CN115393514A

CN115393514A - Training method of three-dimensional reconstruction model, three-dimensional reconstruction method, device and equipment

Info

Publication number: CN115393514A
Application number: CN202211035632.2A
Authority: CN
Inventors: 孟庆月
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2022-08-26
Filing date: 2022-08-26
Publication date: 2022-11-25

Abstract

The present disclosure provides a training method, a three-dimensional reconstruction method, an apparatus, an electronic device, and a medium for a three-dimensional reconstruction model, which relate to the field of artificial intelligence, in particular to the fields of augmented reality, virtual reality, computer vision, deep learning, and the like, and can be applied to scenes such as virtual digital people, meta universe, and the like. The training method comprises the following steps: obtaining a plurality of sample images acquired for a target area, at least two of the plurality of sample images being acquired at different times; obtaining a plurality of deformed images through a first sub-network based on a plurality of sample images; obtaining at least one reconstruction result of a three-dimensional reconstruction of the target region based on the plurality of deformed images and the second sub-network; determining a first loss value based on the plurality of deformed images and the at least one reconstruction result; and adjusting a parameter of the first sub-network based on the first loss value.

Description

Training method of three-dimensional reconstruction model, three-dimensional reconstruction method, device and equipment

Technical Field

The present disclosure relates to the field of artificial intelligence technologies, and in particular, to augmented reality, virtual reality, computer vision, deep learning, and the like, which can be applied to scenes such as virtual digital people, meta universe, and the like, and in particular, to a training method for a three-dimensional reconstruction model, a three-dimensional reconstruction method, an apparatus, an electronic device, a computer-readable storage medium, and a computer program product.

Background

Artificial intelligence is the subject of research that makes computers simulate some human mental processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), both at the hardware level and at the software level. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing, and the like: the artificial intelligence software technology mainly comprises a computer vision technology, a voice recognition technology, a natural language processing technology, machine learning/deep learning, a big data processing technology, a knowledge map technology and the like.

In the field of computer vision, three-dimensional reconstruction involves the process of reconstructing three-dimensional information based on an image of a target object or target region. It is desirable to obtain a more accurate and more widely applicable three-dimensional reconstruction method.

The approaches described in this section are not necessarily approaches that have been previously conceived or pursued. Unless otherwise indicated, it should not be assumed that any of the approaches described in this section qualify as prior art merely by virtue of their inclusion in this section. Similarly, the problems mentioned in this section should not be considered as having been acknowledged in any prior art, unless otherwise indicated.

Disclosure of Invention

The present disclosure provides a training method for a three-dimensional reconstruction model, a three-dimensional reconstruction method, an apparatus, an electronic device, a computer-readable storage medium, and a computer program product.

According to an aspect of the present disclosure, there is provided a training method for a three-dimensional reconstruction model including a first sub-network and a second sub-network connected to the first sub-network, the method including: obtaining a plurality of sample images acquired for a target area, at least two of the plurality of sample images being acquired at different times; obtaining, by the first sub-network, a plurality of deformation images based on the plurality of sample images; obtaining at least one reconstruction result of a three-dimensional reconstruction of the target region based on the plurality of deformed images and the second sub-network; determining a first loss value based on the plurality of deformed images and the at least one reconstruction result; and adjusting a parameter of the first sub-network based on the first loss value.

According to another aspect of the present disclosure, there is provided a three-dimensional reconstruction method including: obtaining a plurality of images acquired for a target area, at least two of the sample images being acquired at different times; obtaining a plurality of deformed images based on the plurality of images; and obtaining a reconstruction result of the three-dimensional reconstruction of the target region based on the plurality of deformed images, wherein the operation of obtaining the plurality of deformed images based on the plurality of images is realized based on a first sub-network obtained by a training method for a three-dimensional reconstruction model according to one or more embodiments of the present disclosure.

According to another aspect of the present disclosure, there is provided a training apparatus for a three-dimensional reconstruction model including a first sub-network and a second sub-network connected to the first sub-network, the apparatus including: an image obtaining unit configured to obtain a plurality of sample images acquired for a target area, at least two of the plurality of sample images being acquired at different times; a warping unit for obtaining a plurality of warped images through the first sub-network based on the plurality of sample images; a reconstruction unit for obtaining at least one reconstruction result of a three-dimensional reconstruction of the target region based on the plurality of deformed images and the second sub-network; a loss determination unit for determining a first loss value based on the plurality of deformed images and the at least one reconstruction result; and a parameter adjusting unit for adjusting a parameter of the first sub-network based on the first loss value.

According to another aspect of the present disclosure, there is provided a three-dimensional reconstruction apparatus including: an image obtaining unit for obtaining a plurality of images acquired for a target area, at least two of the sample images being acquired at different times; a deformation unit configured to obtain a plurality of deformed images based on the plurality of images; and a reconstruction unit for obtaining a reconstruction result of a three-dimensional reconstruction of the target region based on the plurality of deformed images, wherein the operation of obtaining the plurality of deformed images based on the plurality of images is implemented based on a first sub-network obtained by the training apparatus for a three-dimensional reconstruction model according to one or more embodiments of the present disclosure.

According to another aspect of the present disclosure, there is provided an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a training method or a three-dimensional reconstruction method for a three-dimensional reconstruction model according to one or more embodiments of the present disclosure.

According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform a training method or a three-dimensional reconstruction method for a three-dimensional reconstruction model according to one or more embodiments of the present disclosure.

According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program, when executed by a processor, implements a training method or a three-dimensional reconstruction method for a three-dimensional reconstruction model according to one or more embodiments of the present disclosure.

According to one or more embodiments of the present disclosure, three-dimensional reconstruction can be efficiently performed, and in particular, three-dimensional reconstruction can be performed based on images acquired at different times.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the embodiments and, together with the description, serve to explain the exemplary implementations of the embodiments. The illustrated embodiments are for purposes of example only and do not limit the scope of the claims. Throughout the drawings, identical reference numbers designate similar, but not necessarily identical, elements.

FIG. 1 illustrates a schematic diagram of an exemplary system in which various methods described herein may be implemented, according to an embodiment of the present disclosure;

FIG. 2 shows a flow diagram of a training method for a three-dimensional reconstructed model according to an embodiment of the disclosure;

FIG. 3 shows a schematic diagram of data flow in accordance with an embodiment of the present disclosure;

fig. 4 shows a flow chart of a three-dimensional reconstruction method according to an embodiment of the present disclosure;

FIG. 5 shows a block diagram of a training apparatus for three-dimensional reconstruction of a model according to an embodiment of the present disclosure;

fig. 6 shows a block diagram of a three-dimensional reconstruction apparatus according to an embodiment of the present disclosure;

FIG. 7 illustrates a block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

In the present disclosure, unless otherwise specified, the use of the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, the timing relationship, or the importance relationship of the elements, and such terms are used only to distinguish one element from another. In some examples, a first element and a second element may refer to the same instance of the element, and in some cases, based on the context, they may also refer to different instances.

The terminology used in the description of the various described examples in this disclosure is for the purpose of describing particular examples only and is not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the elements may be one or more. Furthermore, the term "and/or" as used in this disclosure is intended to encompass any and all possible combinations of the listed items.

Embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

Fig. 1 illustrates a schematic diagram of an exemplary system 100 in which various methods and apparatus described herein may be implemented in accordance with embodiments of the present disclosure. Referring to fig. 1, the system 100 includes one or

more client devices

101, 102, 103, 104, 105, and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120.

Client devices

101, 102, 103, 104, 105, and 106 may be configured to execute one or more applications.

In an embodiment of the present disclosure, the server 120 may run one or more services or software applications that enable the training method for three-dimensional reconstruction models or the three-dimensional reconstruction method according to the present disclosure to be performed.

In some embodiments, the server 120 may also provide other services or software applications, which may include non-virtual environments and virtual environments. In some embodiments, these services may be provided as web-based services or cloud services, for example, provided to users of

client devices

101, 102, 103, 104, 105, and/or 106 under a software as a service (SaaS) model.

In the configuration shown in fig. 1, server 120 may include one or more components that implement the functions performed by server 120. These components may include software components, hardware components, or a combination thereof, which may be executed by one or more processors. A user operating a

client device

101, 102, 103, 104, 105, and/or 106 may, in turn, utilize one or more client applications to interact with the server 120 to take advantage of the services provided by these components. It should be understood that a variety of different system configurations are possible, which may differ from system 100. Accordingly, fig. 1 is one example of a system for implementing the various methods described herein and is not intended to be limiting.

The user may use

client devices

101, 102, 103, 104, 105, and/or 106 to train a three-dimensional reconstruction model, three-dimensional reconstruction, view training or reconstruction results, and so forth. The client device may provide an interface that enables a user of the client device to interact with the client device. The client device may also output information to the user via the interface. Although fig. 1 depicts only six client devices, those skilled in the art will appreciate that any number of client devices may be supported by the present disclosure.

Client devices

101, 102, 103, 104, 105, and/or 106 may include various types of computer devices, such as portable handheld devices, general purpose computers (such as personal computers and laptop computers), workstation computers, wearable devices, smart screen devices, self-service terminal devices, service robots, gaming systems, thin clients, various messaging devices, sensors or other sensing devices, and so forth. These computer devices may run various types and versions of software applications and operating systems, such as MICROSOFT Windows, APPLE iOS, UNIX-like operating systems, linux, or Linux-like operating systems (e.g., GOOGLE Chrome OS); or include various Mobile operating systems such as MICROSOFT Windows Mobile OS, iOS, windows Phone, android. Portable handheld devices may include cellular telephones, smart phones, tablets, personal Digital Assistants (PDAs), and the like. Wearable devices may include head-mounted displays (such as smart glasses) and other devices. The gaming system may include a variety of handheld gaming devices, internet-enabled gaming devices, and the like. The client device is capable of executing a variety of different applications, such as various Internet-related applications, communication applications (e.g., email applications), short Message Service (SMS) applications, and may use a variety of communication protocols.

Network 110 may be any type of network known to those skilled in the art that may support data communications using any of a variety of available protocols, including but not limited to TCP/IP, SNA, IPX, etc. Merely by way of example, one or more networks 110 may be a Local Area Network (LAN), an ethernet-based network, a token ring, a Wide Area Network (WAN), the internet, a virtual network, a Virtual Private Network (VPN), an intranet, an extranet, a blockchain network, a Public Switched Telephone Network (PSTN), an infrared network, a wireless network (e.g., bluetooth, WIFI), and/or any combination of these and/or other networks.

The server 120 may include one or more general purpose computers, special purpose server computers (e.g., PC (personal computer) servers, UNIX servers, mid-end servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and/or combination. The server 120 may include one or more virtual machines running a virtual operating system, or other computing architecture involving virtualization (e.g., one or more flexible pools of logical storage that may be virtualized to maintain virtual storage for the server). In various embodiments, the server 120 may run one or more services or software applications that provide the functionality described below.

The computing units in server 120 may run one or more operating systems including any of the operating systems described above, as well as any commercially available server operating systems. The server 120 may also run any of a variety of additional server applications and/or middle tier applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, and the like.

In some implementations, the server 120 can include one or more applications to analyze and consolidate data feeds and/or event updates received from users of the

client devices

101, 102, 103, 104, 105, and 106. Server 120 may also include one or more applications to display data feeds and/or real-time events via one or more display devices of

client devices

101, 102, 103, 104, 105, and 106.

In some embodiments, the server 120 may be a server of a distributed system, or a server incorporating a blockchain. The server 120 may also be a cloud server, or a smart cloud computing server or a smart cloud host with artificial intelligence technology. The cloud server is a host product in a cloud computing service system, and is used for solving the defects of high management difficulty and weak service expansibility in the traditional physical host and Virtual Private Server (VPS) service.

The system 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of the databases 130 may be used to store information such as audio files and video files. The database 130 may reside in various locations. For example, the database used by the server 120 may be local to the server 120, or may be remote from the server 120 and may communicate with the server 120 via a network-based or dedicated connection. The database 130 may be of different types. In certain embodiments, the database used by the server 120 may be, for example, a relational database. One or more of these databases may store, update, and retrieve data to and from the database in response to the command.

In some embodiments, one or more of the databases 130 may also be used by applications to store application data. The databases used by the application may be different types of databases, such as key-value stores, object stores, or regular stores supported by a file system.

The system 100 of fig. 1 may be configured and operated in various ways to enable application of the various methods and apparatus described in accordance with the present disclosure.

A training method 200 for a three-dimensional reconstructed model according to an exemplary embodiment of the present disclosure is described below with reference to fig. 2. The three-dimensional reconstruction model may include a first sub-network and a second sub-network connected to the first sub-network.

At step S201, a plurality of sample images acquired for a target area are obtained, at least two of the plurality of sample images being acquired at different times.

At step S202, a plurality of deformed images is obtained by the first sub-network based on the plurality of sample images.

At step S203, at least one reconstruction result of a three-dimensional reconstruction of the target region is obtained based on the plurality of deformed images and the second sub-network.

At step S204, a first loss value is determined based on the plurality of deformed images and the at least one reconstruction result.

At step S203, a parameter of the first sub-network is adjusted based on the first loss value.

According to the method disclosed by the embodiment of the disclosure, three-dimensional reconstruction can be effectively carried out, and particularly, three-dimensional reconstruction can be carried out based on images acquired at different moments.

Generally, in three-dimensional reconstruction, images from multiple angles are often acquired simultaneously. In particular, in the case of a scene with dynamic changes, there may be inconsistency between the images acquired at different times. According to the embodiment of the present disclosure, especially according to the deformation process of the present disclosure, the plurality of sample images are deformed to reduce or eliminate the influence caused by the scene change, so that a good training and rendering result can be obtained even when the training scene has a dynamic change.

According to some embodiments, obtaining at least one reconstruction result based on the plurality of deformed images and the second sub-network comprises: obtaining a first reconstruction result according to the second sub-network based on the plurality of deformed images; and obtaining a second reconstruction result according to the second sub-network based on the first reconstruction result and the plurality of deformed images; and determining a first loss value based on the plurality of deformed images and the at least one reconstruction result comprises: determining the first loss value based on the plurality of deformed images, the first reconstruction result, and the second reconstruction result.

According to such embodiments, the outcome of the two-stage training can be utilized to supervise the deformation. This is because the inventors of the present application found that the rays in the image frames are not distorted only when the plurality of deformed image frames are sufficiently consistent, thereby achieving consistency of the rough training result and the fine training result.

As can be appreciated by those skilled in the art, the two-stage training described above may include: a first stage, inputting an image into a model to obtain a coarse (coarse) result; subsequently, ray portions of the image that satisfy the threshold are obtained based on the coarse results, and the refined portions are input to the model, obtaining fine (fine) results. For example, a plurality of refined images may be determined based on the coarse results to identify portions of the rays where objects are more likely to be present, and a finer result may be calculated based on the refined images (the finer ray portions) and the second network.

According to some embodiments, the first reconstruction result comprises at least one first color value, the second reconstruction result comprises at least one second color value, and determining a first loss value based on the plurality of deformed images and the at least one reconstruction result comprises: determining at least one warped color value based on the plurality of warped images; and determining the first loss value to identify a difference between the first color value, the second color value, and the warped color value.

As an example, the first loss value may be calculated as follows:

wherein C (r) is the true color value,

and

is a rendering of color values, and in particular,

and

results of coarse and fine phase training rendering are represented, respectively.

According to some embodiments, the method 200 may further comprise: determining a second loss value based on the plurality of sample images and the plurality of deformation images, the second loss value identifying a degree of rigidity of deformation between the plurality of deformation images and the plurality of sample images; and adjusting a parameter of the first sub-network based on the second loss value.

By adding such an exemplary loss function, the deformation can be made rigid, and deformation which is not normal can not occur, so that a more real reconstruction effect can be obtained.

According to some embodiments, method 200 may further comprise adjusting a parameter of the second sub-network based on the first loss value. The reconstruction part can also be trained simultaneously, thereby achieving the effect of end-to-end training. According to other example form examples, a parameter of the second sub-network may be adjusted based on the first penalty value and the second penalty value.

A data flow diagram 300 according to an embodiment of the present disclosure is described with reference to fig. 3.

As shown in fig. 3, an input frame 301 is input to a first network 310 for warping. The first network 310 may be a multi-layer perceptron (MLP) or may be other networks or models as will be appreciated by those skilled in the art. Warped frame 302 is obtained through processing by first network 310.

The warped frame is then input to the second network 320. The data input to the second network 320 may include three-dimensional coordinates (x, y, z) and a perspective

The data input to the second network may also be in other data formats as will be appreciated by those skilled in the art. The second network can implicitly learn a static 3D scene through the neural network, can render the rendering of the unlearned view angle in the actual rendering process,

illustratively, the second network 320 may in turn comprise a first subsection 321 and a second subsection 322. As one specific example, the first subsection 321 and the second subsection 322 may each be a multi-layer perceptron (MLP), but it is understood that the present disclosure is not so limited. For example, the first sub-portion 321 may output a density (σ) of rays, while the second sub-portion 322 may output the rendered color values as an output of the second network 320.

According to one or more embodiments of the present disclosure, 3D reconstruction can be performed based on a plurality of images taken for a dynamic scene.

During the training process, the loss function of the network may be divided into two parts, for example, corresponding to the first loss value part and the second loss value part above, respectively.

As described above, the first loss value part may be shaped as:

wherein C (r) is the true color value,

and

is a rendering of color values, and in particular,

and

the results of the coarse and fine stage training renderings are represented, respectively.

It is to be understood that the true color values may be color values calculated based on the warped frame. By making both coarse and fine phase training rendering results consistent with the true color values computed therefrom, it can be ensured that the warped frames are consistent, and thus the warping process (first network) can be trained.

As other examples, the first loss value may be calculated in other manners understood by those skilled in the art, as long as the first loss value can be used to represent the similarity (or difference) between the plurality of deformed images and the at least one reconstruction result.

The second loss value part may be used in particular for supervision of the deformation part. As one construction example, a frame before deformation may be denoted as x, a frame after deformation may be denoted as x ', and assuming that a deformation process x' = D (x, ω), the process may be regarded as an equation with n-ary parameters.

In the solving process, firstly, the Jacobian matrix J of the deformation parameters D is calculated _D (x) Then the matrix is subjected to singular value decomposition, including

J _D (x)＝UΣV ^*

Based on the decomposition result, the second loss value can be defined as

Such a loss function may increase the degree of rigidity of the deformation, thereby making the deformation result more realistic.

A three-dimensional reconstruction method 400 according to an exemplary embodiment of the present disclosure is described below with reference to fig. 4.

At step S401, a plurality of images acquired for a target area are obtained, at least two of the sample images being acquired at different times.

At step S402, a plurality of deformed images are obtained based on the plurality of images.

At step S403, a reconstruction result of three-dimensional reconstruction of the target region is obtained based on the plurality of deformed images.

In such embodiments, obtaining a plurality of deformation images based on the plurality of images is implemented based on a first sub-network obtained by a training method for a three-dimensional reconstruction model according to one or more embodiments of the present disclosure.

According to some embodiments, the operation of obtaining a reconstruction result based on the plurality of deformed images is implemented based on a second sub-network obtained by a training method according to one or more embodiments of the present disclosure.

A training apparatus 500 for three-dimensional reconstruction models according to an embodiment of the present disclosure will now be described with reference to fig. 5. The three-dimensional reconstruction model includes a first sub-network and a second sub-network connected to the first sub-network. The training apparatus 500 for a three-dimensional reconstruction model may include an image obtaining unit 501, a deformation unit 502, a reconstruction unit 503, a loss determination unit 504, and a parameter adjustment unit 505. The image obtaining unit 501 may be configured to obtain a plurality of sample images acquired for a target area, at least two of the plurality of sample images being acquired at different time instants. The warping unit 502 may be configured to obtain a plurality of warped images through the first sub-network based on the plurality of sample images. The reconstruction unit 503 may be configured to obtain at least one reconstruction result of a three-dimensional reconstruction of the target region based on the plurality of deformed images and the second sub-network. The loss determination unit 504 may be configured to determine a first loss value based on the plurality of deformed images and the at least one reconstruction result. The parameter adjusting unit 505 may be configured to adjust a parameter of the first sub-network based on the first loss value.

According to the device of the embodiment of the disclosure, three-dimensional reconstruction can be effectively carried out, and particularly, three-dimensional reconstruction can be carried out based on images acquired at different moments.

According to some embodiments, the reconstruction unit is further adapted to: obtaining a first reconstruction result according to the second sub-network based on the plurality of deformed images; and obtaining a second reconstruction result according to the second sub-network based on the first reconstruction result and the plurality of deformed images; and the loss determination unit is further configured to: determining the first loss value based on the plurality of deformed images, the first reconstruction result, and the second reconstruction result.

According to some embodiments, the first reconstruction result comprises at least one first color value, the second reconstruction result comprises at least one second color value, and the loss determination unit is to: determining at least one warped color value based on the plurality of warped images; and determining the first loss value to identify a difference between the first color value, the second color value, and the warped color value.

According to some embodiments, the apparatus 500 may further comprise means for: determining a second loss value based on the plurality of sample images and the plurality of deformation images, the second loss value identifying a degree of rigidity of deformation between the plurality of deformation images and the plurality of sample images; and adjusting a parameter of the first sub-network based on the second loss value.

According to some embodiments, the apparatus 500 may further comprise: means for adjusting a parameter of the second sub-network based on the first loss value.

A three-dimensional reconstruction apparatus 600 according to an embodiment of the present disclosure will now be described with reference to fig. 6. The three-dimensional reconstruction apparatus 600 may comprise an image obtaining unit 601, a deformation unit 602, and a reconstruction unit 603. The image obtaining unit 601 may be configured to obtain a plurality of images acquired for a target area, at least two of the sample images being acquired at different time instants. The warping unit 602 may be configured to obtain a plurality of warped images based on the plurality of images. The reconstruction unit 603 may be configured to obtain a reconstruction result of a three-dimensional reconstruction of the target region based on the plurality of deformed images.

In such embodiments, obtaining a plurality of deformation images based on the plurality of images may be implemented based on a first sub-network obtained by a training apparatus for three-dimensional reconstruction models according to one or more embodiments of the present disclosure.

In the technical scheme of the disclosure, the collection, acquisition, storage, use, processing, transmission, provision, public application and other processing of the personal information of the related user are all in accordance with the regulations of related laws and regulations, and do not violate the good customs of the public order.

According to an embodiment of the present disclosure, there is also provided an electronic device, a readable storage medium, and a computer program product.

Referring to fig. 7, a block diagram of a structure of an electronic device 700, which may be a server or a client of the present disclosure, which is an example of a hardware device that may be applied to aspects of the present disclosure, will now be described. Electronic device is intended to represent various forms of digital electronic computer devices, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 7, the electronic device 700 includes a computing unit 701, which may perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 702 or a computer program loaded from a storage unit 708 into a Random Access Memory (RAM) 703. In the RAM703, various programs and data required for the operation of the electronic device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM703 are connected to each other by a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.

A number of components in the electronic device 700 are connected to the I/O interface 705, including: an input unit 706, an output unit 707, a storage unit 708, and a communication unit 709. The input unit 706 may be any type of device capable of inputting information to the electronic device 700, and the input unit 706 may receive input numeric or character information and generate key signal inputs related to user settings and/or function controls of the electronic device, and may include, but is not limited to, a mouse, a keyboard, a touch screen, a track pad, a track ball, a joystick, a microphone, and/or a remote controller. Output unit 707 may be any type of device capable of presenting information and may include, but is not limited to, a display, speakers, a video/audio output terminal, a vibrator, and/or a printer. Storage unit 708 may include, but is not limited to, magnetic or optical disks. The communication unit 709 allows the electronic device 700 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers, and/or chipsets, such as bluetooth (TM) devices, 802.11 devices, wiFi devices, wiMax devices, cellular communication devices, and/or the like.

Computing unit 701 may be a variety of general purpose and/or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The computing unit 701 performs the various methods and processes described above, such as the methods 200 and/or 400 and variations thereof. For example, in some embodiments, methods 200 and/or 400, variations thereof, and so forth, may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 708. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 700 via the ROM 702 and/or the communication unit 709. When loaded into RAM703 and executed by computing unit 701, may perform one or more of the steps of methods 200 and/or 400, variations thereof, and so on, described above. Alternatively, in other embodiments, the computing unit 701 may be configured by any other suitable means (e.g., by way of firmware) to perform the methods 200 and/or 400, variations thereof, and so forth.

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on 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 compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be performed in parallel, sequentially or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.

Although embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it is to be understood that the above-described methods, systems and apparatus are merely exemplary embodiments or examples and that the scope of the present invention is not limited by these embodiments or examples, but only by the claims as issued and their equivalents. Various elements in the embodiments or examples may be omitted or may be replaced with equivalents thereof. Further, the steps may be performed in an order different from that described in the present disclosure. Further, various elements in the embodiments or examples may be combined in various ways. It is important that as technology evolves, many of the elements described herein may be replaced with equivalent elements that appear after the present disclosure.

Claims

1. A training method for a three-dimensional reconstruction model including a first sub-network and a second sub-network connected to the first sub-network, the method comprising:

obtaining a plurality of sample images acquired for a target area, at least two of the plurality of sample images being acquired at different times;

obtaining, by the first sub-network, a plurality of deformation images based on the plurality of sample images;

obtaining at least one reconstruction result of a three-dimensional reconstruction of the target region based on the plurality of deformed images and the second sub-network;

determining a first loss value based on the plurality of deformed images and the at least one reconstruction result; and

adjusting a parameter of the first sub-network based on the first loss value.

2. The method of claim 1, wherein obtaining at least one reconstruction result based on the plurality of deformed images and a second sub-network comprises: obtaining a first reconstruction result according to the second sub-network based on the plurality of deformed images; and obtaining a second reconstruction result according to the second sub-network based on the first reconstruction result and the plurality of deformed images; and is provided with

Determining a first loss value based on the plurality of deformed images and the at least one reconstruction result comprises: determining the first loss value based on the plurality of deformed images, the first reconstruction result, and the second reconstruction result.

3. The method of claim 2, wherein the first reconstruction result includes at least one first color value, the second reconstruction result includes at least one second color value, and determining a first loss value determines a first loss value based on the plurality of deformed images and the at least one reconstruction result comprises:

determining at least one warped color value based on the plurality of warped images; and

determining the first penalty value to identify differences between the first color value, the second color value, and the warped color value.

4. The method of any of claims 1-3, further comprising:

determining a second loss value based on the plurality of sample images and the plurality of deformation images, the second loss value identifying a degree of rigidity of deformation between the plurality of deformation images and the plurality of sample images; and

adjusting a parameter of the first sub-network based on the second loss value.

5. The method of any of claims 1-4, further comprising adjusting a parameter of the second sub-network based on the first loss value.

6. A method of three-dimensional reconstruction, comprising:

obtaining a plurality of images acquired for a target area, at least two of the sample images being acquired at different times;

obtaining a plurality of deformed images based on the plurality of images; and

obtaining a reconstruction result of a three-dimensional reconstruction of the target region based on the plurality of deformation images, wherein the obtaining of the plurality of deformation images based on the plurality of images is performed based on the first sub-network obtained according to any one of claims 1-5.

7. The three-dimensional reconstruction method according to claim 6, wherein the operation of obtaining a reconstruction result based on the plurality of deformed images is carried out based on the second sub-network obtained according to claim 5.

8. A training apparatus for a three-dimensional reconstruction model including a first sub-network and a second sub-network connected to the first sub-network, the apparatus comprising:

an image obtaining unit configured to obtain a plurality of sample images acquired for a target area, at least two of the plurality of sample images being acquired at different times;

a warping unit for obtaining a plurality of warped images by the first sub-network based on the plurality of sample images;

a reconstruction unit for obtaining at least one reconstruction result of a three-dimensional reconstruction of the target region based on the plurality of deformed images and the second sub-network;

a loss determination unit for determining a first loss value based on the plurality of deformed images and the at least one reconstruction result; and

a parameter adjusting unit for adjusting a parameter of the first sub-network based on the first loss value.

9. The apparatus of claim 8, wherein the reconstruction unit is further configured to: obtaining a first reconstruction result according to the second sub-network based on the plurality of deformed images; and obtaining a second reconstruction result according to the second sub-network based on the first reconstruction result and the plurality of deformed images; and is provided with

The loss determination unit is further configured to: determining the first loss value based on the plurality of deformed images, the first reconstruction result, and the second reconstruction result.

10. The apparatus of claim 9, wherein the first reconstruction result comprises at least one first color value, the second reconstruction result comprises at least one second color value, and the loss determination unit is to:

determining the first loss value to identify a difference between the first color value, the second color value, and the warped color value.

11. The apparatus of any of claims 8-10, further comprising means for:

determining a second loss value based on the plurality of sample images and the plurality of deformed images, the second loss value identifying a degree of rigidity of deformation between the plurality of deformed images and the plurality of sample images; and

adjusting a parameter of the first sub-network based on the second loss value.

12. The apparatus of any of claims 8-11, further comprising: means for adjusting a parameter of the second sub-network based on the first loss value.

13. A three-dimensional reconstruction apparatus comprising:

an image obtaining unit for obtaining a plurality of images acquired for a target area, at least two of the sample images being acquired at different times;

a morphing unit configured to obtain a plurality of morphed images based on the plurality of images, wherein obtaining the plurality of morphed images based on the plurality of images is implemented based on the first sub-network obtained according to any one of claims 8-12; and

a reconstruction unit configured to obtain a reconstruction result of a three-dimensional reconstruction of the target region based on the plurality of deformed images.

14. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein

The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5 or 6-7.

15. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any of claims 1-5 or 6-7.

16. A computer program product comprising a computer program, wherein the computer program realizes the method of any one of claims 1-5 or 6-7 when executed by a processor.