A multi-angle three-dimensional face reconstruction method and device and a storage medium

Abstract

A multi-angle three-dimensional face reconstruction method, device and storage medium, the method comprises the steps of: acquiring multi-angle face pictures; generating a three-dimensional face point cloud model according to the multi-angle face pictures; and rendering the three-dimensional face point cloud model to obtain a three-dimensional face model. The multi-angle three-dimensional face reconstruction method, device and storage medium provided by the application can realize parallel computing to improve the modeling speed, can remove outlier point clouds and better supplement possible missing details, and can further render the generated face model to obtain a more realistic face model.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of three-dimensional face reconstruction, and particularly relates to a multi-angle three-dimensional face reconstruction method and device and a storage medium. BACKGROUND

[0002] In recent years, computer vision has made great progress under the impetus of many technologies, and a face contains a large part of important biological information of a person and has always been of great concern. When opening a mobile phone bank app to verify identity, the mobile phone will automatically jump to a face recognition interface, which generally relies on two-dimensional face image recognition. For three-dimensional animals, a single input in the form of a picture will inevitably lose information, and input from a certain angle may not be easy to identify individual identity information, in order to achieve higher recognition accuracy, many high-end face recognition technologies consider using face three-dimensional modeling to further assist face recognition.

[0003] In addition, not only for improving face recognition accuracy, face three-dimensional modeling can also be used in VR, cloud gaming and other scenarios, which is a general trend under the background of 5G. Taking VR as an example, a user can generate a character of the same size as himself in a virtual game space according to his own image, bringing a better immersive experience to the user. In addition, three-dimensional face reconstruction will play an indispensable role in movie special effects, beauty and medical treatment. Therefore, how to construct a realistic three-dimensional face with the same size as the real world has practical significance.

[0004] However, the reconstruction of a three-dimensional face can only be based on a common two-dimensional storage format such as a photo. In order to obtain face depth information, an RGB-D camera capable of detecting depth can effectively construct a three-dimensional face model, but it cannot obtain a face texture pattern, and has high power consumption and high cost. At the same time, with the brilliant performance of deep learning in computer vision, more and more researchers consider using deep learning as a technical means to realize three-dimensional reconstruction of a face.

[0005] At present, the technology for realizing a good fitting three-dimensional face is still a supervised deep learning method, which means that a large number of high-precision three-dimensional face labels are needed as samples for training. Therefore, how to quickly obtain more high-precision three-dimensional face models by various physical means is a problem that needs to be solved. SUMMARY

[0006] In view of the above problems, the present application provides a multi-angle three-dimensional face reconstruction method, device and storage medium which overcome the above problems or at least partially solve the above problems.

[0007] To solve the above technical problems, the present application provides a multi-angle three-dimensional face reconstruction method, which comprises the following steps:

[0008] obtaining multi-angle face pictures;

[0009] generating a three-dimensional face point cloud model according to the multi-angle face pictures;

[0010] rendering the three-dimensional face point cloud model and obtaining a three-dimensional face model.

[0011] Preferably, the step of generating a three-dimensional face point cloud model according to the multi-angle face pictures comprises the steps of:

[0012] reconstructing sparse feature points of the multi-angle face pictures;

[0013] obtaining camera poses;

[0014] optimizing the sparse feature points according to the camera poses;

[0015] generating a dense three-dimensional point cloud of a face surface according to the camera poses;

[0016] correcting the dense three-dimensional point cloud of the face surface.

[0017] Preferably, the step of obtaining camera poses comprises the steps of:

[0018] arranging a calibration pattern in a photographic field;

[0019] measuring spatial coordinates of the calibration pattern in an absolute spatial coordinate system of the photographic field;

[0020] finding corresponding positions of the calibration pattern in photographic images;

[0021] determining a corresponding relationship between the multi-angle face pictures and the photographic field;

[0022] solving matrix parameters of a camera;

[0023] obtaining actual three-dimensional position coordinates of position points in the multi-angle face pictures in spatial points by using the matrix parameters.

[0024] Preferably, the step of generating a dense three-dimensional point cloud of a face surface according to the camera poses comprises the steps of:

[0025] finding target points with image consistency in space;

[0026] calculating depth values of each pixel according to the target points;

[0027] performing consistency aggregation by using correlations between adjacent pixel blocks and obtaining a face depth map;

[0028] aggregating the face depth map to obtain a dense three-dimensional point cloud of a face surface.

[0029] Preferably, the modifying the dense three-dimensional point cloud of the face surface comprises the steps of:

[0030] meshing the dense three-dimensional point cloud of the face surface;

[0031] completing the missing part of the dense three-dimensional point cloud of the face surface;

[0032] restoring the missing part;

[0033] cubic feature sampling the dense three-dimensional point cloud of the face surface to obtain a fine point cloud model.

[0034] Preferably, the generating a three-dimensional face point cloud model according to the multi-angle face picture comprises the steps of:

[0035] obtaining a dense three-dimensional point cloud of a face surface;

[0036] estimating a normal vector of the dense three-dimensional point cloud of the face surface;

[0037] projecting the dense three-dimensional point cloud of the face surface onto a two-dimensional plane according to the normal vector;

[0038] triangulating and topologically connecting the dense three-dimensional point cloud of the face surface to obtain a three-dimensional face point cloud model.

[0039] Preferably, the rendering the three-dimensional face point cloud model to obtain a three-dimensional face model comprises the steps of:

[0040] obtaining a camera pose;

[0041] obtaining a two-dimensional projection of the three-dimensional face point cloud model under the camera pose;

[0042] obtaining an original photo of the three-dimensional face point cloud model;

[0043] obtaining a color difference part of the two-dimensional projection and the original photo;

[0044] optimizing the color difference part;

[0045] color adjusting the three-dimensional face point cloud model according to the color difference part.

[0046] The application also provides a multi-angle three-dimensional face reconstruction device, the device comprising:

[0047] a multi-angle face picture acquisition module, configured to acquire multi-angle face pictures;

[0048] a three-dimensional face point cloud model generation module, configured to generate a three-dimensional face point cloud model according to the multi-angle face pictures;

[0049] The three-dimensional face model generation module is configured to render the three-dimensional face point cloud model and obtain a three-dimensional face model.

[0050] The application also provides an electronic device, which comprises:

[0051] at least one processor; and

[0052] a memory in communication with the at least one processor; wherein

[0053] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the multi-angle three-dimensional face reconstruction method.

[0054] The application also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the multi-angle three-dimensional face reconstruction method.

[0055] The one or more technical solutions in the embodiments of the application have at least the following technical effects or advantages: the multi-angle three-dimensional face reconstruction method, device and storage medium provided by the application can realize parallel computing to improve the modeling speed, can remove outlier point clouds and better supplement possible missing details, and can further render the generated face model to obtain a more realistic face model. BRIEF DESCRIPTION OF DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the application, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings in the following description are some embodiments of the application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0057] Figure 1 is a flowchart of a multi-angle three-dimensional face reconstruction method provided by the embodiments of the application;

[0058] Figure 2 is a multi-angle three-dimensional face reconstruction device provided by the embodiments of the application;

[0059] is a structural diagram of a multi-angle three-dimensional face reconstruction device;

[0060] Figure 3 is a structural diagram of an electronic device provided by the embodiments of the application;

[0061] Figure 4 is a structural diagram of a non-transitory computer-readable storage medium provided by the embodiments of the application. DETAILED DESCRIPTION

[0062] The advantages and various effects of the present application will be more clearly presented hereinafter with specific embodiments and examples. Those skilled in the art should understand that these embodiments and examples are used to illustrate the present application, not to limit the present application.

[0063] Throughout the specification, unless otherwise specifically indicated, the terms used herein are understood to have the meanings commonly used in the art. Therefore, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. If there is a contradiction, the present specification takes precedence.

[0064] Unless otherwise specifically indicated, various raw materials, reagents, instruments and equipment used in the present application can be purchased from the market or can be prepared by existing methods.

[0065] As Figure 1 In the embodiments of the present application, a multi-angle three-dimensional face reconstruction method is provided, which comprises the steps of:

[0066] S1: obtaining a multi-angle face picture;

[0067] In the embodiments of the present application, the multi-angle face picture can be obtained by a camera. The multi-angle face picture acquisition step is as follows: first, a ring-shaped photography field is made, and cameras are arranged in a ring shape in the ring-shaped photography field, then the face is photographed from the left and right sides and the front face in three main directions and from different pitch angles, thereby obtaining high-definition pictures of the face from multiple angles.

[0068] S2: generating a three-dimensional face point cloud model according to the multi-angle face picture;

[0069] In the embodiments of the present application, the step of generating a three-dimensional face point cloud model according to the multi-angle face picture comprises the steps of:

[0070] reconstructing sparse feature points of the multi-angle face picture;

[0071] obtaining camera poses;

[0072] optimizing the sparse feature points according to the camera poses;

[0073] generating a dense three-dimensional point cloud of the face surface according to the camera poses;

[0074] correcting the dense three-dimensional point cloud of the face surface.

[0075] In the embodiment of the present application, when generating the three-dimensional face point cloud model according to the multi-angle face pictures, the sparse feature points of the multi-angle face pictures are reconstructed, the camera pose in step S1 is obtained, the sparse feature points are optimized according to the camera pose, the dense three-dimensional point cloud of the face surface is generated according to the camera pose, and the dense three-dimensional point cloud of the face surface is corrected.

[0076] In the embodiment of the present application, the obtaining of the camera pose comprises the steps of:

[0077] arranging a calibration pattern in a photographic field;

[0078] measuring the spatial coordinates of the calibration pattern under an absolute spatial coordinate system of the photographic field;

[0079] finding the corresponding positions of the calibration pattern in photographic images;

[0080] determining the corresponding relationship between the multi-angle face pictures and the photographic field;

[0081] solving the matrix parameters of the camera;

[0082] obtaining the actual three-dimensional position coordinates of the position points in the multi-angle face pictures in the spatial points by using the matrix parameters.

[0083] In the embodiment of the present application, when the camera pose is obtained, first, a calibration pattern is arranged in a photographic field, the calibration pattern can be selected according to needs, then the spatial coordinates of the calibration pattern are measured under an absolute spatial coordinate system of the photographic field, at the same time, the corresponding positions of the calibration pattern in photographic images are found, then the corresponding relationship between the multi-angle face pictures and the photographic field is determined, the matrix parameters of the camera are solved, and finally the actual three-dimensional position coordinates of the position points in the multi-angle face pictures in the spatial points are obtained by using the matrix parameters.

[0084] In the embodiment of the present application, the generation of the dense three-dimensional point cloud of the face surface according to the camera pose comprises the steps of:

[0085] finding target points with image consistency in space;

[0086] calculating the depth values of each pixel according to the target points;

[0087] performing consistency aggregation by using the correlation between adjacent pixel blocks and obtaining a face depth map;

[0088] aggregating the face depth map to obtain the dense three-dimensional point cloud of the face surface.

[0089] In the embodiments of the present application, when the dense three-dimensional point cloud of the face surface is generated according to the camera pose, first, the target point with image consistency is searched in the space, and then the depth value of each pixel is calculated according to the target point, and then the face depth map is obtained by consistency aggregation and correlation between adjacent pixel blocks, and then the dense three-dimensional point cloud of the face surface is aggregated to obtain the dense three-dimensional point cloud of the face surface.

[0090] In the embodiments of the present application, the step of correcting the dense three-dimensional point cloud of the face surface includes:

[0091] Griding the dense three-dimensional point cloud of the face surface;

[0092] Completing the missing part of the dense three-dimensional point cloud of the face surface;

[0093] Restoring the missing part;

[0094] Restoring the dense three-dimensional point cloud of the face surface by three times of feature sampling to obtain a fine point cloud model.

[0095] In the embodiments of the present application, when the dense three-dimensional point cloud of the face surface is corrected, first, the dense three-dimensional point cloud of the face surface is gridded, then the missing part of the dense three-dimensional point cloud of the face surface is completed, then the missing part is restored, and then the dense three-dimensional point cloud of the face surface is restored by three times of feature sampling to obtain a fine point cloud model.

[0096] In the embodiments of the present application, the step of generating a three-dimensional face point cloud model according to the multi-angle face picture includes:

[0097] Obtaining a dense three-dimensional point cloud of a face surface;

[0098] Estimating a normal vector of the dense three-dimensional point cloud of the face surface;

[0099] Projecting the dense three-dimensional point cloud of the face surface onto a two-dimensional plane according to the normal vector;

[0100] Triangulating and topologically connecting the dense three-dimensional point cloud of the face surface to obtain a three-dimensional face point cloud model.

[0101] In the embodiments of the present application, when the three-dimensional face point cloud model is generated according to the multi-angle face picture, first, a dense three-dimensional point cloud of a face surface is obtained, then a normal vector of the dense three-dimensional point cloud of the face surface is estimated, then the dense three-dimensional point cloud of the face surface is projected onto a two-dimensional plane according to the normal vector, and then the dense three-dimensional point cloud of the face surface is triangulated and topologically connected to obtain a three-dimensional face point cloud model.

[0102] S3: rendering the three-dimensional face point cloud model to obtain a three-dimensional face model.

[0103] In the embodiments of the present application, the rendering of the three-dimensional face point cloud model and obtaining a three-dimensional face model comprises the steps of:

[0104] obtaining a camera pose;

[0105] obtaining a two-dimensional projection of the three-dimensional face point cloud model under the camera pose;

[0106] obtaining an original photo of the three-dimensional face point cloud model;

[0107] obtaining a color difference part of the two-dimensional projection and the original photo;

[0108] optimizing the color difference part;

[0109] color adjusting the three-dimensional face point cloud model according to the color difference part.

[0110] In the embodiments of the present application, when the three-dimensional face point cloud model is rendered and a three-dimensional face model is obtained, first, a camera pose is obtained, then a two-dimensional projection of the three-dimensional face point cloud model under the camera pose is obtained, then an original photo of the three-dimensional face point cloud model is obtained, then a color difference part of the two-dimensional projection and the original photo is obtained, then the color difference part is optimized, and finally the three-dimensional face point cloud model is color adjusted according to the color difference part.

[0111] As Figure 2 In the embodiments of the present application, the present application also provides a multi-angle three-dimensional face reconstruction device, which comprises:

[0112] a multi-angle face picture acquisition module 10, configured to acquire multi-angle face pictures;

[0113] a three-dimensional face point cloud model generation module 20, configured to generate a three-dimensional face point cloud model according to the multi-angle face pictures;

[0114] a three-dimensional face model generation module 30, configured to render the three-dimensional face point cloud model and obtain a three-dimensional face model.

[0115] The multi-angle three-dimensional face reconstruction device provided by the present application can perform the multi-angle three-dimensional face reconstruction method provided by the above steps.

[0116] Reference will be made to the following Figure 3The diagram illustrates a structural schematic of an electronic device 100 suitable for implementing embodiments of the present disclosure. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0117] like Figure 3 As shown, the electronic device 100 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 101, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 102 or a program loaded from a storage device 108 into a random access memory (RAM) 103. The RAM 103 also stores various programs and data required for the operation of the electronic device 100. The processing unit 101, ROM 102, and RAM 103 are interconnected via a bus 104. An input / output (I / O) interface 105 is also connected to the bus 104.

[0118] Typically, the following devices can be connected to I / O interface 105: input devices 106 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 107 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 108 including, for example, magnetic tapes, hard disks, etc.; and communication devices 109. Communication device 109 allows electronic device 100 to communicate wirelessly or wiredly with other devices to exchange data. Although an electronic device 100 with various devices is shown in the figure, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0119] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 109, or installed from storage device 108, or installed from ROM 102. When the computer program is executed by processing device 101, it performs the functions defined in the methods of embodiments of this disclosure.

[0120] The following is for reference. Figure 4Fig. 8 is a structural diagram illustrating a computer readable storage medium suitable for use in implementing embodiments of the present disclosure, the computer readable storage medium storing a computer program, the computer program being executable by a processor to implement the multi-angle three-dimensional face reconstruction method according to any one of the preceding embodiments.

[0121] It should be noted that the computer readable medium of the present disclosure described above can be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium may, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or apparatus. In the present disclosure, the computer readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer readable program code. Such a propagated data signal can take various forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination of the above. The computer readable signal medium can also be any computer readable medium other than the computer readable storage medium, which can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or apparatus. The program code contained in the computer readable medium can be transmitted by any suitable medium, including but not limited to a wire, a cable, a RF (radio frequency) or the like, or any suitable combination of the above.

[0122] The computer readable medium described above can be included in the electronic device described above; or can exist separately and not be assembled into the electronic device.

[0123] The computer readable medium described above carries one or more programs, when the one or more programs are executed by the electronic device, the electronic device is caused to: obtain at least two internet protocol addresses; send a node evaluation request including the at least two internet protocol addresses to a node evaluation device, wherein the node evaluation device selects an internet protocol address from the at least two internet protocol addresses and returns; receive the internet protocol address returned by the node evaluation device; and wherein the obtained internet protocol address indicates an edge node in a content distribution network.

[0124] Alternatively, the computer readable medium described above carries one or more programs, when the one or more programs are executed by the electronic device, the electronic device is caused to: receive a node evaluation request comprising at least two internet protocol addresses; select an internet protocol address from the at least two internet protocol addresses; and return the selected internet protocol address; wherein the received internet protocol address indicates an edge node in a content distribution network.

[0125] Computer program code for carrying out operations of the present disclosure can be written in any one or more of a variety of programming languages or combinations of languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0126] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flow diagrams or block diagrams can represent a module, a procedure, or a part of code, which comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in a different order than that noted in the figures. For example, two blocks noted in succession can in fact be executed substantially concurrently or in the opposite order, depending on the functionality involved. It should also be noted that each block in the block diagrams and / or flow diagrams, and combinations of blocks in the block diagrams and / or flow diagrams, can be implemented by dedicated hardware-based systems that perform the specified functions or operations, or can be implemented by a combination of dedicated hardware-based systems and computer instructions.

[0127] The units described in the embodiments of the present disclosure can be implemented by software, or can be implemented by hardware. In some cases, the name of the unit does not constitute a limitation on the unit itself, for example, the first obtaining unit can also be described as "a unit for obtaining at least two internet protocol addresses".

[0128] The multi-angle three-dimensional face reconstruction method and device and the storage medium provided in the application can realize parallel computing to improve modeling speed, can remove outlier point clouds and better supplement possible missing details, and further render the generated face model to obtain a more realistic face model.

[0129] It should be understood that the above specific embodiments of the application are only used for illustrative or explanatory purposes of the principles of the application, and do not constitute a limitation of the application. Therefore, any modification, equivalent replacement, improvement, etc. made without departing from the spirit and scope of the application shall be included in the protection scope of the application. In addition, the appended claims of the application are intended to cover all variations and modifications falling within the scope and boundary of the appended claims, or the equivalent forms of such scope and boundary.

Claims

1. A multi-angle three-dimensional face reconstruction method, characterized in that, The method comprises steps of: acquiring multi-angle face pictures; generating a three-dimensional face point cloud model according to the multi-angle face pictures; rendering the three-dimensional face point cloud model and obtaining a three-dimensional face model; the step of generating a three-dimensional face point cloud model according to the multi-angle face pictures comprises steps of: reconstructing sparse feature points of the multi-angle face pictures; acquiring camera poses; optimizing the sparse feature points according to the camera poses; generating a dense three-dimensional point cloud of a face surface according to the camera poses; correcting the dense three-dimensional point cloud of the face surface; the step of acquiring camera poses comprises steps of: arranging calibration patterns in a photographic field; measuring spatial coordinates of the calibration patterns in an absolute spatial coordinate system of the photographic field; finding corresponding positions of the calibration patterns in photographic images; determining corresponding relationships between the multi-angle face pictures and the photographic field; solving matrix parameters of a camera; obtaining actual three-dimensional position coordinates of position points in the multi-angle face pictures in space points by using the matrix parameters; the step of generating a dense three-dimensional point cloud of a face surface according to the camera poses comprises steps of: finding target points with image consistency in space; calculating depth values of each pixel according to the target points; performing consistency aggregation by using correlations between adjacent pixel blocks and obtaining a face depth map; aggregating the face depth map to obtain a dense three-dimensional point cloud of a face surface; the step of correcting the dense three-dimensional point cloud of the face surface comprises steps of: meshing the dense three-dimensional point cloud of the face surface; completing missing parts of the dense three-dimensional point cloud of the face surface; restoring the missing parts; restoring a fine point cloud model by performing three times of feature sampling on the dense three-dimensional point cloud of the face surface; the step of generating a three-dimensional face point cloud model according to the multi-angle face pictures comprises steps of: acquiring a dense three-dimensional point cloud of a face surface; estimating normal vectors of the dense three-dimensional point cloud of the face surface; projecting the dense three-dimensional point cloud of the face surface onto a two-dimensional plane according to the normal vectors; triangulating and topologically connecting the dense three-dimensional point cloud of the face surface to obtain a three-dimensional face point cloud model; the step of rendering the three-dimensional face point cloud model and obtaining a three-dimensional face model comprises steps of: acquiring a two-dimensional projection of the three-dimensional face point cloud model under the camera poses; acquiring an original photograph of the three-dimensional face point cloud model; acquiring a color difference part of the two-dimensional projection and the original photograph; optimizing the color difference part; adjusting colors of the three-dimensional face point cloud model according to the color difference part.

2. A multi-angle three-dimensional face reconstruction apparatus suitable for the method of claim 1, characterized in that, The device comprises: a multi-angle face picture acquisition module, configured to acquire multi-angle face pictures; a three-dimensional face point cloud model generation module, configured to generate a three-dimensional face point cloud model according to the multi-angle face pictures; a three-dimensional face model generation module, configured to render the three-dimensional face point cloud model and obtain a three-dimensional face model.

3. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected with the at least one processor in communication; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the multi-angle three-dimensional face reconstruction method of claim 1.

4. A non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the multi-angle three-dimensional face reconstruction method of claim 1.

Images