Data processing method and apparatus

Abstract

A data processing method, which is applied to the field of artificial intelligence. The method comprises: acquiring images collected with regard to a target scene; on the basis of the images, performing learning to obtain a plurality of primitives of the target scene, wherein the different primitives comprise a 3D distribution of areas at different positions in a space, the 3D distribution being used for indicating target information, and the target information being at least one of semantic information, depth information or optical-flow information; and on the basis of the aggregation of some or all of the plurality of primitives, rendering a 3D model, a semantic map, a depth map or an optical-flow map of the target scene. In the embodiments of the present application, except for RGB images, information of other dimensions, such as a 3D model, a semantic map, a depth map or an optical flow map, is rendered by means of primitives, such that during parameter learning, the reconstruction and rendering effects of the RGB images can be significantly improved by means of the assistance of the information of the other dimensions (i.e., updating parameters on the basis of loss constructed on the basis of the information of the other dimensions).

Description

A data processing method and device thereof

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office on February 27, 2024, with application number 202410217743.8 and application name “A data processing method and device thereof”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of artificial intelligence, and in particular to a data processing method and device thereof. Background Art

[0003] Artificial Intelligence (AI) is the theory, methods, techniques, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, to perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results. In other words, AI is a branch of computer science that seeks to understand the essence of intelligence and develop new intelligent machines that can respond in a manner similar to human intelligence. AI also studies the design principles and implementation methods of various intelligent machines, enabling them to possess the capabilities of perception, reasoning, and decision-making.

[0004] 3D Gaussian splatting represents the scene as a Gaussian sphere and produces rendering results by projecting the Gaussian sphere, achieving real-time rendering speeds. Starting with a uniformly sampled random point cloud, this method learns the spherical harmonic coefficients related to each point's position and viewing direction. Using a differentiable splatting-based renderer, the point cloud is projected onto the imaging plane according to a specific Gaussian distribution to produce the rendering result.

[0005] However, the reconstruction and rendering effects of existing 3D Gaussian splattering methods are still poor. Summary of the Invention

[0006] In the first aspect, the present application provides a data processing method, the method comprising: acquiring an image collected for a target scene; based on the image, learning a plurality of primitives of the target scene, different primitives including 3D distributions of regions at different positions in space, the 3D distributions being used to indicate target information, the target information being at least one of semantic information, depth information or optical flow information; based on the aggregation of some or all of the multiple primitives, rendering a 3D model, semantic map, depth map or optical flow map of the target scene. In an embodiment of the present application, in addition to RGB images, information of other dimensions, such as 3D models, semantic maps, depth maps or optical flow maps, is rendered through primitives. During parameter learning, the reconstruction and rendering effects of RGB images can be significantly improved by using the assistance of information of other dimensions (that is, updating parameters based on the loss constructed based on information of other dimensions).

[0007] Among them, the semantic map can be an instance segmentation map, a global segmentation map, a target segmentation map, etc., which is not limited in the embodiments of the present application.

[0008] In a possible implementation, the primitive is a Gaussian sphere.

[0009] In a possible implementation, the plurality of primitives include a plurality of first primitives in a static area and a plurality of second primitives in a dynamic area of ​​the scene. Separating the primitives in the static and dynamic areas can achieve joint optimization of the static background and the dynamic target.

[0010] In one possible implementation, the image specifically includes images of multiple frames of a video, the video includes a moving object, and the multiple second primitives include multiple primitives of each frame; after learning the multiple primitives of the target scene based on the image, the method also includes: using the motion model of the moving object as a constraint to optimize the multiple second primitives.

[0011] In embodiments of the present application, dynamic object reconstruction and rendering can be performed based on kinematic constraints. For example, a dynamic foreground and background can be simultaneously modeled and optimized based on a scene graph, introducing a kinematic model and optimizing 3D frame parameters simultaneously. The position and rotation matrix of the dynamic object at each moment can be calculated using the kinematic model.

[0012] In a possible implementation, the image specifically includes images of multiple frames of a video, the image of each frame corresponds to multiple second primitives, and the multiple second primitives corresponding to different frames are different.

[0013] In a possible implementation, the method further includes: rendering an RGB image of the target scene based on aggregation of some or all of the multiple primitives.

[0014] In one possible implementation, the rendering of the semantic map, depth map or optical flow map of the target scene based on the aggregation of some or all of the multiple primitives includes: aggregating the semantic information of some or all of the multiple primitives to render the semantic map of the target scene; wherein the aggregation includes a softmax operation on the 3D semantics in the semantic information. This is in contrast to most existing methods that apply softmax to the 2D semantic logarithms obtained by accumulating non-normalized 3D semantic logarithms s_(i). Applying softmax in 2D space results in the generation of noisy 3D semantic labels. This is because 2D space softmax can generate accurate 2D semantics by adjusting the scale of the 3D semantic logarithms, thereby allowing a single sampling point with a large number of logit values ​​to significantly affect the overall volume rendering result.

[0015] In a possible implementation, the method further includes: obtaining labels of a 3D model, a semantic map, a depth map, or an optical flow map of the image; and updating the multiple primitives according to the labels.

[0016] In a second aspect, the present application provides a data processing device, comprising:

[0017] An acquisition module is used to acquire images collected for a target scene;

[0018] A processing module is configured to learn, based on the image, a plurality of primitives of the target scene, where different primitives include 3D distributions of regions at different positions in space, and the 3D distributions are used to indicate target information, where the target information is at least one of semantic information, depth information, or optical flow information; and render a 3D model, semantic map, depth map, or optical flow map of the target scene based on aggregation of some or all of the plurality of primitives.

[0019] In a possible implementation, the primitive is a Gaussian sphere.

[0020] In a possible implementation, the plurality of primitives include a plurality of first primitives in a static area and a plurality of second primitives in a dynamic area of ​​the scene.

[0021] In one possible implementation, the image specifically includes images of multiple frames of a video, the video includes a moving object, and the multiple second primitives include multiple primitives in each frame; after learning and obtaining the multiple primitives of the target scene based on the image, the processing module is further configured to:

[0022] The plurality of second primitives are optimized using the motion model of the moving object as a constraint.

[0023] In a possible implementation, the image specifically includes images of multiple frames of a video, the image of each frame corresponds to multiple second primitives, and the multiple second primitives corresponding to different frames are different.

[0024] In a possible implementation, the processing module is further configured to:

[0025] Rendering an RGB image of the target scene according to aggregation of some or all of the plurality of primitives.

[0026] In a possible implementation, the processing module is specifically configured to:

[0027] Aggregating semantic information of some or all of the multiple primitives to render a semantic graph of the target scene; wherein the aggregation includes performing a softmax operation on 3D semantics in the semantic information.

[0028] In a possible implementation, the processing module is further configured to:

[0029] Obtaining a label of a 3D model, semantic map, depth map, or optical flow map of the image;

[0030] The plurality of primitives are updated according to the tags.

[0031] In a third aspect, an embodiment of the present application provides a data processing device, which may include a memory, a processor, and a bus system, wherein the memory is used to store programs, and the processor is used to execute the programs in the memory to perform the first aspect and any optional method thereof.

[0032] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer executes the above-mentioned first aspect and any optional method thereof.

[0033] In a fifth aspect, an embodiment of the present application provides a computer program, which, when executed on a computer, enables the computer to execute the above-mentioned first aspect and any optional method thereof.

[0034] In a sixth aspect, the present application provides a chip system comprising a processor configured to support the execution of a data processing device to implement the functions described in the aforementioned aspects, such as transmitting or processing the data or information described in the aforementioned methods. In one possible design, the chip system further comprises a memory configured to store program instructions and data necessary for executing the device or training the device. The chip system may consist of a single chip or may include a chip and other discrete components. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] FIG1A is a schematic diagram of a structure of an artificial intelligence main framework;

[0036] Figures 1B to 1C are schematic diagrams of the application system framework of the present application;

[0037] FIG1D is a schematic diagram of an optional hardware structure of a terminal;

[0038] FIG2 is a schematic diagram of the structure of a server;

[0039] FIG3 is a schematic diagram of a system architecture of the present application;

[0040] Figure 4 shows a process of cloud services;

[0041] FIG5 is a flowchart of a data processing method provided in an embodiment of the present application;

[0042] 6 to 8 are schematic diagrams of a process of a data processing method provided in an embodiment of the present application;

[0043] FIG9 , FIG10A and FIG10B are schematic diagrams of a beneficial effect of the present application;

[0044] FIG11 is a schematic structural diagram of a data processing device provided in an embodiment of the present application;

[0045] FIG12 is a schematic diagram of a structure of an execution device provided in an embodiment of the present application;

[0046] FIG13 is a schematic diagram of a structure of a training device provided in an embodiment of the present application;

[0047] FIG14 is a schematic structural diagram of a chip provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] The following describes the embodiments of the present application in conjunction with the accompanying drawings. The terms used in the implementation methods of the present application are only used to explain the specific embodiments of the present application and are not intended to limit the present application.

[0049] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0050] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, and this is merely a way of distinguishing the objects of the same attributes when describing them in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0051] As used herein, the terms "substantially," "about," and similar terms are used as terms of approximation, not as terms of degree, and are intended to take into account the inherent deviations in measurements or calculations that one of ordinary skill in the art would recognize. Furthermore, the use of "may" when describing embodiments of the present application refers to "one or more possible embodiments." As used herein, the terms "use," "using," and "used" may be considered synonymous with the terms "utilize," "utilizing," and "utilized," respectively. Additionally, the term "exemplary" is intended to refer to an example or illustration.

[0052] First, let's describe the overall workflow of an AI system. See Figure 1A, which shows a schematic diagram of the main AI framework. This AI framework will be explained from two perspectives: the "intelligent information chain" (horizontal axis) and the "IT value chain" (vertical axis). The "intelligent information chain" reflects the entire process from data acquisition to processing. For example, it could be the general process of intelligent information perception, intelligent information representation and formation, intelligent reasoning, intelligent decision-making, and intelligent execution and output. Throughout this process, data undergoes a condensed journey from "data-information-knowledge-wisdom." The "IT value chain," spanning the underlying infrastructure of human intelligence, information (provided and processed by technology), and the system's industrial ecosystem, reflects the value that AI brings to the information technology industry.

[0053] (1) Infrastructure

[0054] Infrastructure provides computing power for AI systems, enabling communication with the outside world and supporting this through a foundational platform. External communication occurs through sensors; computing power is provided by intelligent chips (CPUs, NPUs, GPUs, ASICs, FPGAs, and other hardware accelerators). The foundational platform includes a distributed computing framework and network-related platform guarantees and support, including cloud storage and computing, and interconnected networks. For example, sensors communicate with the outside world to acquire data, which is then fed into the intelligent chips within the distributed computing system provided by the foundational platform for computation.

[0055] (2) Data

[0056] Data above the infrastructure layer represents data sources for AI. This data includes graphics, images, voice, and text, as well as IoT data from traditional devices. This includes business data from existing systems and sensor data such as force, displacement, liquid level, temperature, and humidity.

[0057] (3) Data processing

[0058] Data processing generally includes data training, machine learning, deep learning, search, reasoning, decision-making, etc.

[0059] Among them, machine learning and deep learning can symbolize and formalize data for intelligent information modeling, extraction, preprocessing, and training.

[0060] Reasoning refers to the process of simulating human intelligent reasoning in computers or intelligent systems, using formalized information to perform machine thinking and solve problems based on reasoning control strategies. Typical functions are search and matching.

[0061] Decision-making refers to the process of making decisions after intelligent information is reasoned, and usually provides functions such as classification, sorting, and prediction.

[0062] (4) General ability

[0063] After the data has undergone the data processing mentioned above, some general capabilities can be further formed based on the results of the data processing, such as algorithms or a general system, for example, translation, text analysis, computer vision processing, speech recognition, image recognition, etc.

[0064] (5) Smart products and industry applications

[0065] Smart products and industry applications refer to the products and applications of artificial intelligence systems in various fields. They are the encapsulation of the overall artificial intelligence solution, which productizes intelligent information decision-making and realizes practical application. Its application areas mainly include: smart terminals, smart transportation, smart medical care, autonomous driving, smart cities, etc.

[0066] This application can be applied to the field of image processing in the field of artificial intelligence. Taking image processing as an example, the following will introduce multiple application scenarios that have been implemented in products.

[0067] In one possible implementation, the neural radiation field can directly synthesize 3D scenes and perform multi-perspective rendering by inputting a limited number of multi-perspective images, eliminating the complex 3D modeling process and achieving the effect of obtaining a planar image of an object from any perspective at a low acquisition cost.

[0068] This application can be applied to, but is not limited to, applications with 3D scene synthesis and multi-view rendering capabilities (hereinafter referred to as new view generation applications) or cloud services provided by cloud-side servers, etc., which are described below:

[0069] 1. New Perspective Generation Applications

[0070] The product form of the embodiment of the present application can be a new perspective generation application. The new perspective generation application can be run on a terminal device or a cloud-side server.

[0071] In one possible implementation, a new perspective generation application can obtain a trained model based on input images from multiple perspectives and the corresponding camera internal parameters during shooting (such as the camera's posture information, etc.). The trained model can output the corresponding image based on the specified perspective.

[0072] In one possible implementation, the user can open a new perspective generation application installed on the terminal device and input an image and perspective information. The new perspective generation application can process the image through the method provided in the embodiment of the present application and present the processing results to the user (the presentation method can be but is not limited to display, saving, uploading to the cloud side, etc.).

[0073] In one possible implementation, a user can open a new perspective generation application installed on a terminal device and input an image. The new perspective generation application can send the image to a server on the cloud side. The server on the cloud side processes the image using the method provided in an embodiment of the present application and transmits the processing result back to the terminal device. The terminal device can present the processing result to the user (the presentation method can be but is not limited to display, saving, uploading to the cloud side, etc.).

[0074] Next, the new perspective generation application in the embodiment of this application is introduced from the functional architecture and the product architecture that implements the function.

[0075] Referring to FIG. 1B , FIG. 1B is a schematic diagram of the functional architecture of a new perspective generation application in an embodiment of the present application:

[0076] In one possible implementation, as shown in FIG1B , a new perspective generation application 102 may receive input parameters 101 (e.g., including an image) and generate a processing result 103. The new perspective generation application 102 may be executed on, for example, at least one computer system and include computer code that, when executed by one or more computers, causes the computers to execute the method provided in the embodiments of the present application.

[0077] Referring to FIG. 1C , FIG. 1C is a schematic diagram of the physical architecture of a new perspective generation application program according to an embodiment of the present application:

[0078] Referring to FIG1C , FIG1C shows a schematic diagram of a system architecture. The system may include a terminal 100 and a server 200. The server 200 may include one or more servers (FIG1C illustrates one server as an example), and the server 200 may provide the method provided in the embodiments of the present application to one or more terminals.

[0079] Among them, a new perspective generation application can be installed on the terminal 100. The above application and web page can provide an interface. The terminal 100 can receive relevant parameters entered by the user on the new perspective generation interface and send the above parameters to the server 200. The server 200 can obtain processing results based on the received parameters and return the processing results to the terminal 100.

[0080] It should be understood that in some optional implementations, the terminal 100 can also complete the action of obtaining the processing result based on the received parameters by itself without the need for the cooperation of the server, and the embodiments of the present application are not limited to this.

[0081] Next, the product form of the terminal 100 in FIG1C is described;

[0082] The terminal 100 in the embodiment of the present application can be a mobile phone, a tablet computer, a wearable device, an in-vehicle device, an augmented reality (AR) / virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), etc., and the embodiment of the present application does not impose any restrictions on this.

[0083] FIG1D shows a schematic diagram of an optional hardware structure of the terminal 100 .

[0084] 1D , the terminal 100 may include components such as a radio frequency unit 110, a memory 120, an input unit 130, a display unit 140, a camera 150 (optional), an audio circuit 160 (optional), a speaker 161 (optional), a microphone 162 (optional), a processor 170, an external interface 180, and a power supply 190. Those skilled in the art will appreciate that FIG1D is merely an example of a terminal or multi-function device and does not limit the terminal or multi-function device. The terminal or multi-function device may include more or fewer components than shown, or may combine certain components or have different components.

[0085] The input unit 130 can be used to receive input digital or character information and generate key signal input related to user settings and function control of the portable multifunction device. Specifically, the input unit 130 may include a touch screen 131 (optional) and / or other input devices 132. The touch screen 131 can detect user touch operations on or near it (for example, operations performed on or near the touch screen using a finger, joint, stylus, or any other suitable object) and drive corresponding connected devices according to pre-set programs. The touch screen can detect user touch actions on the touch screen, convert the touch actions into touch signals and transmit them to the processor 170. It can also receive and execute commands sent by the processor 170; the touch signals include at least touch point coordinate information. The touch screen 131 provides an input interface and an output interface between the terminal 100 and the user. Touch screens can be implemented using various types, including resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch screen 131, the input unit 130 may also include other input devices. Specifically, the other input devices 132 may include, but are not limited to, one or more of a physical keyboard, function keys (such as a volume control key, a switch key, etc.), a trackball, a mouse, a joystick, and the like.

[0086] The input device 132 may receive input images, camera internal parameters, and the like.

[0087] The display unit 140 may be used to display information input by the user or provided to the user, various menus of the terminal 100, interactive interfaces, file display, and / or playback of any multimedia file. In an embodiment of the present application, the display unit 140 may be used to display the interface of a new perspective generation application, processing results, etc.

[0088] Memory 120 can be used to store instructions and data. It primarily includes an instruction storage area and a data storage area. The data storage area can store various data, such as multimedia files and text. The instruction storage area can store software units such as the operating system, applications, and instructions required for at least one function, or subsets or extensions thereof. It may also include non-volatile random access memory (RAM). It provides processor 170 with management functions for the hardware, software, and data resources within the computing and processing device, supporting control software and applications. It is also used to store multimedia files and running programs and applications.

[0089] The processor 170 is the control center of the terminal 100. It connects all components of the terminal 100 using various interfaces and circuits. By executing instructions stored in the memory 120 and accessing data stored therein, it executes various functions of the terminal 100 and processes data, thereby providing overall control of the terminal device. Optionally, the processor 170 may include one or more processing units. Preferably, the processor 170 may integrate an application processor and a modem processor, with the application processor primarily processing the operating system, user interface, and application programs, while the modem processor primarily handles wireless communications. It is understood that the modem processor may not be integrated into the processor 170. In some embodiments, the processor and memory may be implemented on a single chip; in other embodiments, they may be implemented on separate chips. The processor 170 may also generate corresponding operational control signals and send them to the corresponding components of the computing and processing device. It may also read and process data in the software, particularly the data and programs in the memory 120, to enable the various functional modules therein to perform their corresponding functions, thereby controlling the corresponding components to operate as instructed.

[0090] Among them, the memory 120 can be used to store software codes related to the data processing method, the processor 170 can execute the steps of the chip's data processing method, and can also schedule other units (such as the above-mentioned input unit 130 and display unit 140) to achieve corresponding functions.

[0091] The RF unit 110 (optional) can be used to send and receive information or receive and send signals during a call. For example, after receiving downlink information from the base station, it is passed to the processor 170 for processing; in addition, it sends the designed uplink data to the base station. Generally, the RF circuit includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (LNA), a duplexer, etc. In addition, the RF unit 110 can also communicate with network devices and other devices via wireless communication. This wireless communication can use any communication standard or protocol, including but not limited to Global System of Mobile communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Messaging Service (SMS), etc.

[0092] In this embodiment of the present application, the RF unit 110 may send the image to the server 200 and receive the processing result sent by the server 200.

[0093] It should be understood that the radio frequency unit 110 is optional and can be replaced by other communication interfaces, such as a network port.

[0094] The terminal 100 also includes a power supply 190 (such as a battery) for supplying power to various components. Preferably, the power supply can be logically connected to the processor 170 through a power management system, thereby managing functions such as charging, discharging, and power consumption through the power management system.

[0095] The terminal 100 further includes an external interface 180 , which may be a standard Micro USB interface or a multi-pin connector, and may be used to connect the terminal 100 to other devices for communication, or to connect a charger to charge the terminal 100 .

[0096] Although not shown, the terminal 100 may also include a flash, a wireless fidelity (WiFi) module, a Bluetooth module, sensors with different functions, etc., which are not described in detail here. Some or all of the methods described below may be applied to the terminal 100 shown in FIG1D .

[0097] Next, the product form of the server 200 in FIG1C is described;

[0098] FIG2 provides a schematic diagram of the structure of a server 200. As shown in FIG2, the server 200 includes a bus 201, a processor 202, a communication interface 203, and a memory 204. The processor 202, the memory 204, and the communication interface 203 communicate with each other via the bus 201.

[0099] Bus 201 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. Buses can be categorized as address buses, data buses, and control buses. For ease of illustration, FIG2 shows only one thick line, but this does not imply that there is only one bus or only one type of bus.

[0100] The processor 202 may be any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0101] The memory 204 may include volatile memory, such as random access memory (RAM). The memory 204 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard drive (HDD), or solid state drive (SSD).

[0102] The memory 204 may be used to store software codes related to the data processing method, and the processor 202 may execute the steps of the data processing method of the chip, and may also schedule other units to implement corresponding functions.

[0103] It should be understood that the above-mentioned terminal 100 and server 200 can be centralized or distributed devices, and the processors in the above-mentioned terminal 100 and server 200 (such as processor 170 and processor 202) can be hardware circuits (such as application specific integrated circuit (ASIC), field-programmable gate array (FPGA), general-purpose processor, digital signal processor (DSP), microprocessor or microcontroller, etc.), or a combination of these hardware circuits. For example, the processor can be a hardware system with an instruction execution function, such as a CPU, DSP, etc., or a hardware system without an instruction execution function, such as an ASIC, FPGA, etc., or a combination of the above-mentioned hardware systems without an instruction execution function and hardware systems with an instruction execution function.

[0104] It should be understood that the steps related to the model reasoning process in the embodiments of this application involve AI-related operations. When performing AI operations, the instruction execution architecture of the terminal device and server is not limited to the processor-memory architecture described above. The system architecture provided in the embodiments of this application is described in detail below with reference to Figure 3.

[0105] FIG3 is a schematic diagram of the system architecture provided by an embodiment of the present application. As shown in FIG3 , the system architecture 500 includes an execution device 510 , a training device 520 , a database 530 , a client device 540 , a data storage system 550 , and a data acquisition system 560 .

[0106] The execution device 510 includes a calculation module 511, an I / O interface 512, a pre-processing module 513, and a post-processing module 514. The calculation module 511 may include the target model / rule 501, and the pre-processing module 513 and the post-processing module 514 are optional.

[0107] The execution device 510 may be a terminal device or a server that runs the above-mentioned new perspective generation application.

[0108] The data acquisition device 560 is used to collect training samples. The training samples can be multiple images, etc. After collecting the training samples, the data acquisition device 560 stores these training samples in the database 530.

[0109] The training device 520 can train the neural network to be trained (such as the neural radiance field (NeRF) in the embodiment of the present application) based on the training samples maintained in the database 530 to obtain the target model / rule 501.

[0110] It should be noted that, in actual applications, the training samples maintained in the database 530 may not all be collected by the data acquisition device 560, but may also be received from other devices. It should also be noted that the training device 520 may not train the target model / rule 501 entirely based on the training samples maintained in the database 530, but may also obtain training samples from the cloud or other places for model training. The above description should not be used as a limitation on the embodiments of the present application.

[0111] The target model / rule 501 obtained through training with the training device 520 can be applied to different systems or devices, such as the execution device 510 shown in FIG3 . The execution device 510 can be a terminal, such as a mobile phone terminal, a tablet computer, a laptop computer, an augmented reality (AR) / virtual reality (VR) device, an in-vehicle terminal, etc., or a server, etc.

[0112] Specifically, the training device 520 may transfer the trained model to the execution device 510 .

[0113] In Figure 3, the execution device 510 is configured with an input / output (I / O) interface 512 for data interaction with external devices. The user can input data (such as images in the embodiment of the present application) to the I / O interface 512 through the client device 540.

[0114] Preprocessing module 513 and preprocessing module 514 are used to preprocess the input data received by I / O interface 512. It should be understood that preprocessing module 513 and preprocessing module 514 may be absent or only one preprocessing module may be present. If preprocessing module 513 and preprocessing module 514 are absent, computing module 511 may be used directly to process the input data.

[0115] When the execution device 510 preprocesses the input data, or when the computing module 511 of the execution device 510 performs calculations and other related processing, the execution device 510 can call the data, code, etc. in the data storage system 550 for corresponding processing, and can also store the data, instructions, etc. obtained from the corresponding processing in the data storage system 550.

[0116] Finally, the I / O interface 512 provides the processed results to the client device 540 and thus to the user.

[0117] In the scenario shown in FIG3 , the user can manually input data, and this "manual input data" can be operated through the interface provided by I / O interface 512. In another scenario, client device 540 can automatically send input data to I / O interface 512. If user authorization is required for client device 540 to automatically send input data, the user can set the corresponding permissions in client device 540. The user can view the results output by execution device 510 on client device 540, and the specific presentation form can be a display, sound, action, or other specific method. Client device 540 can also serve as a data acquisition terminal, collecting input data input into I / O interface 512 and output results output from I / O interface 512 as new sample data, and storing them in database 530. Of course, collection can also be performed without client device 540, and instead the I / O interface 512 directly stores the input data input into I / O interface 512 and output results output from I / O interface 512 as new sample data in database 530.

[0118] It is worth noting that FIG3 is merely a schematic diagram of a system architecture provided by an embodiment of the present application, and the positional relationships between the devices, components, modules, etc. shown in the figure do not constitute any limitation. For example, in FIG3 , the data storage system 550 is an external memory relative to the execution device 510. In other cases, the data storage system 550 can also be placed in the execution device 510. It should be understood that the execution device 510 can be deployed in the client device 540.

[0119] From the inference side of the model:

[0120] In the embodiment of the present application, the computing module 511 of the above-mentioned execution device 510 can obtain the code stored in the data storage system 550 to implement the steps related to the model reasoning process in the embodiment of the present application.

[0121] In an embodiment of the present application, the computing module 511 of the execution device 510 may include a hardware circuit (such as an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a general-purpose processor, a digital signal processor (DSP), a microprocessor or a microcontroller, etc.), or a combination of these hardware circuits. For example, the training device 520 may be a hardware system with an instruction execution function, such as a CPU, DSP, etc., or a hardware system without an instruction execution function, such as an ASIC, FPGA, etc., or a combination of the above-mentioned hardware systems without an instruction execution function and hardware systems with an instruction execution function.

[0122] Specifically, the computing module 511 of the execution device 510 can be a hardware system with an execution instruction function, and the steps related to the model reasoning process provided in the embodiment of the present application can be software codes stored in the memory. The computing module 511 of the execution device 510 can obtain the software code from the memory and execute the obtained software code to implement the steps related to the model reasoning process provided in the embodiment of the present application.

[0123] It should be understood that the computing module 511 of the execution device 510 can be a combination of a hardware system that does not have the function of executing instructions and a hardware system that has the function of executing instructions. Some of the steps related to the model reasoning process provided in the embodiment of the present application can also be implemented by the hardware system that does not have the function of executing instructions in the computing module 511 of the execution device 510, which is not limited here.

[0124] From the training side of the model:

[0125] In an embodiment of the present application, the above-mentioned training device 520 can obtain the code stored in the memory (not shown in Figure 3, which can be integrated into the training device 520 or deployed separately from the training device 520) to implement the steps related to model training in the embodiment of the present application.

[0126] In an embodiment of the present application, the training device 520 may include a hardware circuit (such as an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a general-purpose processor, a digital signal processor (DSP), a microprocessor or a microcontroller, etc.), or a combination of these hardware circuits. For example, the training device 520 may be a hardware system with an instruction execution function, such as a CPU, DSP, etc., or a hardware system without an instruction execution function, such as an ASIC, FPGA, etc., or a combination of the above-mentioned hardware systems without an instruction execution function and hardware systems with an instruction execution function.

[0127] It should be understood that the training device 520 can be a combination of a hardware system that does not have the function of executing instructions and a hardware system that has the function of executing instructions. Some of the steps related to model training provided in the embodiments of the present application can also be implemented by the hardware system in the training device 520 that does not have the function of executing instructions, which is not limited here.

[0128] 2. New perspective generation cloud services provided by the server:

[0129] In a possible implementation, the server may provide a new perspective generation service to the terminal side through an application programming interface (API).

[0130] Among them, the terminal device can send relevant parameters (such as images from multiple perspectives and corresponding camera internal parameter information, etc.) to the server through the API provided by the cloud. The server can obtain processing results based on the received parameters, etc., and return the processing results to the terminal.

[0131] The description of the terminal and the server can be the same as that of the above embodiments, and will not be repeated here.

[0132] FIG4 shows a process of generating a cloud-like service using a new perspective provided by a cloud platform.

[0133] 1. Activate and purchase content review services.

[0134] 2. Users can download the software development kit (SDK) corresponding to the content review service. Usually, the cloud platform provides multiple development versions of the SDK for users to choose according to the requirements of the development environment, such as JAVA version SDK, Python version SDK, PHP version SDK, Android version SDK, etc.

[0135] 3. After the user downloads the corresponding version of the SDK to the local computer as needed, they import the SDK project into the local development environment, configure and debug it in the local development environment. The local development environment can also be used to develop other functions, forming an application that integrates new perspective generation capabilities.

[0136] 4. When a new perspective generation application is used and needs to generate a new perspective, it can trigger an API call for new perspective generation. When the application triggers the new perspective generation function, it initiates an API request to the running instance of the new perspective generation service in the cloud environment. The API request carries the image and camera internal parameters. The running instance in the cloud environment processes the image and obtains the processing result.

[0137] 5. The cloud environment returns the processing results to the application, thereby completing a method call provided in an embodiment of the present application.

[0138] The embodiments of this application can be applied to most fields requiring image generation, such as autonomous driving sensor simulation, AR / VR, high-precision mapping, and 3D scene reconstruction. Furthermore, this application can also transfer image data dimensions to other types of camera data, such as depth cameras and event cameras, and should be able to produce comparable experimental results.

[0139] Since the embodiments of the present application involve the application of a large number of neural networks, in order to facilitate understanding, the relevant terms and related concepts such as neural networks involved in the embodiments of the present application are first introduced below.

[0140] (1) Neural Network

[0141] A neural network can be composed of neural units. A neural unit can refer to an operation unit that takes xs (i.e., input data) and intercept 1 as input. The output of the operation unit can be:

[0142] Where s = 1, 2, ... n, n is a natural number greater than 1, Ws is the weight of xs, and b is the bias of the neural unit. f is the activation function of the neural unit, which is used to introduce nonlinear characteristics into the neural network to convert the input signal of the neural unit into the output signal. The output signal of the activation function can be used as the input of the next convolutional layer, and the activation function can be a sigmoid function. A neural network is a network formed by connecting multiple single neural units mentioned above, that is, the output of one neural unit can be the input of another neural unit. The input of each neural unit can be connected to the local receptive field of the previous layer to extract the features of the local receptive field. The local receptive field can be an area composed of several neural units.

[0143] (2) Deep Neural Networks

[0144] A deep neural network (DNN) can be understood as a neural network with many hidden layers. There is no special metric for "many" here. The commonly mentioned multi-layer neural networks and deep neural networks are essentially the same thing. According to the position of different layers of DNN, the neural network inside the DNN can be divided into three categories: input layer, hidden layer, and output layer. Generally speaking, the first layer is the input layer, the last layer is the output layer, and the layers in between are all hidden layers. The layers are fully connected, that is, any neuron in the i-th layer must be connected to any neuron in the i+1-th layer. Although DNN looks complicated, the work of each layer is actually not complicated. Simply put, it is the following linear relationship expression: in, is the input vector, is the output vector, is the offset vector, W is the weight matrix (also called coefficient), and α() is the activation function. Each layer is just an input vector After such a simple operation, the output vector Since there are many DNN layers, the coefficient W and the offset vector So how are the specific parameters defined in DNN? First, let's look at the definition of coefficient W. Take a three-layer DNN as an example, for example: the linear coefficient from the 4th neuron in the second layer to the 2nd neuron in the third layer is defined as The superscript 3 represents the layer number of the coefficient W, while the subscripts correspond to the output of the third layer index 2 and the input of the second layer index 4. In summary, the coefficients from the kth neuron in the L-1th layer to the jth neuron in the Lth layer are defined as Note that the input layer has no W parameter. In deep neural networks, more hidden layers allow the network to better capture complex real-world situations. Theoretically, a model with more parameters is more complex and has greater "capacity," meaning it can handle more complex learning tasks.

[0145] (3) Convolutional Neural Network (CNN) is a deep neural network with a convolutional structure. Convolutional neural network contains a feature extractor consisting of a convolution layer and a subsampling layer. The feature extractor can be regarded as a filter, and the convolution process can be regarded as using a trainable filter to convolve with an input image or convolution feature plane (feature map). The convolution layer refers to the neuron layer in the convolutional neural network that performs convolution processing on the input signal. In the convolution layer of the convolutional neural network, a neuron can only be connected to some neurons in the adjacent layer. A convolution layer usually contains several feature planes, and each feature plane can be composed of some rectangularly arranged neural units. The neural units in the same feature plane share weights, and the shared weights here are the convolution kernels. Shared weights can be understood as the way of extracting image information is independent of position. The implicit principle is that the statistical information of a part of the image is the same as that of other parts. This means that the image information learned in a part can also be used in another part. Therefore, the same learned image information can be used for all positions on the image. In the same convolutional layer, multiple convolution kernels can be used to extract different image information. Generally speaking, the more convolution kernels there are, the richer the image information reflected by the convolution operation.

[0146] Convolution kernels can be initialized as matrices of random size, and during the training process of the convolutional neural network, the convolution kernels can be learned to obtain reasonable weights. In addition, the direct benefit of shared weights is that they reduce the number of connections between the layers of the convolutional neural network, while also reducing the risk of overfitting.

[0147] (4) Backpropagation algorithm

[0148] Convolutional neural networks can use the back propagation (BP) algorithm to correct the size of the parameters in the initial super-resolution model during training, reducing the reconstruction error loss of the super-resolution model. Specifically, the forward propagation of the input signal to the output generates an error loss. This error loss information is then backpropagated to update the parameters of the initial super-resolution model, thereby converging the error loss. The BP algorithm is a backward propagation movement dominated by the error loss, aiming to obtain the optimal super-resolution model parameters, such as the weight matrix.

[0149] (5) Loss function

[0150] During the training of a deep neural network, because we want the output of the deep neural network to be as close as possible to the desired predicted value, we can compare the current network's predicted value with the desired target value and then update the weight vector of each layer of the neural network based on the difference between the two. (Of course, there is usually an initialization process before the first update, which is to pre-configure the parameters for each layer in the deep neural network.) For example, if the network's predicted value is too high, the weight vector is adjusted to make it predict a lower value. This adjustment is continued until the deep neural network can predict the desired target value or a value very close to the desired target value. Therefore, it is necessary to predefine "how to compare the difference between the predicted value and the target value." This is the loss function (or objective function), which is an important equation used to measure the difference between the predicted value and the target value. For example, the loss function output value (loss) indicates a greater difference, so training a deep neural network becomes a process of minimizing this loss as much as possible.

[0151] (6) 3D Gaussian Splatting is an emerging method for scene reconstruction and image rendering. Compared with neural rendering methods, Splatting abandons the process of emitting a ray for each pixel and sampling a large number of samples on the ray. Instead, it represents the scene as a Gaussian sphere and obtains the rendering result by projecting the Gaussian sphere, achieving real-time rendering speed. By switching from volume-based representation to learning point representation, the improvement of existing methods in terms of memory and runtime in training and inference is more than an order of magnitude. The method starts with a uniformly sampled random point cloud, learns the spherical harmonic function coefficients related to the position and viewing direction of each point, and uses a differentiable splatting-based renderer to project the point cloud onto the imaging plane according to a certain Gaussian distribution to obtain the rendering result, so as to train the model to reproduce a set of input training images with a given camera pose.

[0152] (7) Multilayer perceptron, also called artificial neural network (ANN), has multiple hidden layers in addition to the input and output layers. The simplest MLP contains only one hidden layer.

[0153] 3D Gaussian splatting represents the scene as a Gaussian sphere and produces rendering results by projecting the Gaussian sphere, achieving real-time rendering speeds. Starting with a uniformly sampled random point cloud, this method learns the spherical harmonic coefficients related to each point's position and viewing direction. Using a differentiable splatting-based renderer, the point cloud is projected onto the imaging plane according to a specific Gaussian distribution to produce the rendering result.

[0154] However, the reconstruction and rendering effects of existing 3D Gaussian splattering methods are still poor.

[0155] In order to solve the above problems, the present invention provides a data processing method. The data processing method of the present invention is described in detail below with reference to the accompanying drawings.

[0156] Refer to Figure 5, which is a flow chart of a data processing method provided in an embodiment of the present application. As shown in Figure 5, a data processing method provided in an embodiment of the present application may include steps 501 to 503, and these steps are described in detail below.

[0157] 501. Acquire an image captured for a target scene;

[0158] In one possible implementation, an image may be acquired, which may be an image captured by a camera, or one or more frames of a captured video, wherein the video may be captured from multiple perspectives of the same scene. The scene may be a dynamic scene, that is, a scene with moving objects.

[0159] In a possible implementation, the image may be pre-photographed and stored in a gallery of a terminal device, or downloaded from the Internet. The embodiment of the present application does not impose any limitation on the specific content of the image.

[0160] 502. Based on the image, learn and obtain multiple primitives of the target scene, where different primitives include 3D distributions of areas at different positions in space, and the 3D distributions are used to indicate target information, and the target information is at least one of semantic information, depth information, or optical flow information.

[0161] In a possible implementation, a plurality of primitives of the target scene may be learned based on the image, and the primitives may include 3D distributions of regions at different positions in space. For example, the primitives may be Gaussian spheres.

[0162] In a possible implementation, the plurality of primitives include a plurality of first primitives in a static area and a plurality of second primitives in a dynamic area of ​​the scene.

[0163] In one possible implementation, the image specifically includes multiple frames of a video, each frame corresponding to multiple second primitives, and the multiple second primitives corresponding to different frames are different. In other words, a fixed 3D distribution can be obtained for static areas, while a 3D distribution that changes over time frames, i.e., a dynamic 3D distribution, can be obtained for dynamic areas.

[0164] Taking the 3D distribution as a Gaussian distribution as an example, assuming that the scene consists of a static area and N rigid dynamic objects, a complete 3D scene consists of a static background area model and N dynamic object models. The static area is represented by a static Gaussian in the world coordinate system. Each dynamic object uses a dynamic Gaussian in the canonical coordinate system and a set of rigid transformations. Modeling is performed, where t represents the timestamp.

[0165] Static and dynamic regions can be modeled using 3D Gaussians. Each Gaussian is represented by a 3D covariance matrix ∑∈R 3×3 and a 3D position μ∈R 3 and an opacity α∈R + definition:

[0166] Each Gaussian represents a color vector c∈R 3 , parameterized as the SH coefficient.

[0167] In one possible implementation, the 3D distribution is used to indicate target information, which is at least one of semantic information, depth information, or optical flow information. Specifically, the distribution of each primitive (e.g., the semantic logarithm s∈R of the 3D Gaussian) can be used to indicate the target information. S ) to allow rendering of semantic maps (e.g., 2D semantic labels). In addition, additional modeling can be performed based on the distribution of each primitive, allowing rendering of optical flow maps. For example, the 3D position μ can be projected into the image space at two different time stamps (t1 and t2) and the motion can be calculated to obtain the rendered optical flow.

[0168] In a possible implementation, the image specifically includes images of multiple frames of a video, the video includes a moving object (or it can be called a dynamic object), and the multiple second primitives include multiple primitives of each frame; after learning the multiple primitives of the target scene based on the image, the motion model of the moving object can be used as a constraint to optimize the multiple second primitives. In an embodiment of the present application, dynamic target reconstruction and rendering based on kinematic constraints can be performed. For example, referring to Figure 7, the dynamic foreground and background can be simultaneously modeled and optimized based on the scene graph of 3D Gaussian Splatting, and the kinematic model and 3D box parameters can be introduced for simultaneous optimization. Among them, the position and rotation matrix of the dynamic object at each moment can be calculated by the kinematic model.

[0169] 503. Render a 3D model, a semantic map, a depth map, or an optical flow map of the target scene based on aggregation of some or all of the multiple primitives.

[0170] In an embodiment of the present application, in addition to RGB images, information of other dimensions can also be rendered through primitives, such as 3D models, semantic maps, depth maps or optical flow maps. During parameter learning, the reconstruction and rendering effects of RGB images can be significantly improved by assisting with information of other dimensions (that is, updating parameters based on losses constructed based on information of other dimensions).

[0171] In a possible implementation, the RGB image of the target scene may be rendered according to the aggregation of some or all of the multiple primitives.

[0172] For example, taking the Gaussian distribution as an example, for the RGB image branch, the combination of static and dynamic Gaussians can be sorted by α blending and projected onto the image plane:

[0173] In the above formula, α′ j Determined by the projected 2D Gaussian and the 3D opacity alpha.

[0174] Compared to single-object scenes, urban scenes typically involve more complex lighting conditions, and images are typically captured using automatic white balance and automatic exposure. NeRF-based methods typically input each frame's appearance embedding into a neural network along with the 3D position to calculate the color, thereby compensating for exposure. However, when using 3D Gaussians, there is no neural network capable of processing appearance embeddings. The embodiment of the present application can map the camera's external parameters to an affine matrix A∈R through a task network (e.g., MLP). 3×3 and vector b∈R 3 , thus generating an exposure affine matrix for each camera: The rendering quality of the experimental section can be improved by modeling the exposure.

[0175] In a possible implementation, semantic information of some or all of the multiple primitives may be aggregated to render a semantic graph of the target scene; wherein the aggregation includes a softmax operation on 3D semantics in the semantic information.

[0176] For example, taking the Gaussian distribution as an example, for the semantic branch: the 2D semantic label can be obtained based on the 3D semantic logit s through α blending through the rendering formula of the semantic information:

[0177] Before α blending, the 3D semantic logarithm s can be i Perform a softmax operation, which is different from most existing methods that apply softmax to the accumulating non-normalized 3D semantic logits s i The opposite is true for the 2D semantic logits obtained. Applying softmax in 2D space results in the generation of noisy 3D semantic labels. This is because 2D space softmax can generate accurate 2D semantics by adjusting the scale of the 3D semantic logits, allowing a single sampling point with a large number of logit values ​​to significantly affect the overall volume rendering result. For example, although the target rendering label is "tree", an unwanted floating point labeled "car" may not be penalized as long as there is a 3D Gaussian spectrum along this ray that provides a large logit value of "tree". In contrast, the present application embodiment can eliminate such floating points by normalizing the logits in 3D space.

[0178] For example, taking the distribution as Gaussian distribution, for the optical flow branch: 3D Gaussian representation can also render optical flow. Given two time stamps (t1 and t2), first calculate the optical flow of each 3D Gaussian center μ as Specifically, μ can be projected into the 2D image space according to the intrinsic and extrinsic parameters of the camera, and obtained:

[0179] Calculate the motion vector based on the above formula Next, the optical flow map is rendered using the optical flow rendering formula based on volume rendering:

[0180] This rendering process assumes that any pixel of a 2D Gaussian splash shares the same optical flow direction with the corresponding Gaussian center, but with a scaled magnitude.

[0181] In one possible implementation, during parameter learning, labels of the 3D model, semantic map, depth map, or optical flow map of the image can be obtained; and based on the labels, the multiple primitives are updated. This embodiment of the application proposes a complete large-scale scene understanding framework based on 3D Gaussian Spatting, which achieves joint optimization of multiple branches such as RGB, semantics, optical flow, and moving targets, without relying on manual labeling of moving targets, and achieves joint optimization of static background and dynamic targets based on 3D-GS.

[0182] Next, we introduce a specific implementation process:

[0183] Referring to Figure 6, Figure 6 is a schematic diagram of an application architecture of an embodiment of the present application. The present application can obtain a semantic segmentation image sequence, an optical flow image prediction sequence, and a 3D detection tracking frame pseudo-label sequence corresponding to the input image based on a pre-trained model; given an input RGB image, use the SFM (structure-from-motion) model to obtain a three-dimensional color point cloud and initialize the background 3D Gaussian sphere; randomly initialize the 3D Gaussian sphere within the predicted 3D detection frame, and place the foreground 3D Gaussian sphere according to the position of the 3D detection frame; initialize the position, speed, direction, acceleration, and angular velocity parameters of the dynamic vehicle at each moment based on the predicted 3D detection frame; the kinematic model of the dynamic target optimization process can use unicycle model optimization or bicycle model optimization. Figure 8 is a schematic diagram of the dynamic target optimization process based on the unicycle model:

[0184] The unicycle model is shown below: θ t+1 =θ t +w t ;

[0185] Here, v t represents the forward speed, w t is the angular velocity. Compared to directly optimizing the transformation of the dynamic vehicle in each frame independently, the proposed model integrates physical constraints, which enables smoother motion modeling of moving objects and makes them less prone to local minima.

[0186] Although we can define the initial state (x1, y1, θ1) and recursively derive v based on the velocity t and w t , but this recursive parameterization is difficult to optimize. In practice, I define a set of trainable states and trainable speed And add regularization terms to ensure that the state of the vehicle conforms to the characteristics of the unicycle model in the formula. In addition, we take the vertical position of the vehicle Modeled as optimizable parameters.

[0187] Render all foreground and background 3D Gaussian spheres to obtain the model-predicted RGB, semantic, and optical flow maps. In addition, the depth of each 3D Gaussian sphere can be rendered using a similar volume rendering method to obtain a depth map. The center point of the 3D Gaussian sphere is extracted to obtain a semantic point cloud.

[0188] The embodiments of the present application achieve state-of-the-art (SOTA) performance in the field of new-perspective image synthesis, achieving a key indicator of image rendering quality (PSNR). The scene geometry estimation capability is significantly improved compared to existing technologies. Compared to CG image synthesis methods, the method offers lower costs, higher image fidelity, and greater scene diversity. For example, see Figures 9, 10A, and 10B. Figure 9 illustrates the effect of a static scene, Figure 10A illustrates the effect of a dynamic scene, and Figure 10B illustrates the effect of a scene's 3D geometry.

[0189] 11 , which is a schematic diagram of the structure of a data processing device provided in an embodiment of the present application. As shown in FIG11 , a data processing device 1100 provided in an embodiment of the present application includes:

[0190] An acquisition module 1101 is configured to acquire an image captured for a target scene;

[0191] The specific description of the acquisition module 1101 can refer to the description of step 501 in the above embodiment, which will not be repeated here.

[0192] The processing module 1102 is used to learn and obtain multiple primitives of the target scene based on the image, where different primitives include 3D distributions of areas at different positions in space, and the 3D distributions are used to indicate target information, and the target information is at least one of semantic information, depth information, or optical flow information; and render a 3D model, semantic map, depth map, or optical flow map of the target scene based on the aggregation of some or all of the multiple primitives.

[0193] The specific description of the processing module 1102 can refer to the description of step 502 to step 503 in the above embodiment, which will not be repeated here.

[0194] In a possible implementation, the primitive is a Gaussian sphere.

[0195] In a possible implementation, the plurality of primitives include a plurality of first primitives in a static area and a plurality of second primitives in a dynamic area of ​​the scene.

[0196] In one possible implementation, the image specifically includes images of multiple frames of a video, the video includes a moving object, and the multiple second primitives include multiple primitives in each frame; after learning the multiple primitives of the target scene based on the image, the processing module 1102 is further configured to:

[0197] The plurality of second primitives are optimized using the motion model of the moving object as a constraint.

[0198] In a possible implementation, the image specifically includes images of multiple frames of a video, the image of each frame corresponds to multiple second primitives, and the multiple second primitives corresponding to different frames are different.

[0199] In a possible implementation, the processing module 1102 is further configured to:

[0200] Rendering an RGB image of the target scene according to aggregation of some or all of the plurality of primitives.

[0201] In a possible implementation, the processing module 1102 is specifically configured to:

[0202] Aggregating semantic information of some or all of the multiple primitives to render a semantic graph of the target scene; wherein the aggregation includes performing a softmax operation on 3D semantics in the semantic information.

[0203] In a possible implementation, the processing module 1102 is further configured to:

[0204] Obtaining a label of a 3D model, semantic map, depth map, or optical flow map of the image;

[0205] The plurality of primitives are updated according to the tags.

[0206] Next, an execution device provided in an embodiment of the present application is introduced. Please refer to Figure 12. Figure 12 is a structural schematic diagram of an execution device provided in an embodiment of the present application. The execution device 1200 can be specifically manifested as a virtual reality VR device, a mobile phone, a tablet, a laptop computer, a smart wearable device, a monitoring data processing device or a server, etc., which is not limited here. Specifically, the execution device 1200 includes: a receiver 1201, a transmitter 1202, a processor 1203 and a memory 1204 (wherein the number of processors 1203 in the execution device 1200 can be one or more, and Figure 12 takes one processor as an example), wherein the processor 1203 may include an application processor 12031 and a communication processor 12032. In some embodiments of the present application, the receiver 1201, the transmitter 1202, the processor 1203 and the memory 1204 may be connected via a bus or other means.

[0207] The memory 1204 may include a read-only memory and a random access memory, and provides instructions and data to the processor 1203. A portion of the memory 1204 may also include non-volatile random access memory (NVRAM). The memory 1204 stores processor and operation instructions, executable modules, or data structures, or subsets or extended sets thereof. The operation instructions may include various operation instructions for implementing various operations.

[0208] Processor 1203 controls the operation of the execution device. In specific applications, the various components of the execution device are coupled together via a bus system. In addition to a data bus, the bus system may also include a power bus, a control bus, and a status signal bus. However, for clarity, all bus systems are referred to as a bus system in the figure.

[0209] The methods disclosed in the above embodiments of the present application can be applied to or implemented by processor 1203. Processor 1203 can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits or software instructions in processor 1203. The above processor 1203 can be a general-purpose processor, a digital signal processor (DSP), a microprocessor, or a microcontroller, and can further include an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The processor 1203 can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in conjunction with the embodiments of the present application can be directly implemented as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 1204. Processor 1203 reads information from memory 1204 and, in conjunction with its hardware, completes the steps involved in the model inference process in the above method.

[0210] Receiver 1201 can be used to receive input digital or character information and generate signal input related to executing device-related settings and function control. Transmitter 1202 can be used to output digital or character information through the first interface. Transmitter 1202 can also be used to send instructions to the disk pack through the first interface to modify data in the disk pack. Transmitter 1202 can also include a display device such as a display screen.

[0211] The present application also provides a training device. Please refer to FIG. 13 , which is a schematic diagram of the structure of a training device provided by an embodiment of the present application. Specifically, the training device 1300 is implemented by one or more servers. The training device 1300 may vary significantly due to different configurations or performance. It may include one or more central processing units (CPUs) 1313 (e.g., one or more processors), a memory 1332, and one or more storage media 1330 (e.g., one or more mass storage devices) storing application programs 1342 or data 1344. The memory 1332 and storage medium 1330 may be either ephemeral or persistent storage. The program stored in the storage medium 1330 may include one or more modules (not shown), each module including a series of instruction operations on the training device. Furthermore, the CPU 1313 may be configured to communicate with the storage medium 1330 to execute the series of instruction operations in the storage medium 1330 on the training device 1300.

[0212] The training device 1300 may also include one or more power supplies 1326, one or more wired or wireless network interfaces 1350, one or more input and output interfaces 1358; or, one or more operating systems 1341, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0213] In the embodiment of the present application, the central processing unit 1313 is used to execute actions related to model training in the above embodiment.

[0214] An embodiment of the present application also provides a computer program product, which, when running on a computer, enables the computer to execute the steps executed by the aforementioned execution device, or enables the computer to execute the steps executed by the aforementioned training device.

[0215] A computer-readable storage medium is also provided in an embodiment of the present application, which stores a program for signal processing. When the computer-readable storage medium is run on a computer, it enables the computer to execute the steps executed by the aforementioned execution device, or enables the computer to execute the steps executed by the aforementioned training device.

[0216] The execution device, training device or terminal device provided in the embodiments of the present application can specifically be a chip, and the chip includes: a processing unit and a communication unit, the processing unit can be, for example, a processor, and the communication unit can be, for example, an input / output interface, a pin or a circuit, etc. The processing unit can execute the computer execution instructions stored in the storage unit, so that the chip in the execution device executes the data processing method described in the above embodiment, or so that the chip in the training device executes the data processing method described in the above embodiment. Optionally, the storage unit is a storage unit in the chip, such as a register, a cache, etc. The storage unit can also be a storage unit located outside the chip in the wireless access device, such as a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM), etc.

[0217] Specifically, see Figure 14 , which is a schematic diagram of the structure of a chip provided in an embodiment of the present application. The chip may be a neural network processor (NPU) 1400. NPU 1400 is mounted on a host CPU (host CPU) as a coprocessor, with tasks assigned by the host CPU. The core of the NPU is arithmetic circuit 1403, which is controlled by controller 1404 to extract matrix data from memory and perform multiplication operations.

[0218] In some implementations, the arithmetic circuit 1403 includes multiple processing units (PEs). In some implementations, the arithmetic circuit 1403 is a two-dimensional systolic array. The arithmetic circuit 1403 can also be a one-dimensional systolic array or other electronic circuitry capable of performing mathematical operations such as multiplication and addition. In some implementations, the arithmetic circuit 1403 is a general-purpose matrix processor.

[0219] For example, assume there are input matrix A, weight matrix B, and output matrix C. The arithmetic circuit retrieves the corresponding data of matrix B from weight memory 1402 and caches it on each PE in the arithmetic circuit. The arithmetic circuit retrieves the data of matrix A from input memory 1401 and performs a matrix operation on matrix B. The partial or final matrix result is stored in accumulator 1408.

[0220] Unified memory 1406 is used to store input and output data. Weight data is directly transferred to weight memory 1402 through the Direct Memory Access Controller (DMAC) 1405. Input data is also transferred to unified memory 1406 through the DMAC.

[0221] BIU stands for Bus Interface Unit, i.e., bus interface unit 1410 , which is used for interaction between the AXI bus, DMAC, and instruction fetch buffer (IFB) 1409 .

[0222] The bus interface unit 1410 (BIU) is used for the instruction fetch memory 1409 to obtain instructions from the external memory, and is also used for the storage unit access controller 1405 to obtain the original data of the input matrix A or the weight matrix B from the external memory.

[0223] DMAC is mainly used to transfer input data in the external memory DDR to the unified memory 1406 or transfer weight data to the weight memory 1402 or transfer input data to the input memory 1401.

[0224] The vector calculation unit 1407 includes multiple operation processing units. When necessary, it further processes the output of the operation circuit 1403, such as vector multiplication, vector addition, exponential operation, logarithmic operation, size comparison, etc. It is mainly used for non-convolutional / fully connected layer network calculations in neural networks, such as batch normalization, pixel-level summation, and upsampling of feature planes.

[0225] In some implementations, the vector calculation unit 1407 can store the processed output vector to the unified memory 1406. For example, the vector calculation unit 1407 can apply a linear function or a nonlinear function to the output of the operation circuit 1403, such as linear interpolation of the feature plane extracted by the convolution layer, or accumulate a vector of values ​​to generate an activation value. In some implementations, the vector calculation unit 1407 generates a normalized value, a pixel-level summed value, or both. In some implementations, the processed output vector can be used as an activation input to the operation circuit 1403, for example, for use in subsequent layers in a neural network.

[0226] An instruction fetch buffer 1409 connected to the controller 1404 is used to store instructions used by the controller 1404;

[0227] Unified memory 1406, input memory 1401, weight memory 1402, and instruction fetch memory 1409 are all on-chip memories. External memories are private to the NPU hardware architecture.

[0228] The processor mentioned in any of the above places can be a general-purpose central processing unit, a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of the above program.

[0229] It should also be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided in this application, the connection relationship between the modules indicates that there is a communication connection between them, which can be specifically implemented as one or more communication buses or signal lines.

[0230] Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course can also be implemented by special hardware including application-specific integrated circuits, special CPUs, special memories, special components, etc. In general, all functions performed by computer programs can be easily implemented with corresponding hardware, and the specific hardware structures used to implement the same function can also be diverse, such as analog circuits, digital circuits or special circuits, etc. However, for the present application, software program implementation is a better implementation method in most cases. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer's floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk or optical disk, etc., and includes a number of instructions to enable a computer device (which can be a personal computer, training equipment, or network equipment, etc.) to execute the methods described in each embodiment of the present application.

[0231] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0232] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, a computer, a training device or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website, a computer, a training device or a data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

Claims

1. A data processing method, characterized in that: The method comprises: Acquire images collected for the target scene; Learning a plurality of primitives of the target scene based on the image, where different primitives include 3D distributions of regions at different positions in a space where the target scene is located, the 3D distributions being used to indicate target information, where the target information is at least one of semantic information, depth information, or optical flow information; Rendering a 3D model, a semantic map, a depth map, or an optical flow map of the target scene according to aggregation of some or all of the multiple primitives.

2. The method according to claim 1, characterized in that The primitive is a Gaussian sphere.

3. The method according to claim 1 or 2, characterized in that The plurality of primitives include a plurality of first primitives in a static area and a plurality of second primitives in a dynamic area of ​​the scene.

4. The method according to claim 3, characterized in that The image specifically includes images of a plurality of frames of a video, the video includes a moving object, and the plurality of second primitives include a plurality of primitives of each frame; After learning and obtaining a plurality of primitives of the target scene according to the image, the method further includes: The plurality of second primitives are optimized using the motion model of the moving object as a constraint.

5. The method according to claim 3 or 4, characterized in that The image specifically includes images of multiple frames of a video, each frame image corresponds to multiple second primitives, and the multiple second primitives corresponding to different frames are different.

6. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: Rendering an RGB image of the target scene according to aggregation of some or all of the plurality of primitives.

7. The method according to any one of claims 1 to 6, characterized in that: The rendering of the semantic map, depth map or optical flow map of the target scene according to the aggregation of some or all of the multiple primitives includes: Aggregating semantic information of some or all of the multiple primitives to render a semantic graph of the target scene; wherein the aggregation includes performing a softmax operation on 3D semantics in the semantic information.

8. The method according to any one of claims 1 to 7, characterized in that: The method further comprises: Obtaining a label of a 3D model, semantic map, depth map, or optical flow map of the image; The plurality of primitives are updated according to the tags.

9. A data processing device, characterized in that: The device comprises: An acquisition module is used to acquire images collected for a target scene; A processing module is configured to learn, based on the image, a plurality of primitives of the target scene, where different primitives include 3D distributions of regions at different positions in space, and the 3D distributions are used to indicate target information, where the target information is at least one of semantic information, depth information, or optical flow information; and render a 3D model, semantic map, depth map, or optical flow map of the target scene based on aggregation of some or all of the plurality of primitives.

10. The device according to claim 9, characterized in that The primitive is a Gaussian sphere.

11. The device according to claim 9 or 10, characterized in that The plurality of primitives include a plurality of first primitives in a static area and a plurality of second primitives in a dynamic area of ​​the scene.

12. The device according to claim 11, characterized in that The image specifically includes images of multiple frames of a video, the video includes a moving object, and the multiple second primitives include multiple primitives in each frame; after learning and obtaining the multiple primitives of the target scene based on the image, the processing module is further configured to: The plurality of second primitives are optimized using the motion model of the moving object as a constraint.

13. The device according to claim 11 or 12, characterized in that The image specifically includes images of multiple frames of a video, each frame image corresponds to multiple second primitives, and the multiple second primitives corresponding to different frames are different.

14. The device according to any one of claims 9 to 13, characterized in that The processing module is further configured to: Rendering an RGB image of the target scene according to aggregation of some or all of the plurality of primitives.

15. The device according to any one of claims 9 to 14, characterized in that The processing module is specifically used to: Aggregating semantic information of some or all of the multiple primitives to render a semantic graph of the target scene; wherein the aggregation includes performing a softmax operation on 3D semantics in the semantic information.

16. The device according to any one of claims 9 to 15, characterized in that The processing module is further configured to: Obtaining a label of a 3D model, semantic map, depth map, or optical flow map of the image; The plurality of primitives are updated according to the tags.

17. A computer storage medium, characterized in that The computer storage medium stores one or more instructions that, when executed by one or more computers, cause the one or more computers to perform the operations of the method of any one of claims 1 to 8.

18. A computer program product, characterized in that The method comprises computer-readable instructions, which, when executed on a computer device, cause the computer device to execute the method according to any one of claims 1 to 8.

19. A system comprising at least one processor and at least one memory; the processor and the memory are connected via a communication bus and communicate with each other; The at least one memory is used to store code; The at least one processor is configured to execute the code to perform the method according to any one of claims 1 to 8.

Images