CN119535779B - Construction method of structure light diffuse reflection pattern simulation model in space frequency domain imaging - Google Patents
Construction method of structure light diffuse reflection pattern simulation model in space frequency domain imaging Download PDFInfo
- Publication number
- CN119535779B CN119535779B CN202510108082.XA CN202510108082A CN119535779B CN 119535779 B CN119535779 B CN 119535779B CN 202510108082 A CN202510108082 A CN 202510108082A CN 119535779 B CN119535779 B CN 119535779B
- Authority
- CN
- China
- Prior art keywords
- sample
- pattern
- diffuse reflection
- pcbc
- spatial frequency
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G02—OPTICS
- G02B—OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G02B27/00—Optical systems or apparatus not provided for by any of the groups G02B1/00 - G02B26/00, G02B30/00
- G02B27/0012—Optical design, e.g. procedures, algorithms, optimisation routines
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Optics & Photonics (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
本发明涉及仿真模型的构建方法技术领域，具体公开了空间频域成像中结构光漫反射图案仿真模型的构建方法，具体包括以下步骤：步骤1，使用Farrell和Patterson描述的部分电流边界条件（PCBC）公式计算样品的任意漫反射图案分布；步骤2，在空间频域成像（SFDI）中，计算在条纹空间频率下基于光学特性的漫反射系数；本发明中，分析了PCBC和SFDI在模拟空间频域成像中漫反射图案的优缺点，并通过理论计算将二者进行融合，提出了一个新的可以大视场、高精度、实时模拟条纹漫反射图案的方法，并且结合CNN实现了在样本光学特性波动大、高度波动大、离焦程度不同等情况下，仍可以根据1‑Bit实验很好的预测对应8‑Bit结果。
The present invention relates to the technical field of simulation model construction methods, and specifically discloses a method for constructing a structured light diffuse reflection pattern simulation model in spatial frequency domain imaging, which specifically includes the following steps: step 1, using the partial current boundary condition (PCBC) formula described by Farrell and Patterson to calculate the distribution of any diffuse reflection pattern of the sample; step 2, in spatial frequency domain imaging (SFDI), calculating the distribution of the fringe spatial frequency Diffuse reflectance based on optical properties In the present invention, the advantages and disadvantages of PCBC and SFDI in simulating diffuse reflection patterns in spatial frequency domain imaging are analyzed, and the two are integrated through theoretical calculations. A new method for simulating stripe diffuse reflection patterns with large field of view, high precision and real-time is proposed, and combined with CNN, it is realized that when the sample optical properties fluctuate greatly, the height fluctuates greatly, the defocus degree is different, etc., the corresponding 8-Bit result can still be well predicted based on the 1-Bit experiment.
Description
Technical Field
The invention relates to the technical field of simulation model construction methods, in particular to a method for constructing a structured light diffuse reflection pattern simulation model in space frequency domain imaging.
Background
The Spatial Frequency Domain Imaging (SFDI) technology is used as an optical detection method of the tip, and the basic principle is rooted in Monte Carlo simulation or Diffusion Approximation (DA) theory. This technique uses spatially modulated light projections to quantitatively analyze the optical properties of the sample, including absorption and lowering scattering coefficients. SFDI has been widely used as a label-free and non-contact detection method to quantify the optical properties of strongly scattering media such as biological tissue. Although the imaging accuracy and precision of SFDI has been verified by numerous studies, the conventional three-phase demodulation method requires that the sample remain stationary while three phase-shifted images are acquired for demodulation calculations to avoid introducing artifacts, thereby limiting its application in real-time on-line detection.
In order to increase the detection speed and thus its applicability in real-time monitoring, researchers in the prior art explored two-phase and single-phase demodulation methods aimed at improving imaging efficiency by reducing the number of required phase images. Furthermore, single-shot imaging techniques aim to extract more information from a single projection pattern, thereby reducing the number of required patterns and increasing the imaging speed, while maintaining as much integrity of the sample information as possible. In projection technology, imaging speeds in the kilohertz range are achieved by using halftone (1-Bit) techniques. Compared with the traditional continuous tone (8-Bit) SFDI, the 1-Bit SFDI adopts a 1-Bit digital light mode (binary stripe), so that the projection processing data volume is obviously reduced, the projection speed is greatly improved, and high-speed imaging is realized. This technique can increase the projection speed of SFDI by about two orders of magnitude.
Although halftone SFDI technology has made significant progress in processing speed, deep penetration of underlying mechanism studies and theoretical model construction is still necessary. Particularly in the inversion process of optical characteristics, it is currently difficult to directly provide an analytical solution for reducing the scattering coefficient and the absorption coefficient due to the computational complexity of SFDI.
Disclosure of Invention
Aiming at the technical problems in the background technology, the invention provides a method for constructing a structural light diffuse reflection pattern simulation model in space frequency domain imaging.
The technical scheme adopted by the invention is that the construction method of the structural light diffuse reflection pattern simulation model in the space frequency domain imaging specifically comprises the following steps:
Step 1, calculating any diffuse reflection distribution condition of a sample by using a Partial Current Boundary Condition (PCBC) formula described by Farrell and Patterson;
Step 2, in Spatial Frequency Domain Imaging (SFDI), at fringe spatial frequencies Diffuse reflection coefficient based on optical characteristicsThe calculation formula is as follows:
,
In the formula, Is the effective attenuation coefficient of the light source,Is the extinction coefficient of the light-emitting diode,Is a parameter of the internal reflection and,For the diffuse reflectance of the sample,Is the transmission albedo;
step3, simulating the diffuse reflection pattern, calculating and establishing a PCBC-SFD fusion model;
step 4, predicting the sample parameter wavelength lambda and absorption coefficient of the diffuse reflection pattern Coefficient of reduced scatteringInputting a PCBC-SFD fusion model to obtain a diffuse reflection simulation result corresponding to the projection pattern;
step 5, the upper computer generates 5 pictures, including a full black picture, a full white picture, and three fringe patterns with different initial phases alpha at the selected spatial frequency f x, wherein alpha is respectively ;
Step 6, generating a continuous 8-Bit fringe pattern into a corresponding 1-Bit halftone fringe pattern by using an error diffusion method or a halftone fringe generation method, and controlling a projector to project the fringe pattern to a sample by an upper computer;
and 7, synchronously collecting the reflected light intensity distribution of the sample in the stripe pattern illumination mode by using the CCD camera, and storing image data.
The invention is further configured that, in step 1, the diffuse reflection distribution condition of the sample is calculated by using Partial Current Boundary Condition (PCBC) formulas described by Farrell and Patterson, which is specifically as follows:
,
,
Where r is the radial distance to the light source, Is the distance to the light source and,Is the distance to the image source and,Is the effective attenuation coefficient of the light source,Is a reduced scattering coefficient;
,,,,、、 Is a parameter of the internal reflection and, Is a parameter related to the refractive index of the tissue,And (2) andIs the transmission of the albedo,For reflectivity at a distance r from the light source,For the diffuse reflectance of the sample,Is the extinction coefficient.
The invention is further arranged that in the step 3, the PCBC-SFD fusion model calculation process is as follows:
First, the calculation formula of the light intensity distribution of the projection pattern is as follows, Is the amplitude envelope of the dc component,Is the amplitude envelope of the alternating current component,The intensity distribution of the pattern is corresponding to the three phases, and the calculation formula is as follows:
,
,
the diffuse reflectance of the sample is determined by the ratio to standard reflector ,
For two different samples, the corresponding relation between the two samples can be established
,,,
Assignment:,
The light intensity distribution of the projection, standard panel, sample can be expressed as:
,
,
,
Obtaining the light intensity distribution of the diffuse reflection pattern of the sample and the sample , And the relationship between standard plate and projected pattern intensity is as follows:
,
the intensity of the projected stripe is expressed as 0.5+0.5cos (x), so the value of a is typically set to 0.5,
,
Thus, calculate the sampleThe PCBC-SFD fusion model of the actual light intensity distribution of (a) is as follows,To calculate the diffuse reflectance of the ac component at the projected fringe patch at spatial frequency k using SFDI,The calculated pattern for the PCBC is then,To calculate the diffuse reflectance of the dc component represented at frequency 0 using SFDI,Diffuse reflectance for standard white board:
。
The invention has the beneficial effects that the advantages of the diffuse reflection patterns of PCBC and SFDI in the simulated space frequency domain imaging are analyzed, the PCBC and SFDI are fused through theoretical calculation, a novel method which can simulate the stripe diffuse reflection patterns in large view field, high precision and real time is provided, and the method can still well predict the corresponding 8-Bit result according to the 1-Bit experiment under the conditions of large sample optical characteristic fluctuation, large height fluctuation, different defocusing degree and the like by combining with CNN. The method is beneficial to the on-line detection in the subsequent practical industry.
Drawings
FIG. 1 is a schematic flow chart of one embodiment of the present invention.
FIG. 2 is a schematic diagram of the experimental setup and experimental materials of the invention.
Fig. 3 is a schematic diagram of a model-proposed process of the present invention.
Fig. 4 is a schematic diagram of the convolutional neural network structure of the present invention.
FIG. 5 is a schematic representation of the present invention for predicting continuous tone results from halftone patterns using convolutional neural networks.
Detailed Description
The technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order to solve the problems in the background technology, the application provides a method for constructing a structural light diffuse reflection pattern simulation model in space frequency domain imaging, which specifically comprises the following steps:
Step 1, calculating any diffuse reflection distribution condition of a sample by using a Partial Current Boundary Condition (PCBC) formula described by Farrell and Patterson;
The Partial Current Boundary Condition (PCBC) described by Farrell and Patterson can provide a diffuse reflection transmission simulation result more accurately, and is widely applied to various light transmission simulation experiments, so that the diffuse reflection distribution of a sample is calculated by using a PCBC formula proposed by the two persons.
In step 1, the diffuse reflection distribution of the sample is calculated by using a Partial Current Boundary Condition (PCBC) formula described by Farrell and Patterson, which is specifically as follows:
,
,
Where r is the radial distance to the light source, Is the distance to the light source and,Is the distance to the image source and,Is the effective attenuation coefficient of the light source,Is a reduced scattering coefficient;
,,,,,, Is a parameter of the internal reflection and, Is a parameter related to the refractive index of the tissue,And (2) andIs the transmission of the albedo,For reflectivity at a distance r from the light source,For the diffuse reflectance of the sample,Is the extinction coefficient.
Step 2, in Spatial Frequency Domain Imaging (SFDI), at fringe spatial frequenciesDiffuse reflection coefficient based on optical characteristicsThe calculation formula is as follows:
,
In the formula, Is the effective attenuation coefficient of the light source,Is the extinction coefficient of the light-emitting diode,Is a parameter of the internal reflection and,For the diffuse reflectance of the sample,Is the transmission albedo;
step3, simulating the diffuse reflection pattern, calculating and establishing a PCBC-SFD fusion model;
The SFDI formula can calculate the diffuse reflectance of the sample very accurately, but cannot give the distribution of the light source projection of one pixel point into the medium. The PCBC can give a solution about the radial distance of the light source, but when the radial distance is too small, a larger error exists, so that the predicted intensity of the halftone stripe pattern is in error in space frequency domain imaging.
First, the calculation formula of the light intensity distribution of the projection pattern is as follows,Is the amplitude envelope of the dc component,Is the amplitude envelope of the alternating current component,The intensity distribution of the pattern is corresponding to the three phases, and the calculation formula is as follows:
,
,
the diffuse reflectance of the sample is determined by the ratio to standard reflector ,
For two different samples, the corresponding relation between the two samples can be established
,
,
,
Assignment:,
The light intensity distribution of the projection, standard panel, sample can be expressed as:
,
,
,
Obtaining the light intensity distribution of the diffuse reflection pattern of the sample and the sample , And the relationship between standard plate and projected pattern intensity is as follows:
,
the intensity of the projected stripe is expressed as 0.5+0.5cos (x), so the value of a is typically set to 0.5,
,
Thus, calculate the sampleThe PCBC-SFD fusion model of the actual light intensity distribution of (a) is as follows,To calculate the diffuse reflectance of the ac component at the projected fringe patch at spatial frequency k using SFDI,The calculated pattern for the PCBC is then,To calculate the diffuse reflectance of the dc component represented at frequency 0 using SFDI,Diffuse reflectance for standard white board:
。
step 4, predicting the sample parameter wavelength lambda and absorption coefficient of the diffuse reflection pattern Coefficient of reduced scatteringInputting a PCBC-SFD fusion model to obtain a diffuse reflection simulation result corresponding to the projection pattern;
step 5, the upper computer generates 5 pictures, including a full black picture, a full white picture, and three fringe patterns with different initial phases alpha at the selected spatial frequency f x, wherein alpha is respectively ;
Step 6, generating a continuous 8-Bit fringe pattern into a corresponding 1-Bit halftone fringe pattern by using an error diffusion method or a halftone fringe generation method, and controlling a projector to project the fringe pattern to a sample by an upper computer;
and 7, synchronously collecting the reflected light intensity distribution of the sample in the stripe pattern illumination mode by using the CCD camera, and storing image data.
Experimental example 1:
As shown in fig. 1. In this example, using gypsum sculpture and polytetrafluoroethylene balls and fat emulsion solutions of different concentrations, as shown in fig. 2, samples of different optical properties were prepared by mixing distilled water with the fat emulsion solutions to prepare fat emulsion solutions of different volume concentrations, comprising the steps of:
Step1, generating continuous tone projection stripes;
Step 2, generating corresponding halftone stripes by using an error diffusion method according to the generated continuous tone stripes;
step 3, inputting the absorption and reduced scattering coefficients of the medium to be simulated into a PCBC-SFD fusion model to obtain a simulation result of the diffuse reflection pattern, as shown in figure 3;
And 4, providing a reference for setting experiments according to simulation results.
Experimental example 2:
Comprises the steps of,
Step 1, obtaining a large amount of theoretical data by respectively combining halftones and corresponding continuous tone stripes thereof and inputting different absorption and reduced scattering coefficients into PCBC-SFD;
Step 2, constructing a convolutional neural network architecture and training by using the generated theoretical data as a data set to obtain a model for predicting continuous tone experimental results according to halftone data, as shown in fig. 4;
step 3, the upper computer controls the projector to project a fringe pattern on the sample, and the CCD camera synchronously collects the reflected light intensity distribution of the sample in a fringe pattern illumination mode and stores image data;
and 4, inputting the acquired halftone pattern into a trained network to obtain a prediction result of a corresponding continuous tone experiment, as shown in fig. 5.
As another embodiment, the present embodiment provides another technical solution:
in particular comprising the following steps of the method,
Step 1, inputting data of 1-Bit and 8-Bit projection patterns and samples with different absorption and reduced scattering coefficients into a PCBC-SFD fusion model, and obtaining corresponding simulated diffuse reflection images under 1-Bit and 8-Bit projections of samples with different optical characteristics through simulation;
And 2, establishing a CNN network, inputting the 1-Bit generated by PCBC-SFD and the corresponding 8-Bit pattern data set for training, and obtaining the corresponding relation between the 1-Bit and the corresponding 8-Bit pattern data set. The network architecture of CNN is specifically designed to start with a single channel input layer, of size 1080 x 1920 pixels, using a convolutional layer with a3 x 3 kernel and a ReLU activation function to extract and refine the features of the binary input. This configuration introduces nonlinearity and helps prevent gradient extinction during training. Subsequent MaxPooling D operations reduce the dimension of the feature map, enhancing the generalization capability of the network. To capture the wider patterns, a convolution layer with 11 x 11 kernels was introduced. The UpSampling D layer combines additional convolutions to enlarge the feature map to reconstruct the 8-bit pattern. The network ends with a final convolutional layer that uses a sigmoid activation function to normalize the pixel values between 0 and1, effectively modeling an 8-bit pattern;
step 3, projecting 1-Bit and 8-Bit patterns, synchronously collecting reflected light intensity distribution of a sample in a stripe pattern illumination mode by a CCD camera, and storing image data;
Step 4, inputting 1-Bit experimental data and obtaining a corresponding 8-Bit pattern prediction result by using a CNN network;
The embodiment analyzes the advantages and disadvantages of the diffuse reflection patterns of PCBC and SFDI in the simulated space frequency domain imaging, fuses the PCBC and SFDI through theoretical calculation, provides a novel method capable of simulating the diffuse reflection patterns of stripes in a large view field and high precision in real time, and combines CNN to realize that under the conditions of large fluctuation of the optical characteristics of a sample, large fluctuation of the height, different defocus degrees and the like, the corresponding 8-Bit result can be well predicted according to a 1-Bit experiment. The method is beneficial to the on-line detection in the subsequent practical industry.
Although embodiments of the present invention have been shown and described, it will be obvious to those skilled in the art that the scope of the present invention is defined by the appended claims and equivalents thereof.
Claims (2)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510108082.XA CN119535779B (en) | 2025-01-23 | 2025-01-23 | Construction method of structure light diffuse reflection pattern simulation model in space frequency domain imaging |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510108082.XA CN119535779B (en) | 2025-01-23 | 2025-01-23 | Construction method of structure light diffuse reflection pattern simulation model in space frequency domain imaging |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119535779A CN119535779A (en) | 2025-02-28 |
| CN119535779B true CN119535779B (en) | 2025-05-06 |
Family
ID=94704051
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510108082.XA Active CN119535779B (en) | 2025-01-23 | 2025-01-23 | Construction method of structure light diffuse reflection pattern simulation model in space frequency domain imaging |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119535779B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016085934A1 (en) * | 2014-11-24 | 2016-06-02 | Children's Medical Center Corporation | Modulation of sh2b3 to improve red blood cell production from stem cells and/or progenitor cells |
| CN115294095A (en) * | 2022-08-24 | 2022-11-04 | 浙江农林大学 | Nondestructive testing method for subcutaneous recessive damage of peaches |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7525661B2 (en) * | 2004-02-17 | 2009-04-28 | Andreas Mandelis | Laser photo-thermo-acoustic (PTA) frequency swept heterodyned lock-in depth profilometry imaging system |
| EP2223650A1 (en) * | 2009-02-25 | 2010-09-01 | The Provost, Fellows and Scholars of the College of the Holy and Undivided Trinity of Queen Elizabeth near Dublin | Method and apparatus for imaging tissue topography |
| CN104093830A (en) * | 2011-04-15 | 2014-10-08 | 吉恩勒克斯公司 | Cloned strains of attenuated vaccinia virus and methods of use thereof |
| US20140194749A1 (en) * | 2013-01-08 | 2014-07-10 | Bar-Ilan University | Method and System for Detection of Cancer |
| WO2023108024A1 (en) * | 2021-12-10 | 2023-06-15 | Alfred E. Mann Institute For Biomedical Engineering At The University Of Southern California | Systems and methods for optical imaging of subsurface structures of a target |
| CN115524311B (en) * | 2022-09-23 | 2025-07-25 | 哈尔滨理工大学 | Surface diffuse reflectance and three-dimensional morphology integrated imaging method based on inclined stripe pattern |
| CN116499995A (en) * | 2023-04-11 | 2023-07-28 | 浙江农林大学 | A Corrected Measurement Method for Diffuse Reflectance of Spherical Fruit Surface in Spatial Frequency Domain Imaging |
| CN118032717A (en) * | 2024-02-05 | 2024-05-14 | 浙江农林大学 | Alternating current-direct current component mutual correction method for diffuse reflectance of fruit surface in space frequency domain imaging |
-
2025
- 2025-01-23 CN CN202510108082.XA patent/CN119535779B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016085934A1 (en) * | 2014-11-24 | 2016-06-02 | Children's Medical Center Corporation | Modulation of sh2b3 to improve red blood cell production from stem cells and/or progenitor cells |
| CN115294095A (en) * | 2022-08-24 | 2022-11-04 | 浙江农林大学 | Nondestructive testing method for subcutaneous recessive damage of peaches |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119535779A (en) | 2025-02-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115493479B (en) | Three-dimensional display system using electromagnetic field calculation | |
| CN109389639B (en) | Method and device for extracting laser stripe center of rail profile under dynamic driving environment | |
| US7301538B2 (en) | Method and system for adaptive direct volume rendering | |
| CN106056658A (en) | A virtual object rendering method and device | |
| JPH0844867A (en) | Method and apparatus for modifying original image | |
| WO2010094713A1 (en) | Rendering caustics in computer graphics with photon mapping by relaxation | |
| CN117011478B (en) | Single image reconstruction method based on deep learning and stripe projection profilometry | |
| Zheng et al. | Neural relightable participating media rendering | |
| CN114638749A (en) | Low-illumination image enhancement model, method, electronic device and storage medium | |
| Sun et al. | SOL-NeRF: Sunlight modeling for outdoor scene decomposition and relighting | |
| CN119535779B (en) | Construction method of structure light diffuse reflection pattern simulation model in space frequency domain imaging | |
| Shen et al. | Scratch-based Reflection Art via Differentiable Rendering. | |
| Jia et al. | AdaptiveStereo: Depth estimation from adaptive structured light | |
| Ritschel et al. | Interactive reflection editing | |
| CN115859422A (en) | A bridge BIM reverse modeling method, system and device driven by primitive library | |
| CN115984952B (en) | Eye movement tracking system and method based on bulbar conjunctiva blood vessel image recognition | |
| Zhu et al. | Spatial–temporal binarization method via jointly optimizing diffusion kernel and quantization threshold for 3-d surface imaging | |
| Guo et al. | A new rendering algorithm based on multi-space for living soft tissue | |
| Zhu et al. | Three-dimensional measurement of fringe projection based on the camera response function of the quantified exposure time | |
| Mullia et al. | Rna: Relightable neural assets | |
| Phan et al. | Differentiable rendering for 3-dimensional reconstruction of laser-induced tissue ablation | |
| CN117456135B (en) | Real-time 3D model and live-action fusion system based on smart phone camera | |
| CN120070762B (en) | High-efficiency three-dimensional animation production method based on artificial intelligence | |
| CN117292038B (en) | Rendering method, system, equipment and storage medium for sea surface model | |
| CN118135037B (en) | A ceramic color detection method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |