Method and device for determining color information in a radiation field

Abstract

Embodiments of the present application provide a method and device for determining color information in a radiance field. The method comprises: obtaining density information of a three-dimensional point in the radiance field and a plurality of observation images of the radiance field in at least two observation directions; and determining color information of the three-dimensional point based on the plurality of observation images and the density information. The technical solution provided by the embodiments can be used in the field of rendering. By analyzing and processing the density information of the three-dimensional point in the radiance field and the plurality of observation images, the color information of the three-dimensional point can be determined. Thus, the density information and the color information in the radiance field are decoupled. This not only reduces the amount of information that needs to be iteratively learned, i.e., only the density information needs to be iteratively solved, avoiding iterative solving of the color information, but also effectively reduces the data processing resources for determining the color information, making the expression and learning of the radiance field easier, thereby embodying the practicality of the method.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to a method and apparatus for determining color information in a radiation field. Background Technology

[0002] A radiance field (RF) is a representation of three-dimensional space that can express each point in three-dimensional space as its density and color. The density information of each point is a scalar greater than or equal to 0; the color information of each point is an anisotropic vector containing the color of the point in each direction in space, and the color information in each direction can be different.

[0003] Currently, to obtain density and color information in a radiation field, gradient descent is often used to iteratively process the image to acquire the learned density and color information. However, this learning process often requires simultaneous estimation of both density and color information, which not only couples the processing of these two types of information but also increases the difficulty of training due to the large number of learnable parameters. Summary of the Invention

[0004] This invention provides a method and apparatus for determining color information in a radiation field. The color information in the radiation field is directly estimated through density information, which not only decouples the density information and color information in the radiation field, but also reduces the resource information required to determine the density information and color information.

[0005] In a first aspect, embodiments of the present invention provide a method for determining color information in a radiation field, comprising:

[0006] Acquire density information of three-dimensional points in the radiation field and multiple observation images of the radiation field in at least two observation directions;

[0007] Based on the multiple observed images and the density information, the color information of the three-dimensional points is determined.

[0008] Secondly, embodiments of the present invention provide a device for determining color information in a radiation field, comprising:

[0009] The first acquisition module is used to acquire density information of three-dimensional points in the radiation field and multiple observation images of the radiation field in at least two observation directions;

[0010] The first processing module is used to determine the color information of the three-dimensional points based on the multiple observation images and the density information.

[0011] Thirdly, embodiments of the present invention provide an electronic device, including: a memory and a processor; wherein the memory is used to store one or more computer instructions, wherein when the one or more computer instructions are executed by the processor, the method for determining color information in a radiation field described in the first aspect is implemented.

[0012] Fourthly, embodiments of the present invention provide a computer storage medium for storing a computer program, which, when executed by a computer, implements the method for determining color information in a radiation field as described in the first aspect above.

[0013] Fifthly, embodiments of the present invention provide a computer program product, comprising: a computer program, which, when executed by a processor of an electronic device, causes the processor to perform the steps in the method for determining color information in a radiation field as described in the first aspect.

[0014] Sixthly, embodiments of the present invention provide a method for determining color information in a radiation field, comprising:

[0015] Obtain the three-dimensional point to be observed in the radiation field and the observation direction corresponding to the three-dimensional point to be observed;

[0016] Determine the basis function coefficients and the preset basis function used to identify the color information of preset points in the radiation field;

[0017] The color information of the three-dimensional point to be observed is determined by interpolation processing of the basis function coefficients and the preset basis function in the observation direction.

[0018] In a seventh aspect, embodiments of the present invention provide an apparatus for determining color information in a radiation field, comprising:

[0019] The second acquisition module is used to acquire the three-dimensional point to be observed in the radiation field and the observation direction corresponding to the three-dimensional point to be observed.

[0020] The second determining module is used to determine the basis function coefficients and the preset basis function used to identify the color information of preset points in the radiation field;

[0021] The second processing module is used to perform interpolation processing on the observation direction based on the basis function coefficients and the preset basis function to determine the color information of the three-dimensional point to be observed.

[0022] Eighthly, embodiments of the present invention provide an electronic device, including: a memory and a processor; wherein the memory is used to store one or more computer instructions, wherein when the one or more computer instructions are executed by the processor, the method for determining color information in a radiation field described in the sixth aspect above is implemented.

[0023] In a ninth aspect, embodiments of the present invention provide a computer storage medium for storing a computer program that, when executed by a computer, implements the method for determining color information in a radiation field as described in the sixth aspect above.

[0024] In a tenth aspect, embodiments of the present invention provide a computer program product, comprising: a computer program that, when executed by a processor of an electronic device, causes the processor to perform the steps in the method for determining color information in a radiation field as described in the sixth aspect above.

[0025] Eleventhly, embodiments of the present invention provide a method for determining color information in a radiation field, comprising:

[0026] In response to a request to invoke the color confirmation service, determine the processing resources corresponding to the color confirmation service;

[0027] The processing resources are used to perform the following steps: acquire density information of three-dimensional points in the radiation field and multiple observation images of the radiation field in at least two observation directions; and determine the color information of the three-dimensional points based on the multiple observation images and the density information.

[0028] In a twelfth aspect, embodiments of the present invention provide an apparatus for determining color information in a radiation field, comprising:

[0029] The third determining module is used to determine the processing resources corresponding to the color confirmation service in response to a request to call the color confirmation service;

[0030] The third processing module is used to perform the following steps using the processing resources: acquiring density information of three-dimensional points in the radiation field and multiple observation images of the radiation field in at least two observation directions; and determining the color information of the three-dimensional points based on the multiple observation images and the density information.

[0031] In a thirteenth aspect, embodiments of the present invention provide an electronic device, including: a memory and a processor; wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions, when executed by the processor, implement the method for determining color information in a radiation field as described in the eleventh aspect above.

[0032] In a fourteenth aspect, embodiments of the present invention provide a computer storage medium for storing a computer program that, when executed by a computer, implements the method for determining color information in a radiation field as described in the eleventh aspect above.

[0033] In a fifteenth aspect, embodiments of the present invention provide a computer program product, comprising: a computer program that, when executed by a processor of an electronic device, causes the processor to perform the steps in the method for determining color information in a radiation field as described in the eleventh aspect above.

[0034] The technical solution provided in this embodiment can determine the color information of three-dimensional points by analyzing and processing the density information of three-dimensional points in the radiation field and multiple observation images. Compared with the existing technology that determines density and color information through iteration, this not only reduces the amount of information that needs to be iteratively learned (i.e., only the density information needs to be iteratively solved, avoiding the iterative solution for color information), but also effectively reduces the data processing resources required to determine density and color information. This decouples the density and color information in the radiation field, making the expression and learning of the radiation field easier, thus demonstrating the practicality of the method and facilitating its market promotion and application. Attached Figure Description

[0035] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 A schematic diagram of a method for determining color information in a radiation field according to an embodiment of the present invention;

[0037] Figure 2 This is a flowchart illustrating a method for determining color information in a radiation field according to an embodiment of the present invention.

[0038] Figure 3 This is a schematic diagram illustrating the acquisition of the observation angle of a three-dimensional point relative to various observation images, provided in an embodiment of the present invention.

[0039] Figure 4 This is a schematic diagram of a process for determining the confidence level of each observed color based on the density information, as provided in an embodiment of the present invention.

[0040] Figure 5 A flowchart illustrating the process of determining the color information of a three-dimensional point based on the observed color, the observed angle, and the confidence level, provided in an embodiment of the present invention.

[0041] Figure 6 A schematic diagram illustrating another method for determining color information in a radiation field, provided as an application embodiment of the present invention;

[0042] Figure 7 This is a schematic diagram of a device for determining color information in a radiation field, provided in an embodiment of the present invention.

[0043] Figure 8 To and Figure 7 A schematic diagram of the electronic device corresponding to the device for determining color information in a radiation field provided in the embodiment shown;

[0044] Figure 9 This is a schematic diagram of a device for determining color information in a radiation field, provided in an embodiment of the present invention.

[0045] Figure 10 To and Figure 9 A schematic diagram of the electronic device corresponding to the device for determining color information in a radiation field provided in the embodiment shown;

[0046] Figure 11 A flowchart illustrating another method for determining color information in a radiation field provided by an embodiment of the present invention;

[0047] Figure 12 A schematic diagram of the structure of another device for determining color information in a radiation field provided in an embodiment of the present invention;

[0048] Figure 13 To and Figure 12 A schematic diagram of the electronic device corresponding to the device for determining color information in a radiation field provided in the embodiment shown;

[0049] Figure 14 A flowchart illustrating another method for determining color information in a radiation field provided by an embodiment of the present invention;

[0050] Figure 15 A schematic diagram of another device for determining color information in a radiation field provided in an embodiment of the present invention;

[0051] Figure 16 To and Figure 15 The illustrated embodiment provides a schematic diagram of the electronic device corresponding to the device for determining color information in a radiation field. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0053] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” used in the embodiments of this invention and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. “Multiple” generally includes at least two, but does not exclude the inclusion of at least one.

[0054] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0055] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0056] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a product or system comprising a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a product or system. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the product or system that includes said element.

[0057] Furthermore, the timing of the steps in the following method embodiments is merely an example and not a strict limitation.

[0058] Terminology definition:

[0059] Radiance Field (RF): A representation of three-dimensional space that expresses each point in the space as its density and color. The density information of each point is a scalar greater than or equal to 0; the color information of each point is an anisotropic vector containing the color of the point in each direction in space, and the color information in each direction can be different.

[0060] Spherical harmonics (SH) are a set of orthogonal basis functions defined in spherical coordinates. Theoretically, a linear combination of spherical harmonics can approximate any function defined in spherical coordinates within acceptable error ranges. Spherical harmonics have wide applications; in computer graphics, they are often used to represent the color information of a point in space in various directions. Each spherical harmonic basis function can be indicated by its degree and order. Typically, all spherical harmonic basis functions of degree 0-2 are expanded using Cartesian coordinates as follows (function Y... l m (where the subscript l represents the degree and the superscript m represents the order, and -l ≤ m ≤ l, l ∈ N):

[0061]

[0062]

[0063] Where (x, y, z) are the coordinates of the point in the Cartesian coordinate system.

[0064] Explicit and implicit representations of the radiation field: Explicit representation refers to directly storing the density and color information at each point in the radiation field. However, since position and angle are continuous in space, they cannot be directly stored. Therefore, to address the issue of positional continuity, space is often divided into discrete three-dimensional lattices (i.e., voxels) to form a volume model. Only the information at the vertices of the voxels is stored, while the information at non-vertices is obtained through spatial trilinear interpolation. To address the issue of angular continuity, a set of spherical harmonic functions can be used as basis functions to represent color information, requiring only the coefficients of the basis functions to be stored.

[0065] Analytical solution, also known as a closed-form solution, refers to a solution that can be calculated in one step using a derived analytical formula, as opposed to an iterative solution. Theoretically, the solution is unique. In contrast, iterative solutions require multiple iterations, and subsequent iterations rely on the results of previous iterations. The final solution is affected by the initial solution, the number of iterations, and other factors, and theoretically, the solution is not unique.

[0066] Neural Radiance Field (NeRF): A radiation field represented by a neural network. It is usually represented by a Multi-Layer Perceptron (MLP). The input of an MLP is the three-dimensional coordinates and orientation of a point in the scene, and the output is the density at the input point and the color of the input point in the input orientation.

[0067] To understand the specific implementation process of the technical solution in this embodiment, the relevant technologies will be explained below:

[0068] The generation of 3D content is one of the key aspects of extended reality (XR) applications, and the reconstruction and representation of 3D information of people, objects, and environments provides core technological support for this. Extended reality (XR) can include at least one of the following: augmented reality (AR), virtual reality (VR), or mixed reality (MR).

[0069] Currently, density and color information in a radiation field can be obtained by iteratively processing an image using gradient descent. However, this learning process often requires simultaneous estimation of both density and color information, coupling the learning processes for these two types of information together. Furthermore, the large number of learnable parameters increases the difficulty of training.

[0070] To address the aforementioned technical problems, this embodiment proposes a method and apparatus for determining color information in a radiation field. The execution entity of the method for determining color information in a radiation field can be a device for determining color information in a radiation field. This device can be implemented as a local server or a cloud server. In this case, the method for determining color information in a radiation field can be executed in the cloud. Several computing nodes (cloud servers) can be deployed in the cloud, each with computing, storage, and other processing resources. In the cloud, multiple computing nodes can be organized to provide a certain service; of course, a single computing node can also provide one or more services. The cloud can provide this service by providing a service interface, which users can call to use the corresponding service. Service interfaces include Software Development Kits (SDKs), Application Programming Interfaces (APIs), etc.

[0071] For details, please refer to the appendix. Figure 1As shown, the device for determining color information in the radiation field can be communicatively connected to a client or a requesting end. Regarding the solution provided in this embodiment, the cloud can provide a service interface for determining color information in the radiation field. The user, through the client / requesting end, calls this service interface to trigger a request to the cloud to call the lossless compression service interface for the genome data. The cloud determines a computing node to respond to the request and utilizes the processing resources in that computing node to perform the specific processing operation for determining the color information in the radiation field.

[0072] The client / requesting end can be any computing device with a certain data transmission capability. Specifically, it can be a mobile phone, a personal computer (PC), a tablet computer, a configuration application, etc. Furthermore, the basic structure of the client / requesting end can include at least one processor. The number of processors depends on the configuration and type of the client / requesting end. The client / requesting end may also include memory, which can be volatile, such as RAM, or non-volatile, such as read-only memory (ROM), flash memory, etc., or both types. The memory typically stores the operating system (OS), one or more applications, and may also store program data. In addition to the processing unit and memory, the client / requesting end also includes some basic configurations, such as a network interface card (NIC) chip, an I / O bus, a display component, and some peripheral devices. Optionally, some peripheral devices may include, for example, a keyboard, a mouse, a stylus, a printer, etc. Other peripheral devices are well known in the art and will not be described in detail here.

[0073] A device for determining color information in a radiation field refers to a device that can provide color information determination services in a network virtual environment. It typically refers to a device that utilizes a network for information planning and color information determination operations within a radiation field. Physically, this device can be any device capable of providing computing services, responding to service requests, and processing data; for example, it could be a cluster server, a regular server, a cloud server, a cloud host, or a virtual data center. The main components of a device for determining color information in a radiation field include a processor, hard drive, memory, and system bus, similar to a general computer architecture.

[0074] In this embodiment described above, the client can establish a network connection with the device for determining color information in the radiation field. This network connection can be wireless or wired. If the client and the device for determining color information in the radiation field are connected via communication, the mobile network standard can be any one of 2G (GSM), 2.5G (GPRS), 3G (WCDMA, TD-SCDMA, CDMA2000, UTMS), 4G (LTE), 4G+ (LTE+), WiMax, 5G, or 6G.

[0075] In this embodiment, the client can acquire density information of three-dimensional points in the radiation field and multiple observation images corresponding to the radiation field. The three-dimensional points can be any spatial point in the radiation field, and the multiple observation images correspond to at least two different observation directions in the radiation field. Specifically, the client can display an interactive interface through which the user can configure or upload data to obtain the density information of three-dimensional points in the radiation field and multiple observation images. After acquiring the density information of the three-dimensional points and multiple observation images, the user can send these to a device for determining color information in the radiation field.

[0076] A device for determining color information in a radiation field is used to acquire density information of three-dimensional points and multiple observation images sent by a client. The density information and multiple observation images can then be analyzed and processed to determine the color information of the three-dimensional points. In some instances, analyzing and processing the density information and multiple observation images to determine the color information of the three-dimensional points may include: acquiring a pre-trained machine learning model or neural network model, which is used to determine the color information of the three-dimensional points; inputting the density information of the three-dimensional points and multiple observation images into the machine learning model or neural network model to obtain the color information of the three-dimensional points output by the machine learning model or neural network model.

[0077] The technical solution provided in this embodiment can determine the color information of three-dimensional points by analyzing and processing the density information of three-dimensional points in the radiation field and multiple observation images. Compared with the existing technology that determines density and color information through iteration, this solution avoids iteratively solving for color information and only needs to iteratively solve for density information. This decouples the density and color information in the radiation field, which not only reduces the amount of information that needs to be iteratively learned, but also effectively reduces the data processing resources required to determine density and color information. This makes the representation and learning of the radiation field easier, thus demonstrating the practicality of the method and facilitating its market promotion and application.

[0078] The following detailed description of some embodiments of the present invention is provided in conjunction with the accompanying drawings. Where there is no conflict between the embodiments, the following embodiments and features can be combined with each other. Furthermore, the timing of the steps in the following method embodiments is merely an example and not a strict limitation.

[0079] Figure 2 This is a flowchart illustrating a method for determining color information in a radiation field according to an embodiment of the present invention; see attached diagram. Figure 2 As shown, this embodiment provides a method for determining color information in a radiation field. The execution subject of this method can be a device for determining color information in a radiation field. It is understood that this device can be implemented as software, or a combination of software and hardware. Specifically, when the device is implemented as hardware, it can be various electronic devices with the function of determining color information in a radiation field, including but not limited to tablet computers, personal computers (PCs), servers, etc. When the device is implemented as software, it can be installed in the aforementioned electronic devices. Based on the aforementioned device for determining color information in a radiation field, the method for determining color information in a radiation field in this embodiment can include the following steps:

[0080] Step S201: Obtain the density information of three-dimensional points in the radiation field and multiple observation images of the radiation field in at least two observation directions.

[0081] Step S202: Determine the color information of the three-dimensional points based on multiple observation images and density information.

[0082] The specific implementation principles and effects of each of the above steps are explained in detail below:

[0083] Step S201: Obtain the density information of three-dimensional points in the radiation field and multiple observation images of the radiation field in at least two observation directions.

[0084] The radiation field may include multiple three-dimensional points, each of which can be represented by density and color information. Once the density information of the three-dimensional points in the radiation field is determined, the color information of the three-dimensional points can be determined by combining multiple observation images of the radiation field in at least two observation directions. Therefore, when a user needs to determine the color information of a certain three-dimensional point (which may be a vertex or a non-vertex) in the radiation field, the user can input the density information of the three-dimensional point in the radiation field and multiple observation images into the color information determination device in the radiation field (hereinafter referred to as the "determination device"). Specifically, the determination device may display an interactive interface, through which the user can perform interactive operations, thereby enabling the determination device to reliably obtain the density information of the three-dimensional point in the radiation field and multiple observation images through the user's input operations; alternatively, the density information of the three-dimensional point in the radiation field and multiple observation images are stored in a third device, which is communicatively connected to the determination device. In this case, the determination device can actively or passively obtain the density information of the three-dimensional point in the radiation field and multiple observation images through the third device.

[0085] Furthermore, the number of observation images can be two or more. It is understood that the more observation images there are, the more accurate the color information of the determined 3D points will be, and correspondingly, the more data processing time and computing resources will be required. Conversely, the fewer observation images there are, the less accurate the color information of the determined 3D points will be, and correspondingly, the less data processing time and computing resources will be required. Specifically, those skilled in the art can determine the specific number of observation images based on the specific application scenario or application requirements.

[0086] Step S202: Determine the color information of the three-dimensional points based on multiple observation images and density information.

[0087] After acquiring multiple observation images and density information, these images and information can be analyzed and processed to determine the color information of the three-dimensional points. In some instances, a machine learning model or neural network model is pre-trained to determine the color information of the three-dimensional points based on the observation images and density information. After acquiring multiple observation images and density information, these images and information can be input into the machine learning model or neural network model to obtain the color information of the three-dimensional points output by the machine learning model or neural network model.

[0088] In other instances, not only can the color information of three-dimensional points be determined through machine learning models or neural network models, but also by using preset algorithms to analyze and process the density and color information of three-dimensional points in the radiation field to determine the color information of the three-dimensional points. In this case, determining the color information of three-dimensional points based on multiple observation images and density information may include: obtaining the observed color of the three-dimensional point on each observation image and the observation angle of the three-dimensional point relative to each observation image; determining the confidence level of each observed color based on the density information; and determining the color information of the three-dimensional point based on the observed color, observation angle, and confidence level.

[0089] Since the color information of a three-dimensional point in the radiation field is anisotropic, meaning that different color information can be obtained when observing a three-dimensional point from different observation directions, and since multiple observation images correspond to at least two observation directions, in order to accurately determine the color information of a three-dimensional point in a certain observation direction, the three-dimensional point and each observation image can be analyzed and processed to obtain the observed color of the three-dimensional point on each observation image and the observation angle of the three-dimensional point relative to each observation image.

[0090] Specifically, the observed color of a 3D point on each observation image can be obtained by analyzing and processing the projection points of the 3D point on each observation image. At this time, obtaining the observed color of a 3D point on each observation image may include: obtaining the color information of the projection points of the 3D point on each observation image; and determining the color information of the projection points as the observed color.

[0091] Obtaining the color information of the projection points of the 3D points on various observation images may include: obtaining the camera intrinsic and extrinsic parameters (including camera intrinsic and extrinsic parameters) corresponding to the observation images. The camera intrinsic parameters refer to parameters related to the camera's own characteristics, such as the camera's focal length, pixel size, etc.; the camera extrinsic parameters are parameters in the world coordinate system, such as the camera's position, rotation direction, etc.; after obtaining the camera intrinsic and extrinsic parameters, the projection points of the 3D points on various observation images can be determined based on the camera intrinsic and extrinsic parameters; linear interpolation calculations are performed on the projection points to obtain the color information of the projection points, and the obtained color information may include the colors corresponding to the red, green, and blue channels.

[0092] In addition, the observation angle of a 3D point relative to each observation image can be determined by the camera origin corresponding to each observation image. In this case, obtaining the observation angle of a 3D point relative to each observation image may include: determining the camera origin corresponding to each observation image; obtaining the direction vector between the 3D point and the camera origin; and determining the observation angle based on the direction vector. In some instances, the direction vector can be directly used to express the observation angle, thereby effectively ensuring the accuracy and reliability of determining the observation angle.

[0093] For example, see attached document. Figure 3 As shown, multiple observation images may include observation image I1, observation image I2, observation image I3 and observation image I4. Each of the above observation images I1, observation image I2, observation image I3 and observation image I4 corresponds to camera intrinsic and extrinsic parameters. Specifically, the camera intrinsic and extrinsic parameters may include camera intrinsic and extrinsic parameters C1, camera intrinsic and extrinsic parameters C2, camera intrinsic and extrinsic parameters C3 and camera intrinsic and extrinsic parameters C4.

[0094] Since the observation directions corresponding to any two of the above observation images are different, after obtaining the three-dimensional points, the camera origin corresponding to each observation image can be determined, and then the direction vector between the three-dimensional points and the camera origin can be obtained. Specifically, for observation image C1, the direction vector d1 can be obtained. Similarly, the direction vector d2 can be obtained through observation image C2, the direction vector d3 can be obtained through observation image C3, and the direction vector d4 can be obtained through observation image C4.

[0095] Furthermore, since the density information of 3D points is related to the confidence level of the observed colors of the 3D points in each observation image, after obtaining the density information, it can be analyzed and processed to determine the confidence level of the observed colors of the 3D points in each observation image. In some instances, a mapping relationship between density information and the confidence level of observed colors is pre-configured. After obtaining the density information of 3D points, the confidence level of each observed color can be determined based on the above mapping relationship and the density information. For example, refer to the appendix... Figure 3 As shown, for the observed image I1, the confidence level T1 of the observed color can be obtained. Similarly, the direction vector T2 can be obtained from the observed image I2, the direction vector T3 can be obtained from the observed image I3, and the direction vector T4 can be obtained from the observed image I4.

[0096] After obtaining the observed color, observation angle, and confidence level, these parameters can be analyzed to determine the color information of the three-dimensional point. In some instances, the color information of the three-dimensional point can be obtained by analyzing the observed color, observation angle, and confidence level using a pre-trained machine learning model or neural network model. In this case, after obtaining the observed color, observation angle, and confidence level, these parameters can be input into the machine learning model or neural network model to obtain the color information of the three-dimensional point output by the model. This effectively achieves a stable determination of the color information of the three-dimensional point in the radiation field.

[0097] In other instances, after obtaining the color information of the three-dimensional points, the density information and color information of the three-dimensional points in the radiation field can be associated and stored. This facilitates viewing or calling operations based on the stored density and color information of the three-dimensional points, further improving the practicality of the method.

[0098] The method for determining color information in a radiation field provided in this embodiment can be used in the rendering field. By analyzing and processing the density information of three-dimensional points in the radiation field and multiple observation images, the color information of the three-dimensional points can be determined. Compared with the existing technology that determines density and color information through iteration, this method not only reduces the amount of information that needs to be iteratively learned—specifically, it only needs to iteratively solve for density information, avoiding iterative solving for color information—but also effectively decouples density and color information in the radiation field. Furthermore, it effectively reduces the data processing resources required to determine density and color information, making the representation and learning of the radiation field easier. This demonstrates the practicality of the method and is conducive to its market promotion and application.

[0099] Figure 4 This is a flowchart illustrating the process of determining the confidence level of each observed color based on density information, provided in an embodiment of the present invention. Based on the above embodiments, refer to the appendix... Figure 4 As shown, this embodiment provides a method for determining the confidence level of each observed color based on density information. Specifically, determining the confidence level of each observed color based on density information in this embodiment may include:

[0100] Step S401: Obtain the camera origin corresponding to each observed image.

[0101] After acquiring each observation image, they can be analyzed and processed to determine the camera origin corresponding to each image. Specifically, the image coordinate system corresponding to each observation image can be determined first, then the center of the lens's principal optical axis in the image coordinate system can be determined, and the center of the lens's principal optical axis can be used as the camera origin, thus effectively ensuring the accuracy and reliability of determining the camera origin.

[0102] Step S402: Based on density information, determine the transparency between the 3D points and the origin of each camera.

[0103] Since there is a correlation between the confidence level of each observed color and the density information of the 3D point, different density information of the 3D point can correspond to different confidence levels of the observed color. Therefore, in order to accurately determine the confidence level of each observed color, after obtaining the density information, the density information can be analyzed and processed to determine the transparency between the 3D point and each camera origin.

[0104] In some instances, obtaining the transparency between a 3D point and each camera origin based on density information may include: determining multiple sampling points between the 3D point and each camera origin; determining the sampling density corresponding to each of the multiple sampling points based on density information; determining the sampling point spacing between two adjacent sampling points; and determining the transparency between the 3D point and each camera origin based on the sampling density corresponding to each of the multiple sampling points and the sampling point spacing.

[0105] For 3D points and camera origins, there may be other obstructions or objects between them. Therefore, to accurately identify the transparency between 3D points and each camera origin, uniform or non-uniform sampling operations can be performed between the 3D points and each camera origin to determine multiple sampling points. After obtaining multiple sampling points, the sampling density of each sampling point can be determined based on the density information of the 3D points. Specifically, interpolation methods can be used to analyze and process the density information of the 3D points to determine the sampling density of each sampling point. After obtaining multiple sampling points, the sampling point spacing between two adjacent sampling points can be obtained. After obtaining the sampling density and sampling point spacing of each sampling point, further analysis and processing can be performed to obtain the transparency between the 3D points and each camera origin.

[0106] Specifically, determining the transparency between a 3D point and the origin of each camera, based on the sampling density and sampling point spacing of each sampling point, can include: obtaining the product of the sampling density and sampling point spacing of each sampling point; summing all the product values ​​to obtain the sum of the product values; and determining the transparency between the 3D point and the origin of each camera based on the sum of the product values. The transparency obtained above is negatively correlated with the sum of the product values, that is, the larger the sum of the product values, the lower the transparency obtained; the smaller the sum of the product values, the higher the transparency obtained.

[0107] It should be noted that the execution order of the above steps "determining the sampling density corresponding to each of the multiple sampling points based on density information" and "determining the sampling point spacing between two adjacent sampling points" is not limited to the order described above. Those skilled in the art can arbitrarily adjust the execution order of the above steps according to the specific application scenario or application requirements. For example, the step "determining the sampling density corresponding to each of the multiple sampling points based on density information" can be performed simultaneously with the step "determining the sampling point spacing between two adjacent sampling points", or the step "determining the sampling density corresponding to each of the multiple sampling points based on density information" can be performed after the step "determining the sampling point spacing between two adjacent sampling points".

[0108] Step S403: Determine the confidence level of each observed color based on transparency.

[0109] A higher transparency between a 3D point and the camera origin indicates fewer objects between them, leading to more reliable observed colors. Therefore, transparency can be used as a confidence level for observed colors. Specifically, after obtaining the transparency, it can be analyzed to determine the confidence level of each observed color. In some cases, transparency can be directly used as the confidence level for each observed color, effectively ensuring the accuracy and reliability of determining the confidence level of each observed color.

[0110] For example, taking a three-dimensional point p in the radiation field as an example, N sampling points are selected between the three-dimensional point p and the camera origin, and the sampling density corresponding to each sampling point is σ. i The sampling distance between two adjacent sampling points is δ. i Then the sampling density σ of each sampling point can be obtained. i Spacing δ between sampling points i The product of the products is then calculated; finally, all the product values ​​are summed to obtain the total product. After obtaining the sum of the above products, the transparency T of the 3D point p to the camera origin corresponding to each observed image can be determined. k , specifically Then, based on the transparency T obtained above, k This allows for the determination of the confidence level for each observed color, thereby effectively ensuring the stability and reliability of the determination of the confidence level for each observed color.

[0111] In this embodiment, by obtaining the camera origin corresponding to each observed image, and then determining the transparency between the three-dimensional point and each camera origin based on the density information, and determining the confidence level of each observed color based on the transparency, the accuracy and reliability of determining the confidence level of each observed color are effectively guaranteed, and the accuracy of determining the color information of the three-dimensional point based on the confidence level of each observed color is further improved.

[0112] Figure 5 This is a flowchart illustrating the process of determining the color information of a three-dimensional point based on observed color, observation angle, and confidence level, as provided in an embodiment of the present invention. Based on the above embodiment, refer to the appendix... Figure 5 As shown, this embodiment provides a technical solution for determining the color information of a three-dimensional point. Specifically, in this embodiment, determining the color information of a three-dimensional point based on observed color, observation angle, and confidence level may include:

[0113] Step S501: Determine the function coefficients of the preset basis functions based on the observed color, observation angle, and confidence level.

[0114] In computer graphics, the color information of a point in space in various directions can be expressed using predefined basis functions and their coefficients. These predefined basis functions can be implemented as orthogonal basis functions such as spherical harmonic basis functions, cosine basis functions, and sine basis functions. To accurately determine the color information of a 3D point, after obtaining the observed color, observation angle, and confidence level, these parameters can be analyzed to determine the coefficients of the predefined basis functions.

[0115] In some instances, the function coefficients of the preset basis functions can be obtained by analyzing the observed color, observation angle, and confidence level using a pre-trained machine learning model. In this case, determining the function coefficients of the preset basis functions based on the observed color, observation angle, and confidence level can include: acquiring the machine learning model, inputting the observed color, observation angle, and confidence level into the machine learning model, thereby obtaining the function coefficients of the preset basis functions output by the machine learning model.

[0116] In some other instances, the observed color, observation angle, and confidence level can be obtained not only through machine learning models but also through pre-defined algorithms. This allows for the analysis and processing of these factors to obtain the coefficients of a pre-defined basis function. In this case, determining the coefficients of the pre-defined basis function based on the observed color, observation angle, and confidence level can include: determining the function value corresponding to the observation angle based on the pre-defined basis function; and determining the function coefficients based on the observed color, confidence level, and function value.

[0117] Specifically, after obtaining the observation angle and the preset basis function, the observation angle can be substituted into the preset basis function to obtain the function value corresponding to the observation angle. For example, the preset basis function is expressed as follows: At the observation angle d k Then the function value corresponding to the observation angle can be determined.

[0118] In some instances, after obtaining the function value, the function coefficients can be determined by combining the observed color and confidence level. In this case, determining the function coefficients based on the observed color, confidence level, and function value may include: obtaining the sum of the products of the observed color, confidence level, and function value for each sampling point; accumulating the confidence levels of all sampling points to obtain the sum of confidence levels; and determining the function coefficients based on the sum of the products and the sum of confidence levels.

[0119] For example, with a confidence level of T k The function value is The observed color is For example, one can obtain the sum of the products of the observed color, confidence level, and function value for each sampling point, i.e. Furthermore, since there are multiple sampling points between the 3D point and the camera origin, the confidence scores of all obtained sampling points are summed to obtain the sum of confidence scores, which is the confidence score. After obtaining the sum of the product values ​​and the sum of the confidence scores, these can be analyzed to accurately determine the function coefficients. Specifically, the function coefficients can be expressed as: As shown above, the function coefficients are positively correlated with the sum of the product values, while the function coefficients are negatively correlated with the confidence level and the sum of the confidence levels.

[0120] In some other instances, when using the above implementation method to determine function coefficients, to ensure the accuracy of the function coefficients, it is often necessary to have a sufficiently large and uniform number of sampling points between the 3D point and the camera origin. This ensures that the function coefficients corresponding to the various basis functions used to represent the color information of the 3D point do not affect each other. Considering that the above requirements are often not met when sampling data points based on observed images, in order to reduce or even avoid the mutual influence between the coefficients of various basis functions, the historical frequency components of the sampling points whose color information has been estimated can be considered. Then, the function coefficients can be determined by combining the historical frequency components. In this case, determining the function coefficients based on the sum of product values ​​and the sum of confidence scores can include: determining the historical frequency components used to identify the sampling points whose color information has been estimated based on the observed color, confidence scores, and function values; and determining the function coefficients based on the sum of product values, the sum of confidence scores, and the historical frequency components.

[0121] After obtaining the observed color, confidence level, and function value, these can be analyzed to determine the historical frequency components used to identify the sampling points for which the color information has been estimated. In some instances, the historical frequency components can be obtained by analyzing the observed color, confidence level, and function value using a pre-selected trained machine learning model or neural network model.

[0122] In other instances, historical frequency components can be obtained not only through pre-trained machine learning or neural network models, but also by directly analyzing and processing observed color, confidence level, and function values. This allows for the determination of historical frequency components used to identify sampling points with estimated color information. In this case, determining the historical frequency components used to identify sampling points with estimated color information based on observed color, confidence level, and function values ​​can include: obtaining historical function coefficients corresponding to each historical sampling point, which are used to identify the color information of the historical sampling points; determining the historical function value of each historical sampling point at the observation angle based on preset basis functions; multiplying and summing the historical function coefficients and historical function values ​​of each historical sampling point to obtain a product sum; and determining the historical frequency components based on the product sum.

[0123] It is important to note that after obtaining the historical frequency components, the sum of the product values ​​can be determined by combining the historical frequency components. Specifically, obtaining the sum of the product values ​​between the observed color, confidence level, and function value of each sampling point can include: obtaining the observed difference between the observed color and the historical frequency components of each sampling point; and performing multiplication and summation on the observed difference, confidence level, and function value of each sampling point to obtain the sum of the product values.

[0124] For example, the observed color can be Historical frequency components can be in, These can be the historical function coefficients corresponding to each historical sampling point. It can be related to the observation angle d k The corresponding function values ​​can then be used to obtain the observation difference between the observed color and the historical frequency components at each sampling point. Specifically, the observation difference can be... Then, based on the observation difference, confidence level, and function value, a multiplication and summation process can be performed to obtain the sum of the product values. Specifically, the sum of the product values ​​can be expressed as... Then, the function coefficients of the preset basis functions can be determined based on the sum of the product values, thus effectively ensuring the accuracy and reliability of determining the function coefficients.

[0125] Step S502: Determine the color information of the three-dimensional points based on the function coefficients and preset basis functions.

[0126] After obtaining the function coefficients and preset basis functions, these can be analyzed to determine the color information of the 3D point. In some examples, spherical harmonic basis functions are used as the preset basis functions. Since the color information of a 3D point includes three color channels (red, green, and blue), to express the color information of each color channel, spherical harmonic basis functions of 0-2 degrees can be used. That is, the spherical harmonic basis functions for each point can be divided into three groups. The function coefficients corresponding to these three groups of spherical harmonic basis functions can be three groups, each containing nine coefficients. In other words, the color information of a 3D point in each color channel can be expressed using spherical harmonic basis functions and nine function coefficients.

[0127] In some other instances, after determining the color information of the three-dimensional points, the method in this embodiment may further include: performing a three-dimensional modeling operation based on the color information of the three-dimensional points to obtain a three-dimensional model corresponding to the radiation field; and / or performing an image rendering operation based on the color information of the three-dimensional points to obtain a rendered image, further improving the practicality of the method.

[0128] In other instances, after obtaining the color information of 3D points, the preset basis functions and coefficients used to represent the color information of the 3D points can be stored. Specifically, the preset basis functions and coefficients can be associated with the density information of the 3D points and stored. Then, the color and density information of other 3D points in the radiation field can be determined based on the stored preset basis functions and coefficients. Specifically, after obtaining the 3D point to be processed, the stored preset basis functions and coefficients can be determined based on the 3D point to be processed. Then, a trilinear interpolation method can be used to interpolate through the eight vertices closest to the 3D point to be processed, thereby obtaining the color and density information of the 3D point to be processed.

[0129] In this embodiment, the function coefficients of the preset basis function are determined by observing the color, observation angle, and confidence level. Then, the color information of the three-dimensional point is determined based on the function coefficients and the preset basis function, thereby effectively ensuring the accuracy and reliability of determining the color information of the three-dimensional point and further improving the practicality of the method.

[0130] In practical applications, taking spherical harmonic basis functions as preset basis functions as an example, this application embodiment provides an analytical solution method for estimating color information in a radiation field. This method can directly estimate the color information of three-dimensional points after obtaining the density information of three-dimensional points in the radiation field. For a three-dimensional scene corresponding to a radiation field, a set of K observation images corresponding to the radiation field and their corresponding camera intrinsic and extrinsic parameters are obtained. The observation images are denoted as I. i For i∈[1,K], the camera intrinsic and extrinsic parameters can be denoted as C. iRegarding the number of observed images, K, the specific value of K can be tens, hundreds, or thousands. It's understandable that the more observed images, the more accurate the color information of the determined 3D points, resulting in a better radiation field or 3D object constructed based on this color information. However, this also requires more data processing resources and time. Conversely, the fewer observed images, the less accurate the estimated color information of the 3D points, leading to a worse radiation field or 3D object constructed based on this color information.

[0131] To understand the process of determining the color information of 3D points, in the field of computer graphics, a discrete volume model can be used to represent the radiation field. For a radiation field volume model, the density information and spherical harmonic basis function coefficients of each vertex can be stored. Each radiation field volume model can have multiple vertices (e.g., 8, 10, 12, or 15, etc.), and different radiation field volume models can correspond to different numbers of vertices. Furthermore, the radiation field volume model can store not only the density and color information corresponding to each vertex, but also the density and color information corresponding to random points within the radiation field volume model.

[0132] Since color information can be expressed using three color channels (red, green, and blue), to accurately represent color information, each color channel can be represented using nine spherical harmonic basis functions of degree 0-2 and their corresponding coefficients. Specifically, the nine spherical harmonic basis functions can include: Each of the nine spherical harmonic basis functions can correspond to a set of spherical harmonic basis function coefficients, and each set of spherical harmonic basis function coefficients can include nine coefficients.

[0133] Specifically, for a radiation field, the rendered image can be expressed using rendering equations. More specifically, for a particular image pixel, a volume rendering equation can be used. The rendered image pixels are obtained under these camera parameters, where r represents the ray emanating from the camera origin and passing through the pixel, I(r) represents the color of the pixel corresponding to the ray (i.e., the observed color), N is the number of sampling points on the ray during volume rendering, and σ i The density at point i, δ i It is the distance from sampling point i to i-1 (in particular, δ1 = 0). It is the color at point i along the direction of ray i. δ j It is the distance between j and j-1. It is the color obtained through rendering.

[0134] To estimate the color information *c* at each vertex (or random 3D unit) of a volumetric model given a set of observed images and scene density information, it's important to note that the color information obtained for any one of the three color channels (red, green, and blue) is identical. Therefore, this application example only describes the estimation process for a single color channel. Specifically, the process of determining the color information of a specific point *p* in the radiation field can include the following steps:

[0135] Step 1: Obtain the density information of a three-dimensional point p in the radiation field and multiple observation images.

[0136] Step 2: Determine the camera parameters corresponding to each of the multiple observed images.

[0137] Step 3: Calculate the color information of the projection point of the 3D point p on each observation image.

[0138] Specifically, the camera parameters corresponding to the observed image are obtained, the coordinates of the projection point of the 3D point p on the image are calculated, and then the color of the projection point is calculated through bilinear interpolation to obtain the final result. The observed color on the k-th camera is denoted as .

[0139] Step 4: Calculate the direction vector d from point p to the camera origin of each observed image. k .

[0140] Step 5: Calculate the transparency T from point p to the camera origin of each observed image. k Since greater transparency indicates fewer objects between the point p and the camera origin, the observed values ​​in the image are more reliable. Therefore, transparency can be used as the confidence level of the observation. The specific calculation process involves uniformly selecting N sampling points between point p and the camera origin, and then obtaining the transparency using the following formula. Where, σ i It is the density at point i, δ i It is the distance information between sampling point i and sampling point i-1.

[0141] Step 6: Through the above steps, K observations can be obtained. Each observation includes color, angle, and confidence level. The coefficients of the basis functions of the spherical harmonic function can be estimated using the Monte Carlo sampling integral estimation method. Specifically, for the basis functions... In other words, the estimated value of its coefficient

[0142] It is important to note that the basis function coefficients mentioned above are obtained using the Monte Carlo sampling integral estimation method. This method requires a sufficiently large and uniform number of sampling points to ensure that the estimates of each coefficient do not affect each other. However, since observed images often meet this condition, the mutual influence of the coefficients needs to be considered. Therefore, the coefficient estimation equation can be adjusted as follows: in, Used to identify the historical frequency components of the sampled points that have been estimated. The function coefficients used to identify the preset basis functions corresponding to the estimated historical sampling points.

[0143] Step 7: Store the coefficients of the spherical harmonic basis functions in association with the spherical harmonic basis functions.

[0144] It should be noted that this application embodiment can use not only spherical harmonic basis functions to represent colors, but also other basis functions, such as cosine basis functions, sine odd functions, neural network-based basis functions, or other orthogonal basis functions. Similarly, for radiation fields, not only can discrete volume models be used to represent radiation fields, but other methods can also be used to represent radiation fields.

[0145] Furthermore, the technical solution provided in this application embodiment can not only be applied to three-dimensional scenes, but also to the scene / object radiation field reconstruction of XR applications. For example, the color information of each three-dimensional point can be obtained through the above method, and image rendering operations can be performed based on the color information of the three-dimensional points to generate images or three-dimensional models, etc.

[0146] The analytical solution method for estimating color information in a radiation field provided in this application embodiment effectively realizes that, given the density information of three-dimensional points in the radiation field, the color information of the three-dimensional points can be solved analytically. Specifically, spherical harmonic basis functions and their weight coefficients are used to represent the color information of each point in the scene, thereby transforming the problem of estimating the color information of each point into estimating the weight coefficients of the basis functions. This not only improves the accuracy and reliability of determining the color information, but also effectively reduces the storage space required when storing relevant parameters in the radiation field by expressing the color information through weight coefficients.

[0147] Furthermore, to accurately estimate the weight coefficients, the points whose colors are to be estimated can be projected onto the scene observation image, and the colors of the corresponding points on the observation image can be used as the observed colors of the 3D points in various directions. Additionally, since the observed colors of the 3D points may not be accurate due to spatial occlusion, the transparency between the points whose colors are to be estimated and the camera origin is calculated using the scene's density information. This transparency is used as the observation confidence level of the observed colors. Then, using the given observed colors and observation confidence levels in various directions, the weight coefficients of the basis functions can be estimated by minimizing the error, thus effectively ensuring the accuracy and reliability of determining the weight coefficients. Compared to existing technologies, this method effectively avoids iterative solutions for color information, requiring only iterative solutions for density information. This decouples the density and color information in the radiation field, reducing the amount of information that needs to be iteratively learned and the parameters that need to be optimized through learning. This makes the representation and learning of the radiation field easier, further improving the practicality of the method and facilitating its market promotion and application.

[0148] Figure 6 A schematic diagram illustrating another method for determining color information in a radiation field provided in an application embodiment of the present invention; see attached diagram. Figure 6 As shown, this embodiment provides another method for determining color information in a radiation field. The executing entity of this method can be a device for determining color information in a radiation field. It is understood that this device can be implemented as software, or a combination of software and hardware. Specifically, when the device is implemented as hardware, it can be various electronic devices with the function of determining color information in a base radiation field, including but not limited to tablet computers, personal computers (PCs), servers, etc. When the device is implemented as software, it can be installed in the aforementioned electronic devices. Based on the aforementioned device for determining color information in a radiation field, the method for determining color information in a radiation field in this embodiment can include the following steps:

[0149] Step S601: Obtain the three-dimensional point to be observed in the radiation field and the observation direction corresponding to the three-dimensional point to be observed.

[0150] Step S602: Determine the basis function coefficients and the preset basis function used to identify the color information of preset points in the radiation field.

[0151] Step S603: Based on the basis function coefficients and preset basis functions, perform interpolation processing in the observation direction to determine the color information of the three-dimensional point to be observed.

[0152] The specific implementation principles and effects of each of the above steps are explained in detail below:

[0153] Step S601: Obtain the three-dimensional point to be observed in the radiation field and the observation direction corresponding to the three-dimensional point to be observed.

[0154] The radiation field can store multiple spatial points. When a user needs to determine the color of any spatial point in the radiation field, they can input the three-dimensional point to be observed into the determining device. Specifically, the three-dimensional point to be observed can be expressed by coordinate values. For example, the three-dimensional point to be observed can be (x, y, z). Similarly, the observation direction corresponding to the three-dimensional point to be observed can be expressed by vectors or images.

[0155] In some instances, the three-dimensional point to be observed and the observation direction can be obtained through a virtual body model corresponding to the radiation field. In this case, obtaining the three-dimensional point to be observed in the radiation field and the observation direction corresponding to the three-dimensional point to be observed can include: displaying the virtual body model corresponding to the radiation field through a determining device, obtaining the user's coordinate point determination operation and observation direction determination operation input in the virtual body model, thereby obtaining the three-dimensional point to be observed in the radiation field and the observation direction corresponding to the three-dimensional point to be observed.

[0156] In other instances, the three-dimensional point to be observed and the observation direction can be obtained through an interactive interface. In this case, obtaining the three-dimensional point to be observed in the radiation field and the observation direction corresponding to the three-dimensional point to be observed can include: obtaining the data configuration page corresponding to the radiation field through the determining device, obtaining the data configuration operation entered by the user in the data configuration page, and then determining the three-dimensional point to be observed in the radiation field and the observation direction corresponding to the three-dimensional point to be observed based on the data configuration operation.

[0157] In some other instances, the three-dimensional point to be observed and the observation direction can be obtained through a third device. Obtaining the three-dimensional point to be observed in the radiation field and the observation direction corresponding to the three-dimensional point to be observed can include: the three-dimensional point to be observed and the observation direction can be stored in the third device, the third device is communicatively connected to the determining device, and the determining device can actively or passively obtain the three-dimensional point to be observed and the observation direction through the third device.

[0158] Step S602: Determine the basis function coefficients and the preset basis functions used to identify the color information of preset points in the radiation field.

[0159] In order to accurately obtain the color information of the three-dimensional point to be observed, the basis function coefficients and the preset basis functions used to identify the color information of the preset points in the radiation field can be determined first. The preset points in the radiation field can be vertices or non-vertices, and the preset basis functions can be spherical harmonic basis functions, sine basis functions, cosine basis functions, and other orthogonal basis functions, etc.

[0160] Furthermore, the basis function coefficients and preset basis functions used to identify color information at preset points in the radiation field can be obtained through pre-processing. These coefficients and functions can be stored in a preset region, and can be accessed by accessing that region. Alternatively, the basis function coefficients and preset basis functions can be determined by analyzing the density information of the preset points in the radiation field and multiple observation images. In this case, the basis function coefficients and preset basis functions can be obtained by analyzing and processing the density information and multiple observation images using the methods described in the above embodiments. For details, please refer to the above description; further elaboration is omitted here.

[0161] Step S603: Based on the basis function coefficients and preset basis functions, perform interpolation processing in the observation direction to determine the color information of the three-dimensional point to be observed.

[0162] After obtaining the 3D point to be observed and the preset point, since the preset point corresponds to the basis function coefficients and the preset basis function, in order to accurately obtain the 3D point to be observed, interpolation processing can be performed in the observation direction based on the basis function coefficients and the preset basis function. Specifically, trilinear interpolation processing can be performed in the observation direction based on the basis function coefficients and the preset basis function, thereby determining the color information of the 3D point to be observed. This effectively ensures the accuracy and reliability of determining the color information of the 3D point to be observed.

[0163] Furthermore, the method in this embodiment may also include the above-described Figures 1-5 For the methods shown in the embodiments, the parts not described in detail in this embodiment can be referred to the following: Figures 1-5 The relevant descriptions of the illustrated embodiments are provided below. For the execution process and technical effects of this technical solution, please refer to [link / reference]. Figures 1-5 The descriptions in the illustrated embodiments will not be repeated here.

[0164] In this embodiment, by acquiring the three-dimensional point to be observed in the radiation field and the observation direction corresponding to the three-dimensional point to be observed, the basis function coefficients and the preset basis function used to identify the color information of the preset point in the radiation field are determined. Then, based on the basis function coefficients and the preset basis function, interpolation processing is performed on the observation direction to determine the color information of the three-dimensional point to be observed. This effectively enables users to determine the color information corresponding to any three-dimensional point in the radiation field based on the observation direction and the color information of the preset point. This effectively improves the accuracy and reliability of color information determination, further enhances the practicality of the method, and is conducive to market promotion and application.

[0165] Figure 7 This is a schematic diagram of a device for determining color information in a radiation field according to an embodiment of the present invention; see attached diagram. Figure 7 As shown, this embodiment provides a device for determining color information in a radiation field, which is used to perform the above-described... Figure 2 The method for determining color information in the radiation field shown may specifically include:

[0166] The first acquisition module 11 is used to acquire the density information of three-dimensional points in the radiation field and multiple observation images of the radiation field in at least two observation directions;

[0167] The first processing module 12 is used to determine the color information of three-dimensional points based on multiple observation images and density information.

[0168] In some instances, when the first processing module 12 determines the color information of a three-dimensional point based on multiple observation images and density information, the first processing module 12 is used to perform the following: acquiring the observed color of the three-dimensional point on each observation image and the observation angle of the three-dimensional point relative to each observation image; determining the confidence level of each observed color based on the density information; and determining the color information of the three-dimensional point based on the observed color, observation angle, and confidence level.

[0169] In some instances, when the first processing module 12 determines the confidence level of each observed color based on density information, the first processing module 12 is used to perform the following: obtain the camera origin corresponding to each observed image; determine the transparency between the three-dimensional point and each camera origin based on density information; and determine the confidence level of each observed color based on transparency.

[0170] In some instances, when the first processing module 12 obtains the transparency between the 3D point and each camera origin based on density information, the first processing module 12 is used to perform the following: determine multiple sampling points between the 3D point and each camera origin; determine the sampling density corresponding to each of the multiple sampling points based on density information; determine the sampling point spacing between two adjacent sampling points; and determine the transparency between the 3D point and each camera origin based on the sampling density corresponding to each of the multiple sampling points and the sampling point spacing.

[0171] In some instances, when the first processing module 12 determines the transparency between a 3D point and each camera origin based on the sampling density and sampling point spacing of each of the multiple sampling points, the first processing module 12 performs the following: obtaining the product value between the sampling density and sampling point spacing of each sampling point; accumulating all the product values ​​to obtain the sum of the product values; and determining the transparency between the 3D point and each camera origin based on the sum of the product values.

[0172] In some instances, transparency is negatively correlated with the sum of the product values.

[0173] In some instances, when the first processing module 12 determines the color information of a 3D point based on the observed color, observation angle, and confidence level, the first processing module 12 is used to perform: determining the function coefficients of a preset basis function based on the observed color, observation angle, and confidence level; and determining the color information of the 3D point based on the function coefficients and the preset basis function.

[0174] In some instances, when the first processing module 12 determines the function coefficients of a preset basis function based on the observed color, observed angle, and confidence level, the first processing module 12 is used to perform: determining the function value corresponding to the observed angle based on the preset basis function; and determining the function coefficients based on the observed color, confidence level, and function value.

[0175] In some instances, when the first processing module 12 determines the function coefficients based on the observed color, confidence level, and function value, the first processing module 12 performs the following actions: obtaining the sum of the products of the observed color, confidence level, and function value for each sampling point; accumulating the confidence levels of all sampling points to obtain a sum of confidence levels; and determining the function coefficients based on the sum of the products and the sum of confidence levels.

[0176] In some instances, the function coefficients are positively correlated with the sum of the product values, while the function coefficients are negatively correlated with the confidence level and the sum of the confidence levels.

[0177] In some instances, when the first processing module 12 determines the function coefficients based on the sum of product values ​​and the sum of confidence levels, the first processing module 12 is used to perform: determining the historical frequency components used to identify the sampling points for which color information has been estimated based on the observed color, confidence level, and function value; and determining the function coefficients based on the sum of product values, the sum of confidence levels, and the historical frequency components.

[0178] In some instances, when the first processing module 12 obtains the sum of the product values ​​between the observed color, confidence level, and function value of each sampling point, the first processing module 12 is used to perform the following: obtain the observed difference between the observed color and the historical frequency component of each sampling point; perform multiplication and summation processing on the observed difference, confidence level, and function value of each sampling point to obtain the sum of the product values.

[0179] In some instances, when the first processing module 12 determines the historical frequency components used to identify the sampling points whose color information has been estimated, based on the observed color, confidence level, and function value, the first processing module 12 performs the following: obtaining the historical function coefficients corresponding to each historical sampling point, the historical function coefficients being used to identify the color information of the historical sampling points; determining the historical function value of each historical sampling point at the observation angle based on a preset basis function; performing multiplication and summation on the historical function coefficients and historical function values ​​of each historical sampling point to obtain a product sum; and determining the historical frequency components based on the product sum.

[0180] In some instances, after determining the color information of the three-dimensional points, the first processing module 12 in this embodiment is further used to perform a three-dimensional modeling operation based on the color information of the three-dimensional points to obtain a three-dimensional model corresponding to the radiation field; and / or, to perform an image rendering operation based on the color information of the three-dimensional points to obtain a rendered image.

[0181] Figure 7 The device shown can perform Figures 1-5 For the methods shown in the embodiments, the parts not described in detail in this embodiment can be referred to the following: Figures 1-5 The relevant descriptions of the illustrated embodiments are provided below. For the execution process and technical effects of this technical solution, please refer to [link / reference]. Figures 1-5 The descriptions in the illustrated embodiments will not be repeated here.

[0182] In one possible design, Figure 7 The structure of the device for determining color information in the radiation field shown can be implemented as an electronic device, which can be a controller, personal computer, server, or other similar devices. Figure 8 As shown, the electronic device may include a first processor 21 and a first memory 22. The first memory 22 is used to store data executed by the corresponding electronic device. Figures 1-5 In the illustrated embodiment, the program for determining color information in a radiation field is provided, wherein the first processor 21 is configured to execute the program stored in the first memory 22.

[0183] The program includes one or more computer instructions, wherein when the one or more computer instructions are executed by the first processor 21, they can perform the following steps: acquire density information of three-dimensional points in the radiation field and multiple observation images of the radiation field in at least two observation directions; and determine the color information of the three-dimensional points based on the multiple observation images and density information.

[0184] Furthermore, the first processor 21 is also used to perform the aforementioned Figures 1-5 All or part of the steps in the illustrated embodiments.

[0185] The structure of the electronic device may also include a first communication interface 23 for communication between the electronic device and other devices or communication networks.

[0186] In addition, embodiments of the present invention provide a computer storage medium for storing computer software instructions used by an electronic device, which includes instructions for executing the above-described... Figures 1-5 The procedure involved in the method for determining color information in the radiation field in the illustrated embodiment.

[0187] Furthermore, embodiments of the present invention provide a computer program product, comprising: a computer-readable storage medium storing computer instructions, which, when executed by one or more processors, cause one or more processors to perform the aforementioned... Figures 1-5 The steps in the method for determining color information in the radiation field in the illustrated embodiment.

[0188] Figure 9 This is a schematic diagram of a device for determining color information in a radiation field according to an embodiment of the present invention; see attached diagram. Figure 9 As shown, this embodiment provides a device for determining color information in a radiation field, which is used to perform the above-described... Figure 6 The method for determining color information in the radiation field shown may specifically include:

[0189] The second acquisition module 31 is used to acquire the three-dimensional point to be observed in the radiation field and the observation direction corresponding to the three-dimensional point to be observed.

[0190] The second determining module 32 is used to determine the basis function coefficients and the preset basis function used to identify the color information of preset points in the radiation field;

[0191] The second processing module 33 is used to perform interpolation processing in the observation direction based on the basis function coefficients and preset basis functions to determine the color information of the three-dimensional point to be observed.

[0192] Figure 9 The device shown can perform Figure 6 The method of the illustrated embodiment, for parts not described in detail in this embodiment, can be referred to the description of the line. Figure 6 The relevant descriptions of the illustrated embodiments are provided below. For the execution process and technical effects of this technical solution, please refer to the following: Figure 6 The descriptions in the illustrated embodiments will not be repeated here.

[0193] In one possible design, Figure 9 The structure of the device for determining color information in the radiation field shown can be implemented as an electronic device, which can be various devices such as mobile phones, tablets, and servers. Figure 10 As shown, the electronic device may include a second processor 41 and a second memory 42. The second memory 42 is used to store data executed by the corresponding electronic device. Figure 6 In the illustrated embodiment, the program for determining color information in a radiation field is provided, and the second processor 41 is configured to execute the program stored in the second memory 42.

[0194] The program includes one or more computer instructions, wherein when the one or more computer instructions are executed by the second processor 41, they can perform the following steps: acquiring the three-dimensional point to be observed in the radiation field and the observation direction corresponding to the three-dimensional point to be observed; determining the basis function coefficients and the preset basis function used to identify the color information of the preset point in the radiation field; and performing interpolation processing on the observation direction based on the basis function coefficients and the preset basis function to determine the color information of the three-dimensional point to be observed.

[0195] Furthermore, the second processor 41 is also used to perform the aforementioned... Figure 6 All or part of the steps in the illustrated embodiments.

[0196] The structure of the electronic device may also include a second communication interface 43 for communication between the electronic device and other devices or communication networks.

[0197] In addition, embodiments of the present invention provide a computer storage medium for storing computer software instructions used by an electronic device, which includes instructions for executing the above-described... Figure 6 The procedure involved in the method for determining color information in the radiation field in the illustrated embodiment.

[0198] Furthermore, embodiments of the present invention provide a computer program product, comprising: a computer-readable storage medium storing computer instructions, which, when executed by one or more processors, cause one or more processors to perform the aforementioned... Figure 6 The steps in the method for determining color information in the radiation field in the illustrated embodiment.

[0199] Figure 11 A flowchart illustrating another method for determining color information in a radiation field provided by an embodiment of the present invention; see attached diagram. Figure 11 As shown, this embodiment provides a method for determining color information in a radiation field. It can be understood that the execution of this method can be a device for determining color information in a radiation field, which can be implemented as software or a combination of software and hardware. Specifically, the method for determining color information in a radiation field may include:

[0200] Step S1101: In response to the request to invoke the color confirmation service, determine the processing resources corresponding to the color confirmation service;

[0201] Step S1102: Utilize the processing resources to perform the following steps: acquire density information of three-dimensional points in the radiation field and multiple observation images of the radiation field in at least two observation directions; determine the color information of the three-dimensional points based on the multiple observation images and the density information.

[0202] Specifically, the method for determining color information in a radiation field provided by this invention can be executed in the cloud, where several computing nodes can be deployed, each with processing resources such as computing and storage. In the cloud, multiple computing nodes can be organized to provide a certain service; of course, a single computing node can also provide one or more services.

[0203] According to the solution provided by this invention, the cloud can provide a service for determining color information in a radiation field, referred to as the "color information determination service in a radiation field". When a user needs to use this service, they invoke it to trigger a request to the cloud to invoke the service. This request may include the three-dimensional points to be predicted. The cloud determines a computing node to respond to the request and uses the processing resources in that node to perform the following steps: acquiring density information of the three-dimensional points in the radiation field and multiple observation images of the radiation field in at least two observation directions; and determining the color information of the three-dimensional points based on the multiple observation images and the density information.

[0204] Specifically, the implementation process, implementation principle, and implementation effect of the above method steps in this embodiment are the same as those described above. Figures 1-5 The implementation process, principle, and effect of the method steps in the illustrated embodiment are similar. For parts not described in detail in this embodiment, please refer to the [examples provided]. Figures 1-5 The following is a description of the illustrated embodiment.

[0205] Figure 12 This is a schematic diagram of a device for determining color information in a radiation field according to an embodiment of the present invention; see attached diagram. Figure 12 As shown, this embodiment provides a device for determining color information in a radiation field, which is used to perform the above-described... Figure 11 The method for determining color information in the radiation field shown may specifically include:

[0206] The third determining module 51 is used to determine the processing resources corresponding to the color confirmation service in response to a request to call the color confirmation service;

[0207] The third processing module 52 is used to perform the following steps using the processing resources: acquiring density information of three-dimensional points in the radiation field and multiple observation images of the radiation field in at least two observation directions; and determining the color information of the three-dimensional points based on the multiple observation images and the density information.

[0208] Figure 12 The device shown can perform Figure 11 The method of the illustrated embodiment, for parts not described in detail in this embodiment, can be referred to the description of the line. Figure 11 The relevant descriptions of the illustrated embodiments are provided below. For the execution process and technical effects of this technical solution, please refer to the following: Figure 11 The descriptions in the illustrated embodiments will not be repeated here.

[0209] In one possible design, Figure 12The structure of the device for determining color information in the radiation field shown can be implemented as an electronic device, which can be various devices such as mobile phones, tablets, and servers. Figure 13 As shown, the electronic device may include a third processor 61 and a third memory 62. The third memory 62 is used to store data executed by the corresponding electronic device. Figure 11 In the illustrated embodiment, the program for determining color information in a radiation field is provided, and the third processor 61 is configured to execute the program stored in the third memory 62.

[0210] The program includes one or more computer instructions, wherein when executed by a third processor 61, the one or more computer instructions are capable of performing the following steps: in response to a request to invoke a color confirmation service, determining the processing resources corresponding to the color confirmation service; using the processing resources to perform the following steps: acquiring density information of three-dimensional points in a radiation field and multiple observation images of the radiation field in at least two observation directions; and determining the color information of the three-dimensional points based on the multiple observation images and the density information.

[0211] Furthermore, the third processor 61 is also used to perform the aforementioned... Figure 11 All or part of the steps in the illustrated embodiments.

[0212] The structure of the electronic device may also include a third communication interface 63 for communication between the electronic device and other devices or communication networks.

[0213] In addition, embodiments of the present invention provide a computer storage medium for storing computer software instructions used by an electronic device, which includes instructions for executing the above-described... Figure 11 The procedure involved in the method for determining color information in the radiation field in the illustrated embodiment.

[0214] Furthermore, embodiments of the present invention provide a computer program product, comprising: a computer-readable storage medium storing computer instructions, which, when executed by one or more processors, cause one or more processors to perform the aforementioned... Figure 11 The steps in the method for determining color information in the radiation field in the illustrated embodiment.

[0215] Figure 14 A flowchart illustrating another method for determining color information in a radiation field provided by an embodiment of the present invention; see attached diagram. Figure 14 As shown, this embodiment provides another method for determining color information in a radiation field. It is understood that the execution of this method can be a device for determining color information in a radiation field, which can be implemented as software or a combination of software and hardware. Specifically, the method for determining color information in a radiation field may include:

[0216] Step S1401: In response to the request to invoke the color confirmation service, determine the processing resources corresponding to the color confirmation service;

[0217] Step S1402: Using the processing resources, perform the following steps: acquire the three-dimensional point to be observed in the radiation field and the observation direction corresponding to the three-dimensional point to be observed; determine the basis function coefficients and the preset basis function used to identify the color information of the preset point in the radiation field; perform interpolation processing on the observation direction based on the basis function coefficients and the preset basis function to determine the color information of the three-dimensional point to be observed.

[0218] Specifically, the method for determining color information in a radiation field provided by this invention can be executed in the cloud, where several computing nodes can be deployed, each with processing resources such as computing and storage. In the cloud, multiple computing nodes can be organized to provide a certain service; of course, a single computing node can also provide one or more services.

[0219] According to the solution provided by this invention, the cloud can provide a service for determining color information in a radiation field, referred to as the "color information determination service in a radiation field". When a user needs to use this service, they invoke it to trigger a request to the cloud to invoke the service. This request may include the three-dimensional points to be predicted. The cloud determines a computing node to respond to the request and uses the processing resources in that node to perform the following steps: acquiring density information of the three-dimensional points in the radiation field and multiple observation images of the radiation field in at least two observation directions; and determining the color information of the three-dimensional points based on the multiple observation images and the density information.

[0220] Specifically, the implementation process, implementation principle, and implementation effect of the above method steps in this embodiment are the same as those described above. Figures 1-5 The implementation process, principle, and effect of the method steps in the illustrated embodiment are similar. For parts not described in detail in this embodiment, please refer to the [examples provided]. Figures 1-5 The following is a description of the illustrated embodiment.

[0221] Figure 15 This is a schematic diagram of a device for determining color information in a radiation field according to an embodiment of the present invention; see attached diagram. Figure 15 As shown, this embodiment provides a device for determining color information in a radiation field, which is used to perform the above-described... Figure 13 The method for determining color information in the radiation field shown may specifically include:

[0222] The fourth determining module 71 is used to determine the processing resources corresponding to the color confirmation service in response to a request to call the color confirmation service;

[0223] The fourth processing module 72 is used to perform the following steps using the processing resources: acquiring the three-dimensional point to be observed in the radiation field and the observation direction corresponding to the three-dimensional point to be observed; determining the basis function coefficients and the preset basis function used to identify the color information of the preset point in the radiation field; and performing interpolation processing on the observation direction based on the basis function coefficients and the preset basis function to determine the color information of the three-dimensional point to be observed.

[0224] Figure 15 The device shown can perform Figure 14 The method of the illustrated embodiment, for parts not described in detail in this embodiment, can be referred to the description of the line. Figure 14 The relevant descriptions of the illustrated embodiments are provided below. For the execution process and technical effects of this technical solution, please refer to the following: Figure 14 The descriptions in the illustrated embodiments will not be repeated here.

[0225] In one possible design, Figure 15 The structure of the device for determining color information in the radiation field shown can be implemented as an electronic device, which can be various devices such as mobile phones, tablets, and servers. Figure 16 As shown, the electronic device may include a fourth processor 81 and a fourth memory 82. The fourth memory 82 is used to store data executed by the corresponding electronic device. Figure 14 In the illustrated embodiment, the program for determining color information in a radiation field is provided, and the fourth processor 81 is configured to execute the program stored in the fourth memory 82.

[0226] The program includes one or more computer instructions, wherein when the one or more computer instructions are executed by the third processor 61, they can perform the following steps: acquiring the three-dimensional point to be observed in the radiation field and the observation direction corresponding to the three-dimensional point to be observed; determining the basis function coefficients and the preset basis function used to identify the color information of the preset point in the radiation field; and performing interpolation processing on the observation direction based on the basis function coefficients and the preset basis function to determine the color information of the three-dimensional point to be observed.

[0227] Furthermore, the fourth processor 81 is also used to perform the aforementioned... Figure 14 All or part of the steps in the illustrated embodiments.

[0228] The structure of the electronic device may also include a fourth communication interface 83 for communication between the electronic device and other devices or communication networks.

[0229] In addition, embodiments of the present invention provide a computer storage medium for storing computer software instructions used by an electronic device, which includes instructions for executing the above-described... Figure 14 The procedure involved in the method for determining color information in the radiation field in the illustrated embodiment.

[0230] Furthermore, embodiments of the present invention provide a computer program product, comprising: a computer-readable storage medium storing computer instructions, which, when executed by one or more processors, cause one or more processors to perform the aforementioned... Figure 14 The steps in the method for determining color information in the radiation field in the illustrated embodiment.

[0231] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0232] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of a necessary general-purpose hardware platform, or by a combination of hardware and software. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a computer product. The present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0233] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0234] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0235] These computer program instructions may also be loaded onto a computer or other programmable device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable device for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0236] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0237] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0238] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0239] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method of determining color information in a radiation field, characterized by, include: Acquire density information of three-dimensional points in the radiation field and multiple observation images of the radiation field in at least two observation directions; Obtain the observed color of the three-dimensional point on each observation image and the observed angle of the three-dimensional point relative to each observation image; Based on the density information, the confidence level of each observed color is determined; The color information of the three-dimensional point is determined based on the observed color, the observed angle, and the confidence level.

2. The method of claim 1, wherein, Based on the density information, the confidence level of each observed color is determined, including: Obtain the camera origin corresponding to each observed image; Based on the density information, the transparency between the three-dimensional point and each camera origin is determined; Based on the transparency, the confidence level of each observed color is determined.

3. The method of claim 2, wherein, Based on the density information, the transparency between the 3D point and each camera origin is obtained, including: Multiple sampling points are determined between the three-dimensional points and the origins of each camera. Based on the density information, the sampling density corresponding to each of the plurality of sampling points is determined; Determine the sampling distance between two adjacent sampling points; Based on the sampling density corresponding to each of the multiple sampling points and the spacing between the sampling points, the transparency between the three-dimensional point and each camera origin is determined.

4. The method of claim 3, wherein, Based on the sampling density corresponding to each of the multiple sampling points and the sampling point spacing, the transparency between the 3D point and each camera origin is determined, including: Obtain the product between the sampling density of each sampling point and the sampling point spacing; Sum all the product values ​​to obtain the sum of the product values; Based on the sum of the product values, the transparency between the 3D point and each camera origin is determined.

5. The method of claim 1, wherein, Based on the observed color, observation angle, and confidence level, the color information of the three-dimensional point is determined, including: Based on the observed color, observation angle, and confidence level, determine the function coefficients of the preset basis function; The color information of the three-dimensional point is determined based on the function coefficients and the preset basis function.

6. The method of claim 5, wherein, Based on the observed color, observation angle, and confidence level, the function coefficients of the preset basis function are determined, including: Based on the preset basis function, determine the function value corresponding to the observation angle; The function coefficients are determined based on the observed color, confidence level, and function value.

7. The method of claim 6, wherein, Determining the function coefficients based on the observed color, confidence level, and function value includes: Obtain the sum of the products of the observed color, confidence level, and function value for each sampling point; The confidence scores of all sampling points are summed to obtain the sum of confidence scores; The function coefficients are determined based on the sum of the product values ​​and the sum of the confidence scores.

8. The method of claim 7, wherein, Determining the function coefficients based on the sum of the product values ​​and the sum of the confidence scores includes: Based on the observed color, confidence level, and function value, determine the historical frequency components used to identify the sampling points whose color information has been estimated; The function coefficients are determined based on the sum of the product values, the sum of the confidence levels, and the historical frequency components.

9. The method of claim 8, wherein, Obtaining the sum of the products of the observed color, confidence level, and function value for each sampling point, including: Obtain the observed difference between the observed color and the historical frequency component at each sampling point; The observation difference, confidence level, and function value at each sampling point are multiplied and summed to obtain the sum of the product values.

10. The method of claim 8, wherein, Based on the observed color, confidence level, and function value, determine the historical frequency components used to identify sampling points with estimated color information, including: Obtain the historical function coefficients corresponding to each historical sampling point, wherein the historical function coefficients are used to identify the color information of the historical sampling points; Based on the preset basis function, the historical function value of each historical sampling point at the observation angle is determined; The historical function coefficients and historical function values ​​at each historical sampling point are multiplied and summed to obtain the product sum. The historical frequency components are determined based on the sum of the products.

11. A method of determining color information in a radiation field, characterized by, include: Obtain the three-dimensional point to be observed in the radiation field and the observation direction corresponding to the three-dimensional point to be observed; Determine the basis function coefficients and the preset basis function used to identify the color information of the preset points in the radiation field; the basis function coefficients are determined based on the observed color, observation angle and confidence level of the three-dimensional point to be observed in each observation direction, and the confidence level is determined based on the density information of the three-dimensional point to be observed; The color information of the three-dimensional point to be observed is determined by interpolation processing of the basis function coefficients and the preset basis function in the observation direction.

12. A method of determining color information in a radiation field, characterized by, include: In response to a request to invoke the color confirmation service, determine the processing resources corresponding to the color confirmation service; The following steps are performed using the processing resources: acquiring density information of three-dimensional points in the radiation field and multiple observation images of the radiation field in at least two observation directions; acquiring the observation color of the three-dimensional points in each observation image and the observation angle of the three-dimensional points relative to each observation image; determining the confidence level of each observation color based on the density information; and determining the color information of the three-dimensional points based on the observation color, observation angle, and confidence level.

13. An electronic device, comprising: include: A memory and a processor; wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions, when executed by the processor, implement the method of any one of claims 1-12.

Images