KR102642665B1 - Method for adjusting virtual camera - Google Patents

Abstract

The present disclosure provides a method for learning a neural network model for adjusting a virtual camera, which is performed by a computing device, the method comprising: acquiring focus information and rotation information of the virtual camera; placing identical patterns at identical locations in virtual space associated with the virtual camera and real space associated with the real camera; Obtaining adjustment information of the virtual camera based on the arranged identical patterns; and generating learning data, including the focus information and the rotation information as input information and the adjustment information as ground truth information.

Description

How to adjust a virtual camera {METHOD FOR ADJUSTING VIRTUAL CAMERA}

This disclosure relates to a method for adjusting a virtual camera, and more specifically, to a method for generating adjustment information for a virtual camera in relation to registration of real space and virtual space.

Recently, technologies that allow users to experience virtual spaces as if they were reality are being activated using wearable equipment including visual sensors, including XR (Extended Reality) equipment. At this time, in order for the user to have a natural XR experience, the actual space physically reflected in the movements of the user wearing the wearable device and the virtual space reflected to the user must be matched. (At this time, the camera that physically moves in response to the user's actual movement is a real camera, and the camera that exists in the virtual space to output a certain point in the virtual space in conjunction with the real camera can be understood as a virtual camera.)

However, generally, when registering the real space and the virtual space, dynamic movements such as rotation of the camera are not considered, which may cause a problem of poor registration quality. Therefore, a method is needed to perform registration of a virtual camera and a real camera by considering dynamic movements such as rotation, and to efficiently perform complex calculations that occur by considering rotation.

Meanwhile, the present disclosure has been derived based at least on the technical background examined above, but the technical problem or purpose of the present disclosure is not limited to solving the problems or shortcomings examined above. In other words, in addition to the technical issues discussed above, the present disclosure can cover various technical issues related to the content to be described below.

Korean Patent Publication: 2023-0094732 (2023.06.28) relates to a camera calibration error compensation method and device.

The present disclosure aims to solve the problem of improving the quality of registration between virtual space and real space by generating adjustment information of a virtual camera based on a neural network model when performing registration between virtual space and real space. In addition, the present disclosure aims to solve the problem of providing artificial intelligence technology for implementing and learning such neural network models.

In addition, the present disclosure aims to match virtual space and real space, and solve the problem of deterioration in matching quality caused by rotation of the virtual camera or real camera.

Meanwhile, the technical problem to be achieved by the present disclosure is not limited to the technical problems mentioned above, and may include various technical problems within the scope of what is apparent to those skilled in the art from the contents described below.

A method for learning a neural network model for adjusting a virtual camera, performed by a computing device for solving the above-described problem, the method comprising: acquiring focus information and rotation information of the virtual camera; placing identical patterns at identical locations in virtual space associated with the virtual camera and real space associated with the actual camera; Obtaining adjustment information of the virtual camera based on the arranged identical patterns; and generating learning data, including the focus information and the rotation information as input information and the adjustment information as ground truth information.

In one embodiment, the step of acquiring adjustment information of the virtual camera based on the arranged identical patterns includes matching the screen of the virtual camera with the screen of the real camera based on the arranged identical patterns. It may include obtaining adjustment information of the virtual camera to do so.

In one embodiment, the adjustment information for the virtual camera may include information for adjusting distortion of the virtual camera.

In one embodiment, the virtual camera and the real camera may be used to create extended reality (XR) content.

In one embodiment, the step of generating the learning data may include generating the learning data for each zoom section included in the entire zoom section.

In one embodiment, the real camera may include a camera pre-adjusted based on a dynamic pattern whose appearance dynamically changes according to a change in focus of the real camera.

In one embodiment, the dynamic pattern may include a dynamic pattern displayed on a display fixed at a first position, and the actual camera may include a pre-adjusted camera fixed at a second position.

An apparatus for learning a neural network model for adjusting a virtual camera to solve the above-described problem, the apparatus comprising: at least one processor; and a memory, wherein the at least one processor acquires focus information and rotation information of a virtual camera and places identical patterns at the same locations in virtual space associated with the virtual camera and real space associated with the real camera, Learning data that acquires adjustment information of the virtual camera based on the arranged identical patterns, includes the focus information and rotation information as input information, and includes the adjustment information as ground truth information. can be created.

In one embodiment related to the device, the at least one processor is configured to obtain adjustment information of the virtual camera to match the screen of the virtual camera with the screen of the real camera, based on the arranged identical patterns. It may be configured additionally.

In one embodiment related to the device, the adjustment information of the virtual camera may include information for adjusting distortion of the virtual camera.

In one embodiment related to the device, the virtual camera and the real camera may be utilized to create extended reality (XR) content. In one embodiment related to the device, the at least one processor may be further configured to generate the learning data for each zoom section included in the entire zoom section.

In one embodiment related to the device, the real camera may be a camera pre-adjusted based on a dynamic pattern whose appearance dynamically changes according to a change in focus of the real camera.

In one embodiment related to the device, the dynamic pattern may include a dynamic pattern displayed on a display fixed in a first position, and the actual camera may be a pre-adjusted camera fixed in a second position. .

A computer program stored in a computer-readable storage medium for solving the above-described problem, wherein the program performs operations for causing at least one processor to learn a neural network model for adjusting a virtual camera, the operations comprising: controlling the focus of the virtual camera; An operation to obtain information and rotation information; placing identical patterns at identical locations in a virtual space associated with the virtual camera and a real space associated with the actual camera; Obtaining adjustment information of the virtual camera based on the arranged identical patterns; and an operation of generating learning data, including the focus information and the rotation information as input information and the adjustment information as ground truth information.

In one embodiment related to the program, the operation of acquiring adjustment information of the virtual camera based on the arranged identical patterns includes dividing the screen of the virtual camera and the real camera based on the arranged identical patterns. It may include an operation of acquiring adjustment information of the virtual camera to match the screen.

In one embodiment related to the program, the adjustment information of the virtual camera may include information for adjusting distortion of the virtual camera.

In one embodiment related to the program, the virtual camera and the real camera may be used to create extended reality (XR) content.

In one embodiment related to the program, the operation of generating the learning data may include the operation of generating the learning data for each zoom section included in the entire zoom section.

In one embodiment related to the program, the real camera may be a camera pre-adjusted based on a dynamic pattern whose appearance dynamically changes according to a change in focus of the real camera.

In one embodiment related to the program, the dynamic pattern includes a dynamic pattern displayed on a display fixed in a first position, and the actual camera may be a pre-adjusted camera fixed in a second position. .

A data structure included in a computer-readable storage medium for solving the above-described problem, wherein the data structure corresponds to parameters of a neural network that are at least partially updated during a learning process, and the operation of the neural network is at least partially dependent on the parameters. Based on, the learning process includes: acquiring focus information and rotation information of a virtual camera; placing identical patterns at identical locations in virtual space associated with the virtual camera and real space associated with the real camera; Obtaining adjustment information of the virtual camera based on the arranged identical patterns; and generating learning data, including the focus information and the rotation information as input information and the adjustment information as ground truth information.

A method of adjusting a virtual camera performed by a computing device to solve the above-described problem, comprising: acquiring focus information and rotation information of the virtual camera; and generating adjustment information for adjusting the virtual camera based on the focus information and the rotation information using a neural network model, wherein the neural network model includes a virtual space and a real camera associated with the virtual camera. It may be a model learned using learning data obtained based on arranging the same patterns at the same locations in the real space associated with .

An apparatus for controlling a virtual camera to solve the above-described problem, comprising: at least one processor; and memory; It includes, wherein the at least one processor acquires focus information and rotation information of the virtual camera, and uses a neural network model to adjust the virtual camera based on the focus information and rotation information. Generating, the neural network model may be a model learned using learning data obtained based on arranging the same patterns at the same positions in the virtual space associated with the virtual camera and the real space associated with the real camera.

A computer program stored in a computer-readable storage medium for solving the above-described problem, wherein the program performs operations for adjusting a virtual camera with at least one processor, and the operations include focus information and rotation information of the virtual camera. An operation to obtain; and generating adjustment information for adjusting the virtual camera based on the focus information and the rotation information using a neural network model, wherein the neural network model includes a virtual space and a real camera associated with the virtual camera. It may be a model learned using learning data obtained based on arranging the same patterns at the same locations in the real space associated with .

A data structure included in a computer-readable storage medium for solving the above-described problem, wherein the data structure corresponds to a parameter of a neural network model, and the neural network model performs the following steps based at least in part on the parameter, , the steps include: acquiring focus information and rotation information of the virtual camera; and generating adjustment information for adjusting the virtual camera based on the focus information and the rotation information using a neural network model, wherein the neural network model includes a virtual space and a real camera associated with the virtual camera. It may be a model learned using learning data obtained based on arranging the same patterns at the same locations in the real space associated with .

In the present disclosure, when performing registration between virtual space and real space, adjustment information for a virtual camera is generated based on a neural network model to improve the quality of registration between the virtual space and real space. Additionally, the present disclosure can provide artificial intelligence technology for implementing and learning such neural network models.

In addition, the present disclosure can provide a method of registering a real camera and a virtual camera, and performing registration in a manner that is robust to rotational motion. For example, the present disclosure predicts variables for matching a real camera and a virtual camera (e.g., adjustment information for adjusting the virtual camera), trains a neural network model to take into account the camera's rotating motion, and trains the learned A neural network model can be used. Therefore, using the method of the present disclosure, when a user experiences XR where virtual space and real space are mixed, a natural experience can be provided to the user even in dynamic motion.

Meanwhile, the effects of the present disclosure are not limited to the effects mentioned above, and various effects may be included within the range apparent to those skilled in the art from the contents described below.

1 is a block diagram of a computing device performing operations according to an embodiment of the present disclosure.
Figure 2 is a schematic diagram showing a neural network model, according to an embodiment of the present disclosure.
3 is a schematic diagram of a method for placing the same pattern at the same locations in virtual space and real space associated with a real camera, according to an embodiment of the present disclosure.
Figure 4 is a schematic diagram of a method for generating training data for a neural network model, according to an embodiment of the present disclosure.
Figure 5 is a schematic diagram of a method for training a neural network model, according to an embodiment of the present disclosure.
Figure 6 is a schematic diagram of a method for adjusting a real camera, according to an embodiment of the present disclosure.
Figure 7 is a flowchart representing a general process of a method for learning a neural network model for adjusting a virtual camera, according to an embodiment of the present disclosure.
Figure 8 is a flowchart representing a general process for a method for adjusting a virtual camera using a neural network model, according to an embodiment of the present disclosure.
9 is a brief, general schematic diagram of an example computing environment in which embodiments of the present disclosure may be implemented.

Various embodiments are now described with reference to the drawings. In this disclosure, various descriptions are presented to provide an understanding of the disclosure. However, it is clear that these embodiments may be practiced without these specific descriptions.

As used in this disclosure, the terms “component,” “module,” “system,” and the like refer to a computer-related entity, hardware, firmware, software, a combination of software and hardware, or an implementation of software. For example, a component may be, but is not limited to, a process running on a processor, a processor, an object, a thread of execution, a program, and/or a computer. For example, both an application running on a computing device and the computing device can be a component. One or more components may reside within a processor and/or thread of execution. A component may be localized within one computer. A component may be distributed between two or more computers. Additionally, these components can execute from various computer-readable media having various data structures stored thereon. Components can transmit signals, for example, with one or more data packets (e.g., data and/or signals from one component interacting with other components in a local system, a distributed system, to other systems and over a network such as the Internet). Depending on the data being transmitted, they may communicate through local and/or remote processes.

Additionally, the term “or” is intended to mean an inclusive “or” and not an exclusive “or.” That is, unless otherwise specified or clear from context, “X utilizes A or B” is intended to mean one of the natural implicit substitutions. That is, either X uses A; X uses B; Or, if X uses both A and B, “X uses A or B” can apply to either of these cases.

Additionally, the terms “comprise” and/or “comprising” should be understood to mean that the corresponding feature and/or element is present. However, the terms "comprise" and/or "comprising" should be understood as not excluding the presence or addition of one or more other features, elements and/or groups thereof. Additionally, unless otherwise specified or the context is clear to indicate a singular form, the singular forms in this disclosure and claims should generally be construed to mean “one or more.”

And, the term “at least one of A or B” should be interpreted to mean “a case containing only A,” a case containing only B, or “a case of a combination of A and B.”

Those skilled in the art will additionally understand that the various illustrative logical blocks, configurations, modules, circuits, means, logics, and algorithm steps described in connection with the embodiments disclosed herein may be implemented in electronic hardware, computer software, or both. It should be recognized that it can be implemented with combinations of. To clearly illustrate the interchangeability of hardware and software, various illustrative components, blocks, configurations, means, logics, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented in hardware or software will depend on the specific application and design constraints imposed on the overall system. A skilled technician can implement the described functionality in a variety of ways for each specific application. However, such implementation decisions should not be construed as causing a departure from the scope of the present disclosure.

The description of the presented embodiments is provided to enable anyone skilled in the art to use or practice the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art. The general principles defined herein may be applied to other embodiments without departing from the scope of the disclosure. Therefore, the present disclosure is not limited to the embodiments presented herein. This disclosure is to be interpreted in the broadest scope consistent with the principles and novel features presented herein.

The configuration of the computing device 100 shown in FIG. 1 is only a simplified example. In one embodiment of the present disclosure, the computing device 100 may include different configurations for performing the computing environment of the computing device 100, and only some of the disclosed configurations may configure the computing device 100.

The computing device 100 may include a processor 110, a memory 130, and a network unit 150.

The processor 110 may be composed of one or more cores, and may include a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU) of a computing device. unit) may include a processor for data analysis and deep learning. The processor 110 may read a computer program stored in the memory 130 and perform data processing for machine learning according to an embodiment of the present disclosure. According to an embodiment of the present disclosure, the processor 110 may perform an operation for learning a neural network model. The processor 110 processes input data for learning in deep learning (DL), extracts features from input data, calculates errors, and learns neural network models such as updating the weights of the neural network model using backpropagation. You can perform calculations for . At least one of the CPU, GPGPU, and TPU of the processor 110 may process learning of the neural network model. For example, the CPU and GPGPU can work together to process neural network model learning and data classification using the neural network model. Additionally, in one embodiment of the present disclosure, the processors of a plurality of computing devices can be used together to process learning of a neural network model and data classification using the neural network model. Additionally, a computer program executed in a computing device according to an embodiment of the present disclosure may be a CPU, GPGPU, or TPU executable program.

According to an embodiment of the present disclosure, the memory 130 may store any type of information generated or determined by the processor 110 and any type of information received by the network unit 150.

According to an embodiment of the present disclosure, the memory 130 is a flash memory type, hard disk type, multimedia card micro type, or card type memory (e.g. (e.g. SD or -Only Memory), and may include at least one type of storage medium among magnetic memory, magnetic disk, and optical disk. The computing device 100 may operate in connection with web storage that performs a storage function of the memory 130 on the Internet. The description of the memory described above is merely an example, and the present disclosure is not limited thereto.

The network unit 150 according to an embodiment of the present disclosure includes Public Switched Telephone Network (PSTN), x Digital Subscriber Line (xDSL), Rate Adaptive DSL (RADSL), Multi Rate DSL (MDSL), and VDSL ( A variety of wired communication systems can be used, such as Very High Speed DSL), Universal Asymmetric DSL (UADSL), High Bit Rate DSL (HDSL), and Local Area Network (LAN).

In addition, the network unit 150 presented in the present disclosure includes Code Division Multi Access (CDMA), Time Division Multi Access (TDMA), Frequency Division Multi Access (FDMA), Orthogonal Frequency Division Multi Access (OFDMA), and SC-FDMA ( A variety of wireless communication systems can be used, such as Single Carrier-FDMA) and other systems.

In the present disclosure, the network unit 150 may be configured regardless of the communication mode, such as wired or wireless, and may be composed of various communication networks such as a personal area network (PAN) and a wide area network (WAN). You can. Additionally, the network may be the well-known World Wide Web (WWW), or may use wireless transmission technology used for short-distance communication, such as Infrared Data Association (IrDA) or Bluetooth. The techniques described in this disclosure can also be used in other networks mentioned above.

Figure 2 is a schematic diagram showing a neural network according to an embodiment of the present disclosure.

Throughout this disclosure, neural network, neural network model, and neural network may be used interchangeably. A neural network can generally consist of a set of interconnected computational units, which can be referred to as nodes. These nodes may also be referred to as neurons. A neural network consists of at least one node. Nodes (or neurons) that make up neural networks may be interconnected by one or more links.

Within a neural network, one or more nodes connected through a link can form a relative input node and output node relationship. The concepts of input node and output node are relative, and any node in an output node relationship with one node may be in an input node relationship with another node, and vice versa. As described above, input node to output node relationships can be created around links. One or more output nodes can be connected to one input node through a link, and vice versa.

In a relationship between an input node and an output node connected through one link, the value of the data of the output node may be determined based on the data input to the input node. Here, the link connecting the input node and the output node may have a weight (here, the terms parameter and weight may be used with the same meaning throughout the present disclosure). Weights may be variable and may be varied by the user or algorithm in order for the neural network to perform the desired function. For example, when one or more input nodes are connected to one output node by respective links, the output node is set to the values input to the input nodes connected to the output node and the links corresponding to each input node. The output node value can be determined based on the weight.

As described above, in a neural network, one or more nodes are interconnected through one or more links to form an input node and output node relationship within the neural network. The characteristics of the neural network can be determined according to the number of nodes and links within the neural network, the correlation between the nodes and links, and the value of the weight assigned to each link. For example, if the same number of nodes and links exist and two neural networks with different weight values of the links exist, the two neural networks may be recognized as different from each other.

A neural network may consist of a set of one or more nodes. A subset of nodes that make up a neural network can constitute a layer. Some of the nodes constituting the neural network may form one layer based on the distances from the first input node. For example, a set of nodes with a distance n from the initial input node may constitute an n layer. The distance from the initial input node can be defined by the minimum number of links that must be passed to reach the node from the initial input node. However, this definition of a layer is arbitrary for illustrative purposes, and the order of a layer within a neural network may be defined in a different way than described above. For example, a tier of nodes may be defined by their distance from the final output node.

The initial input node may refer to one or more nodes in the neural network through which data is directly input without going through links in relationships with other nodes. Alternatively, in a neural network network, in the relationship between nodes based on links, it may mean nodes that do not have other input nodes connected by links. Similarly, the final output node may refer to one or more nodes that do not have an output node in their relationship with other nodes among the nodes in the neural network. Additionally, hidden nodes may refer to nodes constituting a neural network other than the first input node and the last output node.

A neural network model including a neural network may be learned by at least one of supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. Learning a neural network model may be a process of applying knowledge for the neural network model to perform a specific operation to the neural network model.

Neural network models can be trained to minimize output errors. In the learning of a neural network model, learning data is repeatedly input into the neural network model, the output of the neural network model and the error of the target for the learning data are calculated, and the error of the neural network model is calculated from the output layer of the neural network model to the input layer in the direction of reducing the error. This is the process of updating the weight of each node in the neural network model through backpropagation. In the case of teacher learning, learning data in which the correct answer is labeled in each learning data is used (i.e., labeled learning data), and in the case of non-teacher learning, the correct answer may not be labeled in each learning data. That is, for example, in the case of teacher learning regarding data classification, the learning data may be data in which each learning data is labeled with a category. Labeled training data is input to the neural network model, and the error can be calculated by comparing the output (category) of the neural network model and the label of the training data. As another example, in the case of non-teachable learning for data classification, the error can be calculated by comparing the input learning data with the neural network model output. The calculated error is back-propagated in the neural network model in the reverse direction (i.e., from the output layer to the input layer), and the connection weight of each node in each layer of the neural network model can be updated according to the back-propagation. The amount of change in the connection weight of each updated node may be determined according to the learning rate. The calculation of a neural network model for input data and backpropagation of errors can constitute an epoch. The learning rate may be applied differently depending on the number of repetitions of the epoch of the neural network model. For example, in the early stages of training a neural network model, a high learning rate can be used to ensure that the neural network model quickly achieves a certain level of performance to increase efficiency, and in the latter stages of training, a low learning rate can be used to increase accuracy.

In the training of a neural network model, the training data can generally be a subset of real data (i.e., the data to be processed using the learned neural network model), and therefore, the error for the training data is reduced, but the error for the real data is reduced. There may be increasing epochs. Over-fitting is a phenomenon in which errors in actual data increase due to excessive learning on training data. For example, a phenomenon in which a neural network model that learned a cat by showing a yellow cat fails to recognize that it is a cat when it sees a non-yellow cat may be a type of overfitting. Overfitting can cause errors in machine learning algorithms to increase. To prevent such overfitting, various optimization methods can be used. To prevent overfitting, methods such as increasing the learning data, regularization, dropout that disables some of the network nodes during the learning process, and use of batch normalization can be applied. .

According to an embodiment of the present disclosure, a computer-readable medium storing a data structure is disclosed.

Data structure can refer to the organization, management, and storage of data to enable efficient access and modification of data. Data structure can refer to the organization of data to solve a specific problem (e.g., retrieving data, storing data, or modifying data in the shortest possible time). A data structure may be defined as a physical or logical relationship between data elements designed to support a specific data processing function. Logical relationships between data elements may include connection relationships between user-defined data elements. Physical relationships between data elements may include actual relationships between data elements that are physically stored in a computer-readable storage medium (e.g., a persistent storage device). A data structure may specifically include a set of data, relationships between data, and functions or instructions applicable to the data. Effectively designed data structures allow computing devices to perform computations while minimizing the use of the computing device's resources. Specifically, computing devices can increase the efficiency of operations, reading, insertion, deletion, comparison, exchange, and search through effectively designed data structures.

Data structures can be divided into linear data structures and non-linear data structures depending on the type of data structure. A linear data structure may be a structure in which only one piece of data is connected to another piece of data. Linear data structures may include List, Stack, Queue, and Deque. A list can refer to a set of data that has an internal order. The list may include a linked list. A linked list may be a data structure in which data is connected in such a way that each data is connected in a single line with a pointer. In a linked list, a pointer may contain connection information to the next or previous data. Depending on its form, a linked list can be expressed as a singly linked list, a doubly linked list, or a circularly linked list. A stack may be a data listing structure that allows limited access to data. A stack can be a linear data structure in which data can be processed (for example, inserted or deleted) at only one end of the data structure. Data stored in the stack may have a data structure (LIFO-Last in First Out) where the later it enters, the sooner it comes out. A queue is a data listing structure that allows limited access to data. Unlike the stack, it can be a data structure (FIFO-First in First Out) where data stored later is released later. A deck can be a data structure that can process data at both ends of the data structure.

A non-linear data structure may be a structure in which multiple pieces of data are connected behind one piece of data. Nonlinear data structures may include graph data structures. A graph data structure can be defined by vertices and edges, and an edge can include a line connecting two different vertices. Graph data structure may include a tree data structure. A tree data structure may be a data structure in which there is only one path connecting two different vertices among a plurality of vertices included in the tree. In other words, it may be a data structure that does not form a loop in the graph data structure.

The data structure may include a neural network model. And the data structure including the neural network model may be stored in a computer-readable medium. The data structure including the neural network model includes preprocessed data for processing by the neural network model, data input to the neural network model, weights of the neural network model, hyperparameters of the neural network model, data acquired from the neural network model, and each node or layer of the neural network model. It may include an activation function associated with, a loss function for learning a neural network model, etc. A data structure containing a neural network model may include any of the components disclosed above. In other words, the data structure including the neural network model includes data preprocessed for processing by the neural network model, data input to the neural network model, weights of the neural network model, hyperparameters of the neural network model, data acquired from the neural network model, each node of the neural network model, or It may be composed of all or any combination of the activation function associated with the layer, the loss function for learning the neural network model, etc. In addition to the configurations described above, the data structure containing the neural network model may include any other information that determines the characteristics of the neural network model. Additionally, the data structure may include all types of data used or generated in the computational process of the neural network model and is not limited to the above. Computer-readable media may include computer-readable recording media and/or computer-readable transmission media. A neural network model can generally consist of a set of interconnected computational units, which can be referred to as nodes. These nodes may also be referred to as neurons. A neural network model is composed of at least one node.

The data structure may include data input to the neural network model. A data structure containing data input to the neural network model may be stored in a computer-readable medium. Data input to the neural network model may include learning data input during the learning process of the neural network model and/or input data input to the neural network model on which training has been completed. Data input to the neural network model may include data that has undergone pre-processing and/or data subject to pre-processing. Preprocessing may include a data processing process to input data into a neural network model. Therefore, the data structure may include data subject to preprocessing and data generated by preprocessing. The above-described data structure is only an example and the present disclosure is not limited thereto.

The data structure may include weights of the neural network model. (In the present disclosure, weights and parameters may be used with the same meaning.) And the data structure including the weights of the neural network model may be stored in a computer-readable medium. A neural network model may include multiple weights. Weights may be variable and may be varied by the user or algorithm in order for the neural network model to perform the desired function. For example, when one or more input nodes are connected to one output node by respective links, the output node is set to the values input to the input nodes connected to the output node and the links corresponding to each input node. Based on the weight, the data value output from the output node can be determined. The above-described data structure is only an example and the present disclosure is not limited thereto.

As an example and not a limitation, the weight may include a weight that changes during the learning process of the neural network model and/or a weight that has completed training of the neural network model. Weights that vary during the learning process of a neural network model may include weights that change at the start of an epoch and/or weights that change during the epoch. Weights for which training of the neural network model has been completed may include weights for which the epoch has been completed. Therefore, the data structure including the weights of the neural network model may include weights that change during the learning process of the neural network model and/or the data structure including weights that have completed training of the neural network model. Therefore, the above-described weights and/or combinations of each weight are included in the data structure including the weights of the neural network model. The above-described data structure is only an example and the present disclosure is not limited thereto.

The data structure including the weights of the neural network model may be stored in a computer-readable storage medium (e.g., memory, hard disk) after going through a serialization process. Serialization can be the process of converting a data structure into a form that can be stored on the same or a different computing device and later reorganized and used. Computing devices can transmit and receive data over a network by serializing data structures. The data structure containing the weights of the serialized neural network model can be reconstructed on the same computing device or on a different computing device through deserialization. The data structure including the weights of the neural network model is not limited to serialization. Furthermore, the data structure including the weights of the neural network model is a data structure to increase computational efficiency while minimizing the use of computing device resources (e.g., B-Tree, Trie, m-way search tree, AVL tree in non-linear data structures). , Red-Black Tree). The foregoing is merely an example and the present disclosure is not limited thereto.

The data structure may include hyper-parameters of the neural network model. And the data structure including the hyper-parameters of the neural network model may be stored in a computer-readable medium. A hyperparameter may be a variable that can be changed by the user. Hyperparameters include, for example, learning rate, cost function, number of epoch repetitions, weight initialization (e.g., setting the range of weight values subject to weight initialization), It may include the number of hidden units (e.g., number of hidden layers, number of nodes in the hidden layer). The above-described data structure is only an example and the present disclosure is not limited thereto.

The neural network model in the present disclosure is Multilayer Perceptron (MLP), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), or, Transformer models, etc. may be used. However, the neural network model is not limited to this, and may include variable models such as GRU (Gated Recurrent Unit), GAN (Generative Adversarial Network), or Autoencoder.

A real camera referred to in this disclosure means a camera that produces real images of real objects or real backgrounds. In particular, a real camera according to an embodiment of the present disclosure may mean a real camera linked to extended reality (XR), virtual reality (VR), or augmented reality (AR) equipment. In one embodiment, the actual camera may be implemented in the form of a camera included in a wearable device, but is not limited to this. Meanwhile, the actual camera captures an image and can generate an image including the captured location and angle information in conjunction with a gyro sensor and a position sensor.

also. The virtual camera referred to in this disclosure may mean a virtual camera associated with a virtual space or virtual content. For example, the virtual camera may include a virtual camera associated with a reference point of view of virtual content created in virtual space, or may include a virtual camera that illuminates a specific point of view in virtual space. In addition to these exemplary cameras, various types of virtual cameras related to virtual content or virtual space may be included.

In order for a user existing in a real space to naturally experience a virtual space, in the case of VR, the movement of the virtual camera existing in the virtual space must follow the direction in which the real camera existing in the real space is looking (i.e. The virtual camera must be tracked to the real camera.)

On the other hand, in the case of AR and XR, since virtual objects must be naturally synthesized with images captured by a real camera, not only must the movement of the virtual camera be tracked with the movement of the real camera, but also the degree of distortion of the virtual camera must be adjusted. Needs to be. At this time, the task of adjusting the degree of distortion of the virtual camera to match the real camera may be expressed as “matching the real camera and the virtual camera” or “matching the real space and the virtual space” in this disclosure.

3 is a schematic diagram of a method for placing the same pattern at the same locations in virtual space and real space associated with a real camera, according to an embodiment of the present disclosure.

[0042] [0032] Referring now to FIG. 3, an embodiment of the present disclosure describes a method for adjusting a virtual camera 310. First, before the processor 110 adjusts the virtual camera 310 to match the virtual camera 310 and the real camera 330, the virtual camera 310 is directed to a virtual pattern existing in a virtual space and points to a real camera 310. The camera 330 assumes an environment facing a real pattern in real space 320 that has the same size and appearance as the virtual pattern.

In one embodiment, in the hypothesized environment, processor 110 places identical patterns at the same locations in virtual space 300 associated with virtual camera 310 and real space 320 associated with real camera 330. And adjustment information can be obtained. For example, even if the real camera 330 and the virtual camera 310 are looking in the same direction at the same location, the virtual camera ( The virtual pattern captured by 310 may be different from the actual pattern captured by the actual camera 330. At this time, the processor 110 may adjust (340) the virtual camera 310 so that the patterns included in the virtual pattern and the patterns included in the actual pattern are photographed identically for each focus information and rotation information. .

Expressed differently, the virtual pattern may include A, B, C and D as sub-virtual patterns, and the real pattern may include 1, 2, 3, and 4 as sub-real patterns. At this time, pair combinations of the sub-virtual pattern and the sub-real pattern may include [A, 1], [B, 2], [C, 3], and [D, 4]. The processor 110 matches the sub-virtual pattern A to the sub-real pattern 1, the sub-virtual pattern B to the sub-real pattern 2, and the sub-virtual pattern C to the sub-real pattern 3. , the virtual camera 310 and the real camera 330 can be matched by adjusting (340) the virtual camera 310 so that the sub-virtual pattern D matches the sub-real pattern 4. (FIG. 3 , 350) In addition, the processor 110 may repeat the process of adjusting (340) the virtual camera 310 for each focus information and rotation information, and for each focus information and rotation information combination, the virtual camera Adjustment information can be obtained by adjusting (310) (340).

Previously, it was mentioned that the processor 110 can obtain adjustment information by adjusting 340 the virtual camera 310 for each combination of focus information and rotation information. At this time, as the interval between each focus information and rotation information becomes narrower, the matching quality between the virtual camera 310 and the real camera 330 can be improved. However, as the interval becomes narrower, the amount of calculation of the processor 110 increases. , If the gap is too narrow, the resources of the processor 110 may not be used efficiently. Accordingly, in one related embodiment, the processor 110 may obtain adjustment information for the value between the intervals of each focus information and rotation information based on linear interpolation. For example, assuming that the sets of focus information and rotation information that the processor 110 will use to generate adjustment information are set 1 and set 3, the processor 110 adjusts the virtual camera 310 (340) Thus, adjustment information for sets 1 and 3 can be predicted, respectively, and adjustment information for sets 2 can be obtained using linear interpolation based on the adjustment information for set 1 and the adjustment information for sets 3.

The processor 110 adjusts the camera for each focus information and rotation information of the virtual camera 310, creating a virtual space 300 associated with the virtual camera 310 and a real space 320 associated with the real camera 330. The process of arranging identical patterns at the same position and obtaining adjustment information of the virtual camera 310 based on the arranged identical patterns is to determine the matching quality of the virtual camera 310 and the real camera 330. Although it is effective for improvement, it may be inefficient in terms of time and cost if used every time. To solve this problem, the adjustment information related to the focus information and rotation information mentioned in the above embodiments can be used as learning data for a neural network model used in the embodiments of the present disclosure that will be discussed later. That is, the processor 110 uses the “focus information and rotation information” obtained through various adjustment operations as input information, and uses the “adjustment information” of the virtual camera 310 obtained through the various adjustment operations as the correct answer. (GT; ground truth) information can be used to learn a neural network model, and through this learning process, a neural network model that predicts “adjustment information of the virtual camera 310” based on “focus information and rotation information” is created. It can also be implemented.

Meanwhile, the focus information may be related to the zoom of the virtual camera 310. For example, the focus information may include focus information for a specific zoom section.

Figure 4 is a schematic diagram of a method for generating training data for a neural network model, according to an embodiment of the present disclosure.

From now on, a method for generating learning data for a neural network model whose task is to generate adjustment information for a virtual camera for the purpose of matching a real camera and a virtual camera is disclosed.

In one embodiment, the processor 110 may obtain focus information and rotation information of a virtual camera. At this time, the focus information and rotation information of the virtual camera 400 may include sets of focus information and rotation information at intervals predetermined by the user. Additionally, the processor 110 may adjust 410 the virtual camera 400 by placing identical patterns at the same locations in the virtual space associated with the virtual camera 400 and the real space associated with the real camera, Based on the same arranged patterns, adjustment information can be obtained from the adjusted virtual camera 420. Additionally, the processor 110 may generate learning data that includes the focus information and rotation information as input information 401 and the adjustment information 421 as correct answer information 422.

In one embodiment, the “process of obtaining adjustment information of the virtual camera 400 based on the arranged identical patterns” performed by the processor 110 is based on the arranged identical patterns. The process may include adjusting the virtual camera 400 to match the shooting results of the virtual camera 400 and the shooting results of the real camera, and obtaining adjustment information of the adjusted virtual camera 420. For example, the processor 110 may adjust the virtual camera 400 so that the patterns included in the virtual pattern and the patterns included in the actual pattern are photographed identically for each focus information and rotation information. That is, the virtual pattern includes sub-virtual patterns A, B, C D, and the real pattern includes sub-real patterns 1, 2, 3, and 4, and [A, 1], [B, 2], [C , 3] and [D, 4] are related to each other, the processor 110 adjusts the virtual camera 400 so that the related patterns among the patterns captured by the virtual camera 400 and the real camera are located at the same position. You can. For example, the processor 110 sets the sub-virtual pattern A to the location of sub-real pattern 1, the sub-virtual pattern B to the location of sub-real pattern 2, and the sub-virtual pattern C to the location of sub-real pattern 3. In addition, the sub-virtual pattern D can match the virtual camera 400 and the real camera by adjusting the virtual camera 400 to go to the position of the sub-real pattern 4. (see Fig. 3, 350)

In one embodiment, the processor 110 may repeat the process of adjusting the virtual camera 400 for each focus information and rotation information, and for each combination of focus information and rotation information, the virtual camera 400 Adjustment information can be obtained by adjusting . Meanwhile, the focus information may include information related to enlarging and reducing the virtual camera.

In one embodiment, the adjustment information 421 of the virtual camera may include information for adjusting distortion of the virtual camera 400. For example, even if the virtual camera 400 and the real camera are pointing at exactly the same location and photographing the same type of target, the shooting results of the virtual camera and the shooting results of the real camera may be different from each other. At this time, the processor 110 may adjust the distortion of the virtual camera 400 to match the shooting result of the real camera and the adjusted shooting result of the virtual camera 420. In one embodiment, the information for adjusting the distortion of the virtual camera 400 may include offset information for adjusting various distortion parameters.

In one embodiment, the virtual camera and the real camera may be utilized to create XR content. For example, the physical camera may include a visual sensor included in an XR device for generating XR content. The XR device may include a display that can simultaneously show a virtual environment and a real environment to the user, and through the display, the user can experience an XR environment that is a mixture of the virtual environment and the real environment. For the user to experience a natural XR environment, a virtual camera and real camera matching method according to an embodiment of the present disclosure can be used.

In one embodiment, in the process of generating the learning data, the processor 110 may generate the learning data for each zoom section included in the entire zoom section. For example, the zoom section may include zoom sections at 1x intervals, such as 1x, 2x, 3x, 4x, and 5x. At this time, it may include focus information related to each zoom section, and the processor 110 changes the rotation information of the virtual camera for each zoom section, so that the virtual space associated with the virtual camera and the real space associated with the real camera are the same. Identical patterns can be placed at locations, and corresponding adjustment information and learning data can be generated.

Figure 5 is a schematic diagram of a method for training a neural network model, according to an embodiment of the present disclosure.

From now on, an embodiment of a method of training a neural network model using learning data consisting of correct answer information corresponding to input information obtained based on the above embodiments with reference to FIG. 5 will be disclosed.

Before describing an embodiment of a method for training the neural network model 510, an embodiment of a method for generating adjustment information using the neural network model 510 is disclosed.

In one embodiment, the processor 110 acquires focus information and rotation information (input information 500) of a virtual camera and utilizes the neural network model 510 to obtain the focus information and rotation information (input information 500 )), adjustment information 520 for adjusting the virtual camera can be generated. At this time, the neural network model 510 may include a model learned using learning data obtained based on arranging the same patterns at the same positions in the virtual space associated with the virtual camera and the real space associated with the real camera. there is.

As an example of the learning method, the processor 110 may predict the adjustment information 520 using the neural network model 510 based on the input information 500 included in the learning data. Subsequently, the processor 110 may generate a loss value 550 using the loss function 530 based on the predicted adjustment information 520 and the correct answer information 540 included in the learning data. Additionally, the processor 110 may train the neural network model 510 by back-propagating it to the neural network model 510 based on the loss value.

At this time, the method of generating the learning data includes the steps of the processor 110 acquiring focus information and rotation information of the virtual camera, and the processor 110 obtaining the same virtual space associated with the virtual camera and the real space associated with the real camera. Arranging identical patterns at positions, the processor 110 obtaining adjustment information of the virtual camera based on the arranged identical patterns, and the processor 110 obtaining the focus information and the It may include generating learning data, including rotation information, and including the adjustment information as correct answer information.

6 is a schematic diagram of a method for adjusting a real camera, according to an embodiment of the present disclosure.

Now, with reference to Figure 6, one embodiment of adjusting an actual camera is disclosed. Real cameras referred to in this disclosure may include pre-registered real cameras. Specifically, the actual camera may include a camera pre-adjusted by a dynamic pattern whose appearance or movement changes depending on the change in focus. At this time, the dynamic pattern may include a dynamic pattern displayed on a display fixed at a first position, and the actual camera may include a pre-adjusted camera fixed at a second position. For example, the dynamic pattern may be a fixed screen 600 located in front of the real camera (e.g., the first position), and the real camera is located in front of the fixed screen 600 (e.g., the first position). 2 position) and may include an actual camera 610 adjusted in such a way as to capture a dynamic pattern 601. At this time, the dynamic pattern may include a pattern that is expanded and contracted in proportion to the zoom information of the actual camera.

Meanwhile, the dynamic pattern may include a pattern that moves along a predetermined path or a pattern that moves randomly. In one embodiment, the processor 110 may correct distortion occurring as the dynamic pattern moves and may correct the actual camera.

Through this “method for adjusting a real camera according to an embodiment of the present disclosure,” an adjustment operation of a real camera that takes zoom information into account can be performed without “moving the camera by a person or moving a pattern by a person.” It can be implemented. Conventionally, in order to perform a zoom lens adjustment operation of a real camera, it was necessary for a person to directly move the camera or directly move the pattern according to a change in focus. According to an embodiment of the present disclosure, a real camera The “method for adjustment” may provide the technical effect of implementing a zoom lens adjustment operation without physically moving the camera or pattern.

FIG. 7 is a flowchart representing an overview process of a method for learning a neural network model for adjusting a virtual camera, according to an embodiment of the present disclosure, and FIG. 8 is a flowchart of using a neural network model, according to an embodiment of the present disclosure. This is a flowchart expressing the general process of how to adjust the virtual camera.

Referring to Figure 7, a general method of how processor 110 learns a neural network model to adjust a virtual camera is disclosed. The method includes the processor 110 acquiring focus information and rotation information of a virtual camera (S700); The processor 110 arranging the same patterns at the same positions in the virtual space associated with the virtual camera and the real space associated with the actual camera (S710); Obtaining adjustment information of the virtual camera based on the arranged identical patterns (S720); and generating learning data including the focus information and the rotation information as input information and the adjustment information as ground truth information (S730).

At this time, the step S720 may include the processor 110 acquiring adjustment information of the virtual camera to match the screen of the virtual camera and the screen of the real camera based on the arranged identical patterns. You can.

Additionally, step S730 may include the processor 110 generating the learning data for each zoom section included in the entire zoom section.

At this time, the adjustment information of the virtual camera may include information for adjusting distortion of the virtual camera, and the virtual camera and the real camera will be used to create extended reality (XR) content. You can.

Meanwhile, the real camera may include a camera pre-adjusted based on a dynamic pattern whose appearance dynamically changes according to a change in focus of the real camera. At this time, the dynamic pattern may include a dynamic pattern displayed on a display fixed at a first position, and the actual camera may include a pre-adjusted camera fixed at a second position.

With reference to Figure 8, a high-level process for how processor 110 adjusts a virtual camera is described. The method includes the processor 110 acquiring focus information and rotation information of the virtual camera (S800); And it may include a step (S810) of the processor 110 using a neural network model to generate adjustment information for adjusting the virtual camera based on the focus information and the rotation information.

At this time, in one embodiment, the neural network model may include a neural network model learned based on training data generated based on steps S700 to S730 mentioned above.

9 is a brief, general schematic diagram of an example computing environment in which embodiments of the present disclosure may be implemented.

Although the disclosure has been described above as being generally capable of being implemented by a computing device, those skilled in the art will understand that the disclosure can be implemented in combination with computer-executable instructions and/or other program modules that can be executed on one or more computers and/or hardware. It will be well known that it can be implemented as a combination of software.

Typically, program modules include routines, programs, components, data structures, etc. that perform specific tasks or implement specific abstract data types. Additionally, those skilled in the art will understand that the methods of the present disclosure can be used on single-processor or multiprocessor computer systems, minicomputers, mainframe computers, as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, etc. It will be appreciated that other computer system configurations may be implemented, including, but not limited to, each of which may operate in connection with one or more associated devices.

The described embodiments of the present disclosure may be practiced in a distributed computing environment where certain tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

Computers typically include a variety of computer-readable media. Computer-readable media can be any medium that can be accessed by a computer, and such computer-readable media includes volatile and non-volatile media, transitory and non-transitory media, removable and non-transitory media. Includes removable media. By way of example, and not limitation, computer-readable media may include computer-readable storage media and computer-readable transmission media. Computer-readable storage media refers to volatile and non-volatile media, transient and non-transitory media, removable and non-removable, implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Includes media. Computer readable storage media may include RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital video disk (DVD) or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage. This includes, but is not limited to, a device, or any other medium that can be accessed by a computer and used to store desired information.

A computer-readable transmission medium typically implements computer-readable instructions, data structures, program modules, or other data on a modulated data signal, such as a carrier wave or other transport mechanism. Includes all information delivery media. The term modulated data signal refers to a signal in which one or more of the characteristics of the signal have been set or changed to encode information within the signal. By way of example, and not limitation, computer-readable transmission media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared, and other wireless media. Combinations of any of the above are also intended to be included within the scope of computer-readable transmission media.

An example environment 1300 is shown that implements various aspects of the present disclosure, including a computer 1302, which includes a processing unit 1304, a system memory 1306, and a system bus 1308. do. System bus 1308 couples system components, including but not limited to system memory 1306, to processing unit 1304. Processing unit 1304 may be any of a variety of commercially available processors. Dual processors and other multiprocessor architectures may also be used as processing units 1304.

System bus 1308 may be any of several types of bus structures that may further be interconnected to a memory bus, peripheral bus, and local bus using any of a variety of commercial bus architectures. System memory 1306 includes read only memory (ROM) 1310 and random access memory (RAM) 1312. The basic input/output system (BIOS) is stored in non-volatile memory 1310, such as ROM, EPROM, and EEPROM, and is a basic input/output system that helps transfer information between components within the computer 1302, such as during startup. Contains routines. RAM 1312 may include high-speed RAM, such as static RAM for caching data.

Computer 1302 includes an internal hard disk drive (HDD) 1314 (e.g., EIDE, SATA), which internal hard disk drive 1314 may be configured for external use within a suitable chassis (not shown). , a magnetic floppy disk drive (FDD) 1316 (e.g., for reading from or writing to a removable diskette 1318), and an optical disk drive 1320 (e.g., a CD-ROM disk ( 1322) or for reading from or writing to other high-capacity optical media such as DVDs). Hard disk drive 1314, magnetic disk drive 1316, and optical disk drive 1320 are connected to system bus 1308 by hard disk drive interface 1324, magnetic disk drive interface 1326, and optical drive interface 1328, respectively. ) can be connected to. The interface 1324 for implementing an external drive includes at least one or both of Universal Serial Bus (USB) and IEEE 1394 interface technologies.

These drives and their associated computer-readable media provide non-volatile storage of data, data structures, computer-executable instructions, and the like. For computer 1302, drive and media correspond to storing any data in a suitable digital format. Although the description of computer-readable media above refers to removable optical media such as HDDs, removable magnetic disks, and CDs or DVDs, those of ordinary skill in the art will also recognize zip drives, magnetic cassettes, flash memory cards, and cartridges. It will be appreciated that other types of computer-readable media may also be used in the example operating environment, and that any such media may contain computer-executable instructions for performing the methods of the present disclosure. .

A number of program modules may be stored in drives and RAM 1312, including an operating system 1330, one or more application programs 1332, other program modules 1334, and program data 1336. All or portions of the operating system, applications, modules and/or data may be cached in RAM 1312. It will be appreciated that the present disclosure may be implemented on various commercially available operating systems or combinations of operating systems.

A user may enter commands and information into computer 1302 through one or more wired/wireless input devices, such as a keyboard 1338 and a pointing device such as mouse 1340. Other input devices (not shown) may include microphones, IR remote controls, joysticks, game pads, stylus pens, touch screens, etc. These and other input devices are connected to the processing unit 1304 through an input device interface 1342, which is often connected to the system bus 1308, but may also include a parallel port, an IEEE 1394 serial port, a game port, a USB port, an IR interface, It can be connected by other interfaces, etc.

A monitor 1344 or other type of display device is also connected to system bus 1308 through an interface, such as a video adapter 1346. In addition to monitor 1344, computers typically include other peripheral output devices (not shown) such as speakers, printers, etc.

Computer 1302 may operate in a networked environment using logical connections to one or more remote computers, such as remote computer(s) 1348, via wired and/or wireless communications. Remote computer(s) 1348 may be a workstation, computing device computer, router, personal computer, portable computer, microprocessor-based entertainment device, peer device, or other conventional network node, and is generally connected to computer 1302. For simplicity, only memory storage device 1350 is shown, although it includes many or all of the components described. The logical connections depicted include wired/wireless connections to a local area network (LAN) 1352 and/or a larger network, such as a wide area network (WAN) 1354. These LAN and WAN networking environments are common in offices and companies and facilitate enterprise-wide computer networks, such as intranets, all of which can be connected to a worldwide computer network, such as the Internet.

When used in a LAN networking environment, computer 1302 is connected to local network 1352 through wired and/or wireless communications network interfaces or adapters 1356. Adapter 1356 may facilitate wired or wireless communication to a local area network (LAN) 1352, which may include a wireless access point installed thereon for communicating with wireless adapter 1356. When used in a WAN networking environment, the computer 1302 may include a modem 1358 or be connected to a communicating computing device on the WAN 1354 or to establish communications over the WAN 1354, such as over the Internet. Have other means. Modem 1358, which may be internal or external and a wired or wireless device, is coupled to system bus 1308 via serial port interface 1342. In a networked environment, program modules described for computer 1302, or portions thereof, may be stored in remote memory/storage device 1350. It will be appreciated that the network connections shown are exemplary and that other means of establishing a communications link between computers may be used.

Computer 1302 may be associated with any wireless device or object deployed and operating in wireless communications, such as a printer, scanner, desktop and/or portable computer, portable data assistant (PDA), communications satellite, wirelessly detectable tag. Performs actions to communicate with any device or location and telephone. This includes at least Wi-Fi and Bluetooth wireless technologies. Accordingly, communication may be a predefined structure as in a conventional network or may simply be ad hoc communication between at least two devices.

Wi-Fi (Wireless Fidelity) allows connection to the Internet, etc. without wires. Wi-Fi is a wireless technology, like cell phones, that allows these devices, such as computers, to send and receive data indoors and outdoors, anywhere within the coverage area of a base station. Wi-Fi networks use wireless technology called IEEE 802.11 (a, b, g, etc.) to provide secure, reliable, and high-speed wireless connections. Wi-Fi can be used to connect computers to each other, the Internet, and wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in the unlicensed 2.4 and 5 GHz wireless bands, for example, at data rates of 11 Mbps (802.11a) or 54 Mbps (802.11b), or in products that include both bands (dual band). .

Those skilled in the art will understand that information and signals may be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols and chips that may be referenced in the above description include voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields. It can be expressed by particles or particles, or any combination thereof.

Those skilled in the art will understand that the various illustrative logical blocks, modules, processors, means, circuits and algorithm steps described in connection with the embodiments disclosed herein may be used in electronic hardware, (for convenience) It will be understood that it may be implemented by various forms of program or design code (referred to herein as software) or a combination of both. To clearly illustrate this interoperability of hardware and software, various illustrative components, blocks, modules, circuits and steps have been described above generally with respect to their functionality. Whether this functionality is implemented as hardware or software depends on the specific application and design constraints imposed on the overall system. A person skilled in the art of this disclosure may implement the described functionality in various ways for each specific application, but such implementation decisions should not be construed as departing from the scope of this disclosure.

The various embodiments presented herein may be implemented as a method, apparatus, or article of manufacture using standard programming and/or engineering techniques. The term article of manufacture includes a computer program, carrier, or media accessible from any computer-readable storage device. For example, computer-readable storage media include magnetic storage devices (e.g., hard disks, floppy disks, magnetic strips, etc.), optical disks (e.g., CDs, DVDs, etc.), smart cards, and flash. Includes, but is not limited to, memory devices (e.g., EEPROM, cards, sticks, key drives, etc.). Additionally, various storage media presented herein include one or more devices and/or other machine-readable media for storing information.

It is to be understood that the specific order or hierarchy of steps in the processes presented is an example of illustrative approaches. It is to be understood that the specific order or hierarchy of steps in processes may be rearranged within the scope of the present disclosure, based on design priorities. The appended method claims present elements of the various steps in a sample order but are not meant to be limited to the particular order or hierarchy presented.

The description of the presented embodiments is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments without departing from the scope of the disclosure. Thus, the present disclosure is not limited to the embodiments presented herein but is to be interpreted in the broadest scope consistent with the principles and novel features presented herein.

Claims (26)

A method for learning a neural network model for adjusting a virtual camera, performed by a computing device, comprising:
Obtaining focus information and rotation information of a virtual camera;
placing identical patterns at identical locations in virtual space associated with the virtual camera and real space associated with the actual camera;
Obtaining adjustment information of the virtual camera based on the arranged identical patterns; and
generating learning data including the focus information and the rotation information as input information and the adjustment information as ground truth information;
Including,
The step of acquiring adjustment information of the virtual camera based on the arranged identical patterns,
Based on the arranged identical patterns, obtaining adjustment information of the virtual camera to match the screen of the virtual camera with the screen of the real camera.
Including,
method.
delete According to claim 1,
The adjustment information of the virtual camera includes information for adjusting distortion of the virtual camera.
method.
According to claim 1,
The virtual camera and the real camera are used to create extended reality (XR) content,
method.
According to claim 1,
The step of generating the learning data is,
Including generating the learning data for each zoom section included in the entire zoom section,
method.
According to claim 1,
The actual camera is,
A camera pre-adjusted based on a dynamic pattern whose appearance dynamically changes depending on the change in focus of the actual camera,
method.
According to claim 6,
The dynamic pattern includes a dynamic pattern displayed on a display fixed to a first position,
The actual camera is a pre-adjusted camera fixed in a second position,
method.
A device for learning a neural network model that adjusts a virtual camera,
at least one processor; and
Memory;
Including,
The at least one processor,
Obtain focus information and rotation information of the virtual camera,
Arranging identical patterns at the same locations in virtual space associated with the virtual camera and real space associated with the real camera,
Based on the arranged identical patterns, obtain adjustment information of the virtual camera,
Generating learning data, including the focus information and the rotation information as input information and the adjustment information as ground truth information,
Obtaining adjustment information of the virtual camera based on the arranged identical patterns includes:
Based on the arranged identical patterns, obtaining adjustment information of the virtual camera to match the screen of the virtual camera with the screen of the real camera.
Including,
Device.
delete According to claim 8,
The adjustment information of the virtual camera is,
Containing information for adjusting distortion of the virtual camera,
Device.
According to claim 8,
The virtual camera and the real camera are used to create extended reality (XR) content,
Device.
According to claim 8,
The at least one processor,
Additional configured to generate the learning data for each zoom section included in the entire zoom section,
Device.
According to claim 8,
The actual camera is,
A camera pre-adjusted based on a dynamic pattern whose appearance dynamically changes depending on the change in focus of the actual camera,
Device.
According to claim 13,
The dynamic pattern includes a dynamic pattern displayed on a display fixed to a first position,
The actual camera is a pre-adjusted camera fixed in a second position,
Device.
A computer program stored on a computer-readable storage medium, the program causing at least one processor to perform operations that train a neural network model to adjust a virtual camera, the operations comprising:
An operation of acquiring focus information and rotation information of a virtual camera;
placing identical patterns at identical locations in a virtual space associated with the virtual camera and a real space associated with the actual camera;
Obtaining adjustment information of the virtual camera based on the arranged identical patterns; and
An operation of generating learning data, including the focus information and the rotation information as input information and the adjustment information as ground truth information;
Including,
The operation of obtaining adjustment information of the virtual camera based on the arranged identical patterns includes:
An operation of obtaining adjustment information of the virtual camera to match the screen of the virtual camera with the screen of the real camera, based on the arranged identical patterns.
Including,
A computer program stored on a computer-readable storage medium.
delete According to claim 15,
The adjustment information of the virtual camera includes information for adjusting distortion of the virtual camera.
A computer program stored on a computer-readable storage medium.
According to claim 15,
The virtual camera and the real camera are used to create extended reality (XR) content,
A computer program stored on a computer-readable storage medium.
According to claim 15,
The operation of generating the learning data is,
Including the operation of generating the learning data for each zoom section included in the entire zoom section,
A computer program stored on a computer-readable storage medium.
According to claim 15,
The actual camera is,
A camera pre-adjusted based on a dynamic pattern whose appearance dynamically changes depending on the change in focus of the actual camera,
A computer program stored on a computer-readable storage medium.
According to claim 20,
The dynamic pattern includes a dynamic pattern displayed on a display fixed to a first position,
The actual camera is a pre-adjusted camera fixed in a second position,
A computer program stored on a computer-readable storage medium.
A data structure included in a computer-readable storage medium, comprising:
The data structure corresponds to parameters of a neural network, at least in part updated during a learning process, and the operation of the neural network is based at least in part on the parameters, and the learning process includes:
Obtaining focus information and rotation information of a virtual camera;
placing identical patterns at identical locations in virtual space associated with the virtual camera and real space associated with the actual camera;
Obtaining adjustment information of the virtual camera based on the arranged identical patterns; and
generating learning data including the focus information and the rotation information as input information and the adjustment information as ground truth information;
Including,
The step of acquiring adjustment information of the virtual camera based on the arranged identical patterns,
Based on the arranged identical patterns, obtaining adjustment information of the virtual camera to match the screen of the virtual camera with the screen of the real camera.
Including,
A data structure contained in a computer-readable storage medium.
1. A method of adjusting a virtual camera, performed by a computing device, comprising:
Obtaining focus information and rotation information of the virtual camera; and
Generating adjustment information for adjusting the virtual camera based on the focus information and rotation information using a neural network model.
Including,
The neural network model is a model learned using training data generated based on arranging identical patterns at the same locations in a virtual space associated with the virtual camera and a real space associated with the actual camera,
The learning data is,
Generated by obtaining adjustment information of the virtual camera to match the screen of the virtual camera and the screen of the real camera, based on the arranged identical patterns,
method.
A device for adjusting a virtual camera, comprising:
at least one processor; and
Memory;
Including,
The at least one processor,
Obtain focus information and rotation information of the virtual camera,
Utilizing a neural network model to generate adjustment information for adjusting the virtual camera based on the focus information and the rotation information,
The neural network model is a model learned using learning data obtained based on arranging the same patterns at the same positions in the virtual space associated with the virtual camera and the real space associated with the real camera,
The learning data is,
Generated by obtaining adjustment information of the virtual camera to match the screen of the virtual camera and the screen of the real camera, based on the arranged identical patterns,
Device.
A computer program stored on a computer-readable storage medium, the program performing operations for adjusting a virtual camera with at least one processor, the operations comprising:
Obtaining focus information and rotation information of the virtual camera; and
An operation of generating adjustment information for adjusting the virtual camera based on the focus information and the rotation information using a neural network model.
Including,
The neural network model is a model learned using learning data obtained based on arranging the same patterns at the same positions in the virtual space associated with the virtual camera and the real space associated with the real camera,
The learning data is,
Generated by obtaining adjustment information of the virtual camera to match the screen of the virtual camera and the screen of the real camera, based on the arranged identical patterns,
A computer program stored on a computer-readable storage medium.
A data structure included in a computer-readable storage medium, comprising:
The data structure corresponds to parameters of a neural network model, and the neural network model performs the following steps based at least in part on the parameters, the steps being:
Obtaining focus information and rotation information of a virtual camera; and
Generating adjustment information for adjusting the virtual camera based on the focus information and rotation information using a neural network model.
Including,
The neural network model is a model learned using learning data obtained based on arranging the same patterns at the same positions in the virtual space associated with the virtual camera and the real space associated with the real camera,
The learning data is,
Generated by obtaining adjustment information of the virtual camera to match the screen of the virtual camera and the screen of the real camera, based on the arranged identical patterns,
A data structure contained in a computer-readable storage medium.