Search

CN-121982181-A - Urban level digital twin light rendering method

CN121982181ACN 121982181 ACN121982181 ACN 121982181ACN-121982181-A

Abstract

The embodiment of the invention provides a city level digital twin light-weight rendering method which comprises the steps of obtaining multi-source heterogeneous data, calculating rendering data corresponding to a first rendering channel and a second rendering channel of the multi-source heterogeneous data, extracting rendering multi-level parameters of the rendering data, establishing a visual rendering response surface model aiming at the rendering multi-level parameters to obtain a rendering response value, carrying out multi-objective optimization optimizing aiming at the rendering response value to obtain a rendering relation parameter, reading a list corresponding to the rendering relation parameter when the rendering relation parameter is loaded on the model, carrying out parameterization configuration on geometry, texture and a shader to obtain a digital twin city model, converting a real rendering optimization problem which is originally time-consuming into a quick prediction and multi-objective optimization problem based on a Kriging model, realizing scientific design of city level digital twin light-weight rendering, remarkably improving the optimization efficiency and guaranteeing the robustness of a final scheme.

Inventors

  • TANG WEI
  • LUO JIANMIN
  • ZHAO ZIHAO

Assignees

  • 深圳市云鲸视觉科技有限公司

Dates

Publication Date
20260505
Application Date
20260407

Claims (10)

  1. 1. The city level digital twin light rendering method is characterized by comprising the following steps: acquiring multi-source heterogeneous data; Calculating rendering data corresponding to a first rendering channel and a second rendering channel of the multi-source heterogeneous data; extracting rendering multi-level parameters of the rendering data; establishing a visual rendering response surface model aiming at the rendering multi-level parameters to obtain a rendering response value; performing multi-objective optimization for the rendering response value to obtain rendering relation parameters; and when the model is loaded according to the rendering relation parameters, automatically reading a list corresponding to the rendering relation parameters, and carrying out parameterization configuration on geometry, texture and a shader to obtain the digital twin city model.
  2. 2. The method of claim 1, wherein the multi-source heterogeneous data comprises oblique photography model data, building information model data, geographic information system data, and laser point cloud data, and wherein calculating rendering data corresponding to a first rendering channel and a second rendering channel of the multi-source heterogeneous data comprises: converting the oblique photography model data, the building information model data, the geographic information system data and the laser point cloud data into reference signals; Inputting the reference signal to a first adaptive filter and a second adaptive filter to obtain a main noise source signal and a secondary noise source signal; the secondary noise source signal is subjected to error processing to obtain a processed secondary noise source signal; and performing adaptive weight filtering on the main noise source signal and the processed secondary noise source signal to obtain rendering data corresponding to the first rendering channel and the second rendering channel.
  3. 3. The method of claim 1, wherein the extracting the rendering multi-level parameters of the rendering data comprises: Extracting geometric layer parameters, texture layer parameters and shader layer parameters of the rendering data; And forming the geometric layer parameters, the texture layer parameters and the shader layer parameters into rendering multi-level parameters.
  4. 4. The method of claim 1, wherein the building a visual rendering response surface model for the rendering multi-level parameters results in a rendering response value, comprising: establishing a visual rendering response surface model according to the Kriging approximate model; performing combined sampling on the rendering multi-level parameters, and acquiring initial response values under each group of parameters in a visual rendering response surface model; and performing sensitivity analysis through the initial response value to obtain a rendering response value.
  5. 5. The method according to claim 1, wherein the performing multi-objective optimization for the rendering response value to obtain a rendering relationship parameter includes: establishing a multi-objective optimization function according to the rendering multi-level parameters and the rendering response values; And solving the pareto optimal solution set on the multi-objective optimization function by adopting an NSGA-II genetic algorithm, selecting a corresponding optimal parameter combination from the pareto front, and determining the optimal parameter combination as a rendering relation parameter.
  6. 6. The method of claim 5, wherein the establishing a multi-objective optimization function based on the rendering multi-level parameters and the rendering response values comprises: establishing a first sub-objective optimization function of maximized visual quality based on the rendering multi-level parameters; Establishing a second sub-objective optimization function of minimized rendering overhead based on the rendering multi-level parameters; establishing a third sub-objective optimization function of the minimized rendering time based on the rendering response value; And establishing a multi-objective optimization function according to the first sub-objective optimization function, the second sub-objective optimization function and the third sub-objective optimization function.
  7. 7. An urban level digital twin lightweight rendering system, comprising: the first acquisition module is used for acquiring multi-source heterogeneous data; the computing module is used for computing rendering data corresponding to the first rendering channel and the second rendering channel of the multi-source heterogeneous data; The extraction module is used for extracting rendering multi-level parameters of the rendering data; the rendering response value module is used for establishing a visual rendering response surface model aiming at the rendering multi-level parameters to obtain a rendering response value; the optimization optimizing module is used for carrying out multi-objective optimization optimizing on the rendering response value to obtain rendering relation parameters; And the digital twin city model module is used for automatically reading a list corresponding to the rendering relation parameters according to the rendering relation parameters when the model is loaded, and carrying out parameterization configuration on geometry, texture and a shader to obtain the digital twin city model.
  8. 8. The system of claim 7, wherein the multi-source heterogeneous data comprises oblique photography model data, building information model data, geographic information system data, laser point cloud data, the computing module comprising: the conversion sub-module is used for converting the oblique photography model data, the building information model data, the geographic information system data and the laser point cloud data into reference signals; The input submodule is used for inputting the reference signal to the first adaptive filter and the second adaptive filter to obtain a main noise source signal and a secondary noise source signal; the error processing submodule is used for carrying out error processing on the secondary noise source signal to obtain a processed secondary noise source signal; and the weight filtering sub-module is used for carrying out self-adaptive weight filtering on the main noise source signal and the processed secondary noise source signal to obtain rendering data corresponding to the first rendering channel and the second rendering channel.
  9. 9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the urban level digital twin lightweight rendering method of any one of claims 1 to 6 when the computer program is executed.
  10. 10. A computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor implements the steps of the urban level digital twin lightweight rendering method of any of claims 1 to 6.

Description

Urban level digital twin light rendering method Technical Field The invention relates to the technical field of computers, in particular to a city digital twin light-weight rendering method, a city digital twin light-weight rendering system, computer equipment and a storage medium. Background The core of the lightweight rendering of the urban level digital twin is that the huge three-dimensional data is 'reduced in load' through various technical means on the premise of not influencing the core visual experience, so that the complex urban model can smoothly run on various devices such as webpages, mobile phones and even unmanned aerial vehicles. Implementation of this technique depends on a variety of background techniques, but also faces some inherent challenges; Digital twinned lightweight technologies can include level of detail (LOD) technologies, mixed geometry and gaussian splatter representations, data compression and automated face reduction, cloud rendering cluster services, etc., although the lightweight technologies aim to let models run on the mobile end, the scale of the city is almost infinite. Pure 3D gaussian splatter (3 DGS) techniques may require hundreds of millions of gaussian primitives and tens of GB of video memory to render a city. This is still an unacceptable weight for the computational power, memory and bandwidth of the mobile GPU. Disclosure of Invention In view of the foregoing, embodiments of the present invention have been made to provide an urban level digital twin lightweight rendering method, an urban level digital twin lightweight rendering system, a computer device, and a storage medium that overcome or at least partially solve the foregoing problems. In order to solve the problems, the embodiment of the invention discloses a city level digital twin lightweight rendering method, which comprises the following steps: acquiring multi-source heterogeneous data; Calculating rendering data corresponding to a first rendering channel and a second rendering channel of the multi-source heterogeneous data; extracting rendering multi-level parameters of the rendering data; establishing a visual rendering response surface model aiming at the rendering multi-level parameters to obtain a rendering response value; performing multi-objective optimization for the rendering response value to obtain rendering relation parameters; and when the model is loaded according to the rendering relation parameters, automatically reading a list corresponding to the rendering relation parameters, and carrying out parameterization configuration on geometry, texture and a shader to obtain the digital twin city model. Preferably, the multi-source heterogeneous data includes oblique photography model data, building information model data, geographic information system data, and laser point cloud data, and the calculating the rendering data corresponding to the first rendering channel and the second rendering channel of the multi-source heterogeneous data includes: converting the oblique photography model data, the building information model data, the geographic information system data and the laser point cloud data into reference signals; Inputting the reference signal to a first adaptive filter and a second adaptive filter to obtain a main noise source signal and a secondary noise source signal; the secondary noise source signal is subjected to error processing to obtain a processed secondary noise source signal; and performing adaptive weight filtering on the main noise source signal and the processed secondary noise source signal to obtain rendering data corresponding to the first rendering channel and the second rendering channel. Preferably, the extracting the rendering multi-level parameter of the rendering data includes: Extracting geometric layer parameters, texture layer parameters and shader layer parameters of the rendering data; And forming the geometric layer parameters, the texture layer parameters and the shader layer parameters into rendering multi-level parameters. Preferably, the establishing a visual rendering response surface model for the rendering multi-level parameter to obtain a rendering response value includes: establishing a visual rendering response surface model according to the Kriging approximate model; performing combined sampling on the rendering multi-level parameters, and acquiring initial response values under each group of parameters in a visual rendering response surface model; and performing sensitivity analysis through the initial response value to obtain a rendering response value. Preferably, the performing multi-objective optimization for the rendering response value to obtain a rendering relationship parameter includes: establishing a multi-objective optimization function according to the rendering multi-level parameters and the rendering response values; And solving the pareto optimal solution set on the multi-objective optimization function by adopting an NSGA-