2014-12-02 2015-04-29 苏州福丰科技有限公司 一种三维人脸识别方法
CN106067190A (zh) * 2016-05-27 2016-11-02 俞怡斐 一种基于单幅图像的快速人脸三维模型生成和变换方法
CN107122705A (zh) * 2017-03-17 2017-09-01 中国科学院自动化研究所 基于三维人脸模型的人脸关键点检测方法
CN107292950A (zh) * 2017-06-08 2017-10-24 深圳市唯特视科技有限公司 一种基于深度神经网络的端到端三维人脸重建方法

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111428579A (zh) * 2020-03-03 2020-07-17 平安科技（深圳）有限公司 人脸图像的获取方法与系统
CN111860101A (zh) * 2020-04-24 2020-10-30 北京嘀嘀无限科技发展有限公司 一种人脸关键点检测模型的训练方法及装置
CN111968203A (zh) * 2020-06-30 2020-11-20 北京百度网讯科技有限公司 动画驱动方法、装置、电子设备及存储介质
CN111968203B (zh) * 2020-06-30 2023-11-14 北京百度网讯科技有限公司 动画驱动方法、装置、电子设备及存储介质
US11823327B2 (en) 2020-11-19 2023-11-21 Samsung Electronics Co., Ltd. Method for rendering relighted 3D portrait of person and computing device for the same
CN112614213A (zh) * 2020-12-14 2021-04-06 杭州网易云音乐科技有限公司 人脸表情确定方法、表情参数确定模型、介质及设备
CN112614213B (zh) * 2020-12-14 2024-01-23 杭州网易云音乐科技有限公司 人脸表情确定方法、表情参数确定模型、介质及设备
RU2757563C1 (ru) * 2021-02-19 2021-10-18 Самсунг Электроникс Ко., Лтд. Способ визуализации 3d портрета человека с измененным освещением и вычислительное устройство для него
CN113963425A (zh) * 2021-12-22 2022-01-21 北京的卢深视科技有限公司 人脸活体检测系统的测试方法、装置及存储介质
CN116091704A (zh) * 2023-03-15 2023-05-09 广州思涵信息科技有限公司 一种远程人体三维图像重构方法
CN116091704B (zh) * 2023-03-15 2023-06-13 广州思涵信息科技有限公司 一种远程人体三维图像重构方法

Also Published As

Publication number Publication date
CN109255827A (zh) 2019-01-22

Similar Documents

Publication Publication Date Title
WO2020037676A1 (zh) 三维人脸图像生成方法、装置及电子设备
WO2020037679A1 (zh) 视频处理方法、装置及电子设备
WO2020037680A1 (zh) 基于光线的三维人脸优化方法、装置及电子设备
WO2020037678A1 (zh) 基于遮挡图像生成三维人脸图像方法、装置及电子设备
US11682155B2 (en) Skeletal systems for animating virtual avatars
US11669726B2 (en) Methods and systems for interpolation of disparate inputs
KR20210123399A (ko) 인공 지능에 기초한 애니메이션 이미지 구동 방법, 및 관련 디바이스
US11670032B2 (en) Pose space dimensionality reduction for pose space deformation of a virtual character
US11557076B2 (en) Computer generated hair groom transfer tool
CN108966017B (zh) 视频生成方法、装置及电子设备
CN108596827A (zh) 三维人脸模型生成方法、装置及电子设备
US11836840B2 (en) Systems and methods for cross-application authoring, transfer, and evaluation of rigging control systems for virtual characters
CN112116589B (zh) 虚拟形象的评测方法、装置、设备及计算机可读存储介质
CN112669422A (zh) 仿真3d数字人生成方法、装置、电子设备及存储介质
WO2020056692A1 (zh) 一种信息交互方法、装置及电子设备
WO2020056691A1 (zh) 一种交互对象的生成方法、装置及电子设备
CN115147339A (zh) 人体关键点检测方法及相关装置
US20230260156A1 (en) Methods and systems for interpolation of disparate inputs
US11893681B2 (en) Method for processing two-dimensional image and device for executing method
CN116563450A (zh) 表情迁移方法、模型训练方法和装置
WO2020056693A1 (zh) 一种图片合成方法、装置及电子设备
EP3872768A1 (en) Method for processing two-dimensional image and device for executing method
US11869150B1 (en) Avatar modeling and generation
Chen Cloud-Based Headset: The Next Possible Smartphone
CN116389704A (zh) 视频处理方法、装置、计算机设备、存储介质和产品

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: 18931080

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: 18931080

Country of ref document: EP

Kind code of ref document: A1