42 results about "Marching cubes" patented technology

The present invention relates to the field of rock structure measurement, and disclosed are a three-dimensional pore reconstruction method and system based on a rock image, for use in solving the problem that using a machine learning method to reconstruct pores in a rock image requires relatively high mathematical or computer science expertise, involves high labor and economic costs, and is difficult to apply to small-scale rock pore reconstruction projects. The method comprises: step 1: grouping slice images of each rock sample into one set, and performing preprocessing; step 2: performing grayscale processing, histogram equalization and normalization processing on an image; step 3: using a Harris corner detection algorithm to perform corner detection, sorting Harris response values, selecting key points by setting the number of key points, and using a non-maximum suppression method to screen the selected key points; step 4: segmenting the boundaries of pores in the image by means of an adaptive threshold selection method, and extracting pore features; and step 5: using a marching cubes algorithm to construct a three-dimensional pore reconstruction model. The present invention is used for three-dimensional reconstruction of pores in a rock image.

The invention discloses an occlusion perception 3DGS and neural SDF semantic level hybrid reconstruction method, which comprises the following steps: image preprocessing: initially obtaining an image video frame through a camera, starting from image preprocessing, processing an input image, including semantic segmentation, depth estimation, normal estimation and internal and external parameter calibration, a corresponding semantic graph, a depth graph, a normal graph and camera parameters are generated; aligning the 3DGS with the neural SDF, after preprocessing is completed, performing spatial alignment on geometric information generated based on the 3DGS and a neural symbol distance function, and performing restoration in combination with regional densification and a hierarchical depth map; and finishing the final three-dimensional object modeling and rapid reconstruction by adopting a Marking Cubes algorithm. According to the occlusion perception 3DGS and neural SDF semantic level hybrid reconstruction method provided by the invention, each object in a scene can be quickly reconstructed with high quality, and applications such as downstream editing tasks, interaction and the like are supported at the same time.

The invention provides a three-dimensional reconstruction method, equipment and device, a medium and a product, and relates to the technical field of computer vision, and the method comprises the steps: constructing a spatial hash grid and a local symbol distance field SDF corresponding to a point cloud of a to-be-reconstructed map scene, and constructing a global SDF based on the local SDF; the local SDF is constructed based on geometric parameters and MLP parameters; collecting a plurality of sampling points from the spatial Hash grid, and determining a target local SDF corresponding to each sampling point; determining a predicted SDF value corresponding to each sampling point based on the geometric parameter and the MLP parameter of the target local SDF corresponding to each sampling point, and updating the geometric parameter and the MLP parameter based on the real SDF value and the predicted SDF value of each sampling point to obtain a target global SDF; and extracting a grid surface from the target global SDF based on a moving cube algorithm so as to perform three-dimensional reconstruction on the to-be-reconstructed map scene. According to the method, the three-dimensional reconstruction with expressive force and light weight is realized.

The invention discloses a three-dimensional visualization head and neck tumor preoperative imaging system based on deep learning. The method comprises the following steps: image analysis and preprocessing; carrying out image denoising and spatial-temporal feature extraction based on a deep learning convolutional neural network architecture, and introducing a u-Net model to realize image segmentation and semantic annotation; performing three-dimensional reconstruction and surface rendering by adopting a Marking Cubes algorithm, and realizing visual interaction image presentation and personalized operation by combining volume rendering and surface rendering; and data is output through multiple ports, and data viewing and interactive operation of a web terminal and a mobile terminal are supported. The method has the advantages that according to the technical scheme, through fusion of a three-dimensional attention mechanism and multi-phase data, the tumor segmentation Dice coefficient reaches 0.92 + / -0.03, and the method is superior to a traditional threshold segmentation method.

The invention discloses a CBCT (Cone Beam Computed Tomography) image distance determination method and device for maxillary sinus and maxillary posterior teeth, a medium and a product, and relates to the field of image processing, the method comprises the following steps: acquiring CBCT images of maxillary sinus and maxillary posterior teeth; according to the CBCT images of the maxillary sinus and the maxillary posterior teeth, performing three-dimensional segmentation of the maxillary sinus and the maxillary posterior teeth by adopting a structure segmentation model; the structure segmentation model is constructed based on a deep learning network; according to a three-dimensional segmentation result, generating a surface mesh model based on a marching cube algorithm; determining point cloud data based on a point cloud generation algorithm according to the surface mesh model; according to the point cloud data, the nearest distance between the maxillary sinus and the maxillary posterior teeth and the corresponding nearest apical point of the maxillary posterior teeth are determined; and determining the position relationship between the maxillary sinus and the maxillary posterior teeth according to the nearest distance, and classifying the position relationship. The distance between the maxillary sinus and the maxillary posterior tooth can be efficiently and accurately measured, and the position relation can be judged.

The invention discloses an ocean terrain digital display method based on three-dimensional modeling. The ocean terrain digital display method comprises the following steps of 1, constructing a multi-source ocean data set; 2, performing space fusion by adopting a self-adaptive interpolation method based on position weight to generate a three-dimensional space density field; 3, performing contour surface extraction by adopting an improved Marching Cubes algorithm to generate an initial three-dimensional terrain model; 4, performing local modeling by adopting a Delaunay triangulation network reconstruction method, and constructing a complete three-dimensional terrain model; 5, obtaining a texture terrain model; step 6, constructing an LOD tree structure and realizing dynamic loading in combination with view cone cutting and a screen space error control strategy; and step 7, based on a dynamic loading result of the LOD tree structure, driving node switching through a time controller, and performing visual display. According to the method, three-dimensional modeling and an LOD tree structure are fused, and high-precision reconstruction and evolution display of the ocean topography are achieved.

A physical property equivalent conversion method from a karst geologic model to a 3D printing physical model comprises the following steps that 1, overall data of an existing karst geologic model are finely analyzed, step length information is classified and arranged based on attributes of the karst geologic model, and point cloud data are exported; step 2, adopting a Deep Marking Cubes algorithm, carrying out three-dimensional reconstruction according to classification and size, and preliminarily obtaining a three-dimensional model; 3, the model is subjected to surface repairing, merging calculation, scaling, cutting, assembling and other operations, and an accurate 3D printing model is obtained; and 4, the'shell 'is filled based on the gravity factor filling model, and finally a 3D printing model of the karst geologic model is obtained. According to the karst geologic model 3D printing conversion method system based on gravity factor filling, the three-dimensional structure of oil reservoir geology is better represented, and the actual requirement of the model is better met.

The invention discloses a robot calibration method for spine endoscopic surgery, which comprises the following steps: S1, optical marking points are pasted on the skin or bony structure of a patient, the skin marking is used for fixing a reflective ball by using a medical adhesive tape, the bony marking is percutaneously implanted into a spinous process or crista iliaca through a titanium alloy bone nail, and at least six marking points are needed. According to the method, minimally invasive property and stability are both considered through a double marking strategy, six points cover three vertebral bodies to ensure the integrity of an anatomical range, registration errors caused by breathing / body position changes are reduced, meanwhile, non-rigid registration is combined with a B spline grid (10 mm) to consider calculation efficiency and spine physiological curvature adaptability, high-precision surface reconstruction is achieved through a Marching Cubes algorithm, and the method has the advantages of being high in precision and high in precision. An error suppression mechanism is formed by + / -0.25 mm precision and redundancy measurement (five times of sampling) of the optical tracking system, registration robustness is improved through SVD and ICP double-algorithm complementation, multi-constraint path planning is achieved through an A * algorithm and Monte Carlo simulation, and a 4 mm safety corridor provides a buffer space for instrument errors.

The invention provides a shadow perception satellite image nerve radiation field surface three-dimensional reconstruction method, which comprises the steps of optimizing an RPC model based on a multi-temporal satellite image, generating a sparse point cloud, and constructing a unified coordinate system through outer bounding sphere normalization; three-dimensional points are sampled in the pixel line-of-sight direction, and a training set is constructed; the SDF network predicts that spatial points have symbolic distance values, the color network integrates SDF features and sight line direction output colors, and the shadow color network combines the sun direction to generate shadow vectors; the light color is predicted through volume rendering integration, the shadow probability is calculated based on secondary ray casting in the sun direction, and a loss function is constructed in combination with an irradiance error to jointly optimize network parameters; and generating a three-dimensional grid by using sampling points of the trained SDF network in a unified coordinate system and adopting a Marching Cubes algorithm. According to the invention, the convergence stability of the neural radiation field model on satellite data and the success rate and precision of scene three-dimensional surface reconstruction can be improved.

The invention relates to the technical field of medical image processing and three-dimensional reconstruction, and particularly discloses a reconstruction and analogue simulation method based on a cardiac image. The method comprises the following steps: firstly, preprocessing an input CT or MRI medical image, and automatically segmenting a heart multi-tissue structure by using an nnUNetv2 model, including a plurality of anatomical regions such as atrium, ventricle, myocardial tissue and blood pool; and then performing topology repair, smoothing processing and label resampling on the segmentation result to obtain a three-dimensional label body with a continuous structure and a complete boundary. And based on the optimized tag body, constructing a heart three-dimensional surface model by adopting a Marching Cubes algorithm, and generating a multi-material volume grid suitable for finite element analysis. According to an electrode position and a radio frequency parameter set by a user, a radio frequency ablation simulation model based on a Pennes biological heat conduction equation and an Arrhenius model is established, a temperature field and a tissue thermal damage range are calculated, and a simulation result is displayed in a three-dimensional mode in an overlapping mode. According to the method, the integrated process from medical image automatic segmentation to heart three-dimensional reconstruction and thermal simulation is realized, the segmentation precision, the modeling efficiency and the simulation reliability are improved, and the method can be applied to application scenes such as surgical planning, preoperative evaluation and medical teaching.

The invention discloses a medical image-based auricle projection area measurement method and system, and belongs to the technical field of forensic medicine. According to the method, a head CT image sequence is subjected to three-dimensional reconstruction through an improved Marking Cubes algorithm to form a high-precision head three-dimensional model, an auricle region is further extracted through fine segmentation, auricle projection areas are automatically measured at all visual angles through a dynamic angle iterative algorithm, and finally the maximum projection area value is determined. The problems that traditional manual measurement is low in precision and poor in efficiency, and the precision is affected due to the fact that modeling holes are prone to occurring in handheld three-dimensional scanning equipment are solved. The method can be applied to forensic medicine auricle defect quantitative evaluation, and a high-precision and objective basis is provided for judicial expertise.

The present invention discloses a solid-liquid coupling simulation method with surface tension effect based on the material point method, belonging to the fields of computer graphics and physics-based simulation. The system used in the simulation method includes solid model modeling, fluid model modeling, Level Set implicit surface construction, Marching Cubes display surface construction, surface particle resampling, and collision detection. The system simulates fluids and solids on the basis of the material point method, constructs Level Set to resample fluid surface particles, and adds surface tension to the fluid using the CSF model. Different background grids are used to simulate fluids and solids respectively to solve the inherent adhesion phenomenon during MPM solid-liquid coupling and achieve the slip contact effect during solid-liquid coupling. Finally, the coupling phenomenon of incompressible fluid with surface tension effect and nonlinear elastic solid is realized.

The application discloses an analysis system and method based on first principle and quantum oscillation test, and the analysis system comprises a data input module, a preprocessing module, an operation module and an output module, wherein the operation module comprises an extreme value orbit visualization unit used for visualizing the position of an extreme value orbit in a Fermi surface, an extreme value curve visualization unit used for outputting a frequency change diagram of the corresponding extreme value orbit in a calculation process, and a Fermi surface selected area calculation unit used for effectively improving the calculation efficiency for a complex Fermi surface. The application can quickly and accurately screen and determine the quantum oscillation frequency and effective mass information of relevant materials based on the marching cubes, slice-to-slice orbit matching in SKEAF and hdbscan algorithm, and further determine the Fermi surface characteristics of the materials, which has important significance for the research on the electronic structure and physical properties of quantum materials.

The invention provides a complex tubular structure modeling method based on 2D segmented algebraic splines, and relates to the technical field of geometric modeling and computer graphics. The method comprises the following steps: firstly, constructing a section control polygon and generating a high-order algebraic spline primary function; calculating a Frenet frame corresponding to the guide curve, and mapping the section control polygon along the curve to generate a multi-section structure; and constructing an implicit field based on the parameters, and extracting contour surfaces by using a Marching Cubes algorithm to generate a triangular mesh model. The method is small in number of control points, high in structural continuity and suitable for efficient modeling and batch generation of complex tubular structures.

The application discloses a brain glioma segmentation and three-dimensional visualization model training method and system based on multi-modal fusion, and comprises the following steps: inputting multi-modal medical image data into a Laplacian pyramid multi-modal fusion learning model to generate a fusion graph, then inputting the fusion graph into a U-net segmentation model comprising an encoder and a decoder to obtain a segmentation mask under the multi-modal fusion graph; and finally, based on the multi-modal fusion graph and the segmentation mask, adopting a Marching cubes (MC) algorithm to perform three-dimensional reconstruction visualization of brain regions and brain tumor region labeling. The brain glioma segmentation and three-dimensional visualization model training method and system based on multi-modal fusion provided by the application optimizes the disadvantages of insufficient information and incomplete modeling under single modal, fully utilizes the advantages of the completeness of multi-modal data, performs multi-modal fusion, segmentation and three-dimensional visualization, can more comprehensively assist surgeons in treatment, and improves the accuracy in the operation process.

The invention relates to a medical image processing and three-dimensional reconstruction simulation system. The medical image processing and three-dimensional reconstruction simulation system comprises image loading, image processing, three-dimensional reconstruction, simulation analysis and multi-view display. The system loads various medical image formats, provides real-time display of axial, sagittal and coronal slices, extracts information of key parts by using an image segmentation strategy, generates a high-precision three-dimensional model based on a Marching Cubes algorithm, supports thermal and electrophysiology analysis, can automatically input physiological parameters, simulates heat distribution and current distribution of tissues, supports interactive adjustment, and is high in accuracy and high in accuracy. And a user can conveniently observe image details and analysis results. By using the system, the medical image processing efficiency and the three-dimensional reconstruction precision can be improved, meanwhile, the multi-dimensional analysis requirement of a complex anatomical structure is met through a simulation analysis function, and the system can be widely applied to medical diagnosis, surgical planning and medical teaching scenes.

The application discloses a kind of tropical cyclone temperature body structure calculation method and system, wherein the method includes: based on satellite microwave detection data and tropical cyclone position information, the three-dimensional temperature data of tropical cyclone area is smoothed, and temperature grid with tropical cyclone center as origin is formed.Three-dimensional temperature anomaly value is calculated according to the smoothed temperature grid.Based on three-dimensional temperature anomaly value, three-dimensional region growth method is used to extract tropical cyclone warm core main area.Based on the extracted tropical cyclone warm core main area, the isosurface is calculated using Marching Cubes algorithm.According to the isosurface, the light model is rendered to draw the three-dimensional visualization structure of tropical cyclone warm core.Based on the three-dimensional temperature anomaly value of tropical cyclone warm core main area, the tropical cyclone warm core intensity index is calculated.Thus, the application effectively solves the problem of insufficient overall understanding of tropical cyclone temperature structure in the prior art, and provides the ability of systematic quantitative analysis.

The invention relates to the technical field of tunnel face surrounding rock grading in railway construction, and provides a drilling and blasting method tunnel face surrounding rock three-dimensional refined grading method based on a seismic wave reflection method, which comprises the following steps: collecting three-dimensional inversion dot matrix data of an area in front of a tunnel face; the data coordinate system is converted into a tunnel design coordinate system, the surrounding rock basic quality index BQ value of each point is calculated according to the wave velocity, and a space BQ value dot matrix database is generated; performing spatial region division on the BQ value dot matrix by adopting a three-dimensional region self-growth method to obtain a connected region with similar BQ value characteristics; after the representative value of the region boundary is determined, using a Marking Cubes algorithm to extract contour surfaces to construct a surrounding rock three-dimensional grid model; and finally, mapping the model vertex BQ value with a preset grading standard, and outputting a three-dimensional refined grading model with a surrounding rock grading label. Automatic processing and three-dimensional visualization of surrounding rock classification are achieved, and classification accuracy and construction decision reliability are improved.

The invention discloses a non-rigid object three-dimensional reconstruction method based on a single-view neural radiation field, and the method comprises the steps: firstly inputting a single RGB image, extracting global features through a pre-trained deep learning backbone network, and generating a mask image of an object in combination with a semantic segmentation network; secondly, predicting volume density and color distribution by adopting a neural radiation field variant pixelNeRF, embedding a dynamic deformation field and a parameterized template to constrain shape rationality, and solving the problem of shape ambiguity in single-view reconstruction; thirdly, extracting a grid model through a Marking Cubes algorithm, complementing shielding and details by using a reconstruction algorithm, and enhancing the sense of reality of the surface by using a texture super-resolution technology; and finally, providing a user interaction interface for local optimization, and correcting a motion posture through a differentiable physical engine to generate a drivable three-dimensional animation model. By combining the single-view neural radiation field and the dynamic deformation modeling technology, the method has the advantages of high precision, high efficiency, support of interactive editing, capability of generating driving animations and the like.

The application discloses a multi-radar power envelope fusion method, comprising: single-radar envelope modeling, constructing envelope fusion foundation; determining non-coherent field fusion, constructing multi-radar envelope model; constructing gradient diffusion model, realizing envelope fusion smooth transition; displaying Euler method iteration convergence, realizing multi-radar envelope complete fusion; adopting adaptive octree structure to dynamically divide three-dimensional space. Advantageous effects: the multi-radar power envelope fusion method firstly calculates single-station detection probability of each radar unit at a grid point in a three-dimensional space voxel according to a radar equation, a propagation loss model and target scattering characteristics; then adopts a probability union or a more complex dependent relationship model to generate a full-space joint detection probability field; finally, an isosurface extraction (such as an improved Marching Cubes algorithm) and a probability gradient driven color / transparency mapping are adopted to generate a visual continuous, mathematically accurate fusion envelope surface.

The present invention discloses a three-dimensional structure interactive topology optimization method based on level set, which relates to the technical fields of computer-aided design, topology optimization, and interactive design. The method includes establishing a three-dimensional structure topology optimization design region; importing the level set field of the initial structure or a three-dimensional model file and generating an initial level set field; extracting a geometric structure from the level set field by using the Marching Cubes method, rendering and displaying the initial model; performing level set topology optimization on the structure, updating and real-time rendering and displaying the structure form; during the optimization process, the process can be paused at any time for interactive modification, and forced or non-forced intervention methods are adopted to increase or decrease the structure or refine the form through an interactive sphere, and the level set field is updated in real time to continue the optimization. Therefore, by adopting the above method, the topology optimization of complex initial models can be efficiently realized, the structure form can be dynamically adjusted, the cumbersome post-processing steps of traditional methods can be effectively reduced, and the structure design efficiency, accuracy, and flexibility are improved.

This invention discloses a method and system for constructing a mesh model based on the spatial parameters of a 3D Gaussian surface model, belonging to the field of 3D reconstruction technology. It includes at least the following steps: establishing an initial 3D Gaussian elliptical surface model based on the sparse point cloud of the reconstructed object; constructing a local implicit function field for each Gaussian elliptical surface model; for a single Gaussian elliptical surface model, the implicit function value of a vertex is the signed distance from the voxel vertex to the corresponding Gaussian elliptical surface; performing global weighted fusion based on the local implicit function field of the current Gaussian elliptical surface model; and extracting 0-isosurfaces using the Marching Cubes algorithm based on the vertex function values ​​of the global voxel field, thereby constructing the mesh model of the reconstructed object. This invention establishes a voxel field consistent with the distribution of the 3D Gaussian elliptical surface through the 3D spatial parameters of the 3D Gaussian elliptical surface model, enabling accurate and unobstructed surface representation and achieving high-precision 3D reconstruction of the mesh model.

The application provides a shadow-aware satellite image neural radiance field ground surface three-dimensional reconstruction method, comprising: optimizing an RPC model based on multi-temporal satellite images and generating a sparse point cloud, and constructing a unified coordinate system through an outer enclosing sphere normalization; sampling three-dimensional points along a pixel line-of-sight direction and constructing a training set; an SDF network predicts a signed distance value of a spatial point, a color network fuses SDF features and a line-of-sight direction to output color, and a shadow color network generates a shadow vector in combination with a sun direction; a ray color is predicted through volume rendering integration, a shadow probability is calculated based on twice ray casting of the sun direction, a loss function is constructed in combination with an irradiance error to jointly optimize network parameters; and a three-dimensional grid is generated by using a Marching Cubes algorithm after sampling points in the unified coordinate system by using the trained SDF network. The application can improve the convergence stability of a neural radiance field model on satellite data and the success rate and precision of scene three-dimensional surface reconstruction.

Disclosed herein are an apparatus and method for compressing 3D volume data. The apparatus for compressing three-dimensional (3D) volume data includes one or more processor, and execution memory configured to store at least one program that is executed by the one or more processors, wherein the at least one program is configured to receive 3D volume data for data compression, select necessary voxels that contribute to formation of a geometric surface from the 3D volume data using a marching cubes algorithm, represent location information of the selected necessary voxels by a tree structure, and binarize the location information of the necessary voxels by serializing the tree structure, and quantize truncated signed distance values to surfaces adjacent to the necessary voxels constituting a volume from the 3D volume data using the binarized location information of the necessary voxels.

The invention relates to the technical field of tunnel advanced geological forecast, and discloses a railway tunnel construction tunnel face front surrounding rock water abundance three-dimensional model construction method comprising the following steps: collecting a plurality of transient electromagnetic survey lines in a tunnel face direction, and uniformly mapping two-dimensional inversion results to a right-handed coordinate system according to survey line angles, mileages and survey point distances; and constructing a spatial water-rich database. After geometric parameters of the tunnel face are obtained, a three-dimensional cube grid is established, and apparent resistivity values are given to nodes. A kd tree is constructed based on node distribution, a normal vector and curvature are calculated, and a mark array is initialized. And completing node clustering by adopting a three-dimensional region self-growth algorithm in combination with attribute difference, a region threshold and curvature constraint to form a water-rich region. And a binary volume data field is constructed for each clustering region, contour surfaces are extracted by using Marching Cubes, and a surrounding rock water yield three-dimensional model is generated. According to the method, high-precision three-dimensional modeling of the water-rich area in front of the tunnel face is effectively constructed, and the accuracy of advanced prediction of the tunnel is remarkably improved.

The invention discloses a multi-radar power envelope fusion method, which comprises the steps of performing single-radar envelope modeling, and constructing an envelope fusion foundation; incoherent field fusion is determined, and a multi-radar envelope model is constructed; constructing a gradient diffusion model to realize envelope fusion smooth transition; euler method iterative convergence is displayed, and multi-radar envelope complete fusion is realized; and dynamically dividing a three-dimensional space by adopting a self-adaptive octree structure. The multi-radar power envelope fusion method has the beneficial effects that firstly, according to a radar equation, a propagation loss model and target scattering characteristics, the single-station detection probability of each radar unit at a grid point is calculated in a three-dimensional space voxelization mode; a probability union set or a more complex dependency relationship model is adopted, and a total-space joint detection probability field is generated through fusion; finally, through contour surface extraction (such as an improved March i ng Cubes algorithm) and color / transparency mapping driven by probability gradient, a fusion envelope curved surface with continuous vision and accurate mathematics is generated.

This invention discloses a three-dimensional thermal environment neural field reconstruction method and system for diagnosing building facade defects, belonging to the field of building energy conservation technology. It includes: simultaneously acquiring multi-view image data using an integrated thermal infrared and visible light dual-modal device; achieving cross-modal camera pose calibration using an improved Structure for Motion Restoration (SfM) algorithm; constructing an implicit thermal radiation model using neural radiation fields (NeRF) to introduce temperature information and enhance thermal environment characterization; and generating an explicit triangular mesh model with both geometric details and thermal properties using the signed distance function (SDF) and Marching Cubes algorithm. The invention's multi-modal neural radiation field fusion framework complements thermal infrared and visible light data to achieve three-dimensional thermal environment reconstruction. This method can be widely applied to building facade safety diagnosis, energy-saving renovation, and low-carbon operation and maintenance.

The invention discloses a three-dimensional thermal environment neural field reconstruction method and system for building facade defect diagnosis, and belongs to the technical field of building energy saving. The method comprises the following steps: synchronously acquiring multi-view image data through an integrated thermal infrared and visible light bimodal device, and realizing cross-modal camera pose calibration by using an improved motion recovery structure (SfM) algorithm; the method comprises the following steps: constructing a thermal radiation implicit model by using a neural radiation field (NeRF), introducing temperature information to enhance thermal environment representation, and generating an explicit triangular mesh model with both geometric details and thermophysical properties through a signed distance function (SDF) and a Marching Cubes algorithm; according to the multi-mode neural radiation field fusion framework, thermal infrared data and visible light data are complementary, and thermal environment three-dimensional reconstruction is achieved. The method can be widely applied to safety diagnosis, energy-saving transformation and low-carbon operation and maintenance of building facades.

The invention belongs to the technical field of three-dimensional modeling, and particularly relates to an unsupervised non-watertight point cloud high-fidelity reconstruction method. Aiming at the problems of inconsistent gradient directions, local detail loss, artifact fragmentation and the like in open surfaces, non-watertight point clouds and complex geometric scenes in the existing method, the invention provides a normalization and density adaptive resampling mechanism; symmetric point pairs are generated through local normal estimation, and prior constraints with consistent UDF values and opposite gradients are applied; designing a multi-scale Gabor code with spatial locality and direction selectivity, and combining the combined feature input of a symmetric invariant base and a symmetric variant base; gradually converging from global topology to local details by adopting progressive multi-scale sampling and composite unsupervised loss function optimization; and a UDF curved surface extraction method based on gradient discrimination and improved Marking Cubes is provided.

The present invention belongs to the technical field of semiconductor manufacturing, and provides a method, device, equipment and storage medium for determining semiconductor photolithography evolution. The method of the present invention includes: determining a calculation region for simulating photolithography development according to input parameters of a photoresist region and a mask region of a 3D semiconductor device structure, and determining an initial value of a level set equation; determining an evolution speed of the photoresist surface based on the input parameters; obtaining a discrete format of the level set equation; solving the discrete format of the level set equation based on the initial value of the level set equation and the evolution speed to obtain a three-dimensional discrete data field in the calculation region; and using the marching cubes method to extract a photolithography development surface region when the simulation time is reached. The present invention solves the problem that it is currently necessary to invest in actual production to determine the development status by introducing a level set equation to simulate and determine the evolution surface after the photolithography development reaches the simulation time, which is convenient for the subsequent development of the photolithography process.