Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

91results about How to "Improve rebuild efficiency" patented technology

Method for accelerating high-quality MRI (Magnetic Resonance Imaging) image reconstruction based on TC-KANReccon model

The invention relates to an accelerated high-quality MRI (Magnetic Resonance Imaging) image reconstruction method based on a TC-KANReccon model. The method comprises the following steps: S1, collecting and preprocessing image data; s2, an accelerated high-quality MRI image reconstruction model based on a TC-KANReccon model is built; and S3, designing a noise cutting strategy of linear reduction of the cutting threshold. In each step of the sampling process, a linear decreasing cutting strategy is adopted according to the current progress of the sampling step. The strategy is applied to noise estimation generated by an MF-UKAN diffusion trunk so as to generate an MRI image with a better visual effect; s4, repeatedly training a diffusion model and a VAE module by taking the preprocessed MRI image and the full-sampling k-space data as input, optimizing network parameters, and continuously performing iterative optimization; and S5, inputting the under-sampled k-space data into the trained accelerated high-quality MRI image reconstruction model based on the TC-KANReccon model, and applying a matched noise cutting strategy of linear reduction of a cutting threshold to finally generate a high-quality MRI image.
Owner:HANGZHOU DIANZI UNIV

Fast magnetic resonance reconstruction method and system based on multistage wavelet convolutional network

The invention provides a fast magnetic resonance reconstruction method and system based on a multistage wavelet convolution network, and particularly relates to the technical field of magnetic resonance imaging and image reconstruction, and the scheme comprises the steps: collecting multi-channel under-sampling K space data; inverse Fourier transform is carried out on the multi-channel under-sampling K space data to obtain an under-sampling magnetic resonance image; and inputting the undersampled magnetic resonance image into a trained multi-stage wavelet convolutional network for reconstruction to obtain a reconstructed magnetic resonance image, the multi-stage wavelet convolutional network being constructed based on multi-stage wavelet transform and a convolutional neural network. According to the scheme, the magnetic resonance K space data is collected in an undersampling mode, the scanning time can be shortened, the multi-stage wavelet convolution network can effectively reserve high-frequency details of the image in the reconstruction process, and therefore the reconstruction quality and efficiency of the multi-channel magnetic resonance image can be remarkably improved on the whole.
Owner:SHENZHEN ANKE HIGH TECH CO LTD

Three-dimensional scene reconstruction method and device

The invention discloses a three-dimensional scene reconstruction method and device, and belongs to the field of computer vision and image processing. The method comprises: determining spatial geometric information of a shooting scene according to M two-dimensional images, the M two-dimensional images being images of the shooting scene at different shooting angles, the spatial geometric information at least comprising: at least one target spatial point and at least one spatial line segment, M being an integer greater than 1; and according to the spatial geometric information, a three-dimensional Gaussian ellipsoid set is generated, and the three-dimensional Gaussian ellipsoid set comprises at least one three-dimensional Gaussian ellipsoid used for representing three-dimensional scene information of the shooting scene.
Owner:VIVO MOBILE COMM CO LTD

Object three-dimensional reconstruction method and device based on deep learning

The invention discloses an object three-dimensional reconstruction method and device based on deep learning, and relates to the technical field of three-dimensional reconstruction, and the reconstruction method comprises the steps: collecting a target object video of a target object through a camera imaging device, determining a target image set based on the target object video, and obtaining a target image set based on the target image set; the method comprises the steps of obtaining a target image set, determining target camera parameters and an initial camera pose, correcting the initial camera pose to obtain a target camera pose, inputting the target image set, the target camera parameters and the target camera pose to a preset neural radiation field model, outputting target radiation field information, and constructing an object three-dimensional model of a target object based on the target radiation field information. According to the invention, the technical problem of low accuracy of three-dimensional reconstruction of an object in the prior art is solved.
Owner:YGSOFT INC

Ultrasonic harmonic image generation method and device, electronic equipment and medium

The embodiment of the invention discloses an ultrasonic harmonic image generation method and device, electronic equipment and a medium. A specific embodiment of the method comprises the following steps: controlling an ultrasonic transmitting probe to transmit a low-frequency ultra-harmonic signal; controlling an ultrasonic receiving probe to receive the echo signal set to be detected; carrying out compressed sampling processing on the echo signal set to be detected and then carrying out signal reconstruction to obtain a reconstructed echo signal set; carrying out delay superposition processing on the reconstructed echo signal set to obtain a superposed echo signal; performing signal filtering decomposition processing on the superposed echo signals to obtain a super-harmonic signal set; performing envelope detection on the super-harmonic signal set to obtain an echo amplitude information set; and generating a target area ultrasonic harmonic image set, and sending the target area ultrasonic harmonic image set to a target terminal for display. According to the embodiment, by transmitting the low-frequency signal and receiving the ultra-harmonic signal, the attenuation of the received signal can be reduced, the signal penetration depth can be improved, the purity of the received signal can be improved, and the quality and the resolution of the generated ultrasonic harmonic image can be improved.
Owner:SHANGHAI TENTH PEOPLES HOSPITAL +2

Video key frame extraction method and system based on shot segmentation and VGG neural network

The invention relates to the technical field of video processing, in particular to a video key frame extraction method and system based on shot segmentation and a VGG neural network, and the method comprises the steps: firstly, extracting LBP-HF features and Canny features of continuous video frames, and obtaining shot boundary frames; then calculating the inter-frame similarity of boundary frames of adjacent shots, and dividing each shot into an active area or an inactive area by setting a threshold value; selecting a shot boundary frame as a coarse extraction key frame set for an inactive area; for the active area, sequentially inputting the video frames in the shot into a VGG19 convolutional neural network for feature vector description, extracting image depth features, calculating the similarity between the video frames, setting a threshold value to determine key frames, and adding the obtained key frames of the active area into a coarse extraction key frame set; and finally, removing key frames with high similarity in the roughly extracted key frame set to obtain a final video key frame set. According to the method, the key frame extraction efficiency and accuracy are effectively improved.
Owner:HENAN SONGSHAN LAB IND RES INST CO LTD LUOYANG BRANCH

Collision accident rapid reconstruction platform and reconstruction method

The invention relates to a collision accident rapid reconstruction platform and reconstruction method, and the platform comprises an accident information collection module which is used for collecting to-be-reconstructed real traffic accident information; the multi-rigid-body modeling module is used for performing multi-rigid-body modeling on a first collision vehicle, a second collision vehicle and traffic participants in the accident in MADYMO software; the simulation analysis module is used for performing simulation calculation on the simulation matrix generated by the optimization algorithm module; the parameter conversion module is used for converting parameters extracted from the traffic accident video into modeling parameters which can be identified in the simulation model; and the optimization algorithm module is used for determining a multi-target optimization algorithm, a design variable, a constraint condition and a reconstruction target. According to the method, the collision accident reconstruction efficiency is remarkably improved, the objectivity and accuracy of a reconstruction result are ensured, and the method is suitable for reconstruction of different complex collision scenes.
Owner:HUNAN UNIVERSITY SUZHOU INSTITUTE

Diffusion-driven channel adaptive point cloud semantic communication method

The invention provides a diffusion-driven channel adaptive point cloud semantic communication method, which belongs to the technical field of wireless communication, and comprises the following steps: obtaining a training point cloud data set, constructing a point cloud feature extraction network based on a hypergraph convolutional neural network as a semantic encoder, and constructing a channel adaptive enhancement module as a channel decoder, a channel adaptive recovery module is constructed at a receiving end as a channel decoder, a diffusion reconstruction network is constructed as a semantic decoder, end-to-end joint training is performed on the point cloud feature extraction network, the channel adaptive enhancement module, the channel adaptive recovery module and the diffusion reconstruction network, the diffusion reconstruction network predicts original point cloud distribution, and the point cloud feature extraction network and the channel adaptive enhancement module are subjected to end-to-end joint training. And a loss function is constructed based on the chamfering distance between the predicted point cloud distribution and the original point cloud. In the communication process, the reconstructed semantic features are input into the diffusion reconstruction network to reconstruct an original point cloud structure. The high-order semantic features of the point cloud can be effectively extracted so as to improve the adaptive capacity of the method to the incomplete point cloud.
Owner:南宁桂电电子科技研究院有限公司 +1

Face model reconstruction method and device, equipment and medium

The invention provides a face model reconstruction method and device, equipment and a medium. The method comprises the following steps: acquiring multi-frame original point clouds of a user face; determining an original point cloud of a reference frame and an original point cloud of a non-reference frame in the multiple frames of original point clouds; according to the multiple frames of original point clouds, reconstructing a first face model matched with the expression state corresponding to the original point clouds of the reference frame; and reconstructing a second face model matched with the expression state corresponding to the original point cloud of each non-reference frame by aligning the first face model to the original point cloud of each non-reference frame. By using the method, the reconstruction efficiency of the dynamic face model can be improved.
Owner:SHINING 3D TECH CO LTD

Reference marking system, three-dimensional reconstruction method and electronic equipment

The invention provides a reference marking system, a three-dimensional reconstruction method and electronic equipment, and relates to the technical field of three-dimensional reconstruction. The marking assembly comprises at least four non-coplanar markers with different target features, and the target features of the markers have projection stability; the marking assembly has full-view projection specificity, and two-dimensional projection images of the marking assembly are in one-to-one correspondence with three-dimensional space postures of the marking assembly. The reference marking system is suitable for X-ray imaging and natural light imaging, and can realize accurate identification of projection positions of all markers, so that accurate spatial position and attitude information can be provided for three-dimensional reconstruction, high-precision three-dimensional reconstruction can be performed from a single or sparse angle, and the spatial positioning precision and the reconstruction efficiency are improved.
Owner:李尧

Limited angle projection phase contrast CT image reconstruction method and device based on deep learning

The invention discloses a limited angle projection phase contrast CT image reconstruction method and device based on deep learning. The method comprises the following steps: acquiring limited angle projection data of X-ray phase contrast CT scanning through an equal angle increment strategy; performing flat field correction and dark field correction preprocessing on the limited angle projection data to obtain limited angle projection data before phase recovery; preprocessing the finite angle projection data through a phase recovery strategy to obtain finite angle projection data after phase recovery; cT reconstruction is carried out on the limited angle projection data before and after phase recovery through a filtering back projection strategy, and CT images of limited angle projection before and after phase recovery are obtained; a phase contrast CT intelligent image reconstruction network model is constructed and trained; and performing reconstruction processing on the CT image of the limited angle projection before and after phase recovery through the trained phase contrast CT intelligent image reconstruction network model to obtain a reconstructed phase contrast CT image. According to the method, phase contrast CT image reconstruction can be rapidly and efficiently carried out, finite angle reconstruction artifacts can be effectively inhibited, and the image quality is improved.
Owner:TIANJIN MEDICAL UNIV

Dot matrix auxiliary focusing digital holographic microscope system and holographic reconstruction method

ActiveCN119620574Agood precisionImprove rebuild speedInstrumentsDot matrixDigital holographic microscopy
The invention relates to a dot matrix auxiliary focusing digital holographic microscope system and a holographic reconstruction method, the system comprises a digital holographic microscopy light path part and a dot matrix auxiliary focusing light path part, the digital holographic microscopy light path part adopts polarization modulated narrow-band laser to irradiate an object sample to be measured to become object light; the reference light which is orthogonal with the polarization reflected by the reference mirror is subjected to interference imaging in the polarization camera, so that different phase shift acquisition of a single image is realized; the dot matrix auxiliary focusing light path part calculates the focus position of the object sample to be measured by using the definition of the image, and the optimal inverse diffraction distance required in the digital holographic reconstruction process can be directly obtained. Compared with the prior art, the method has the advantages that the automatic focusing efficiency of the digital holographic microscope is improved, the digital holographic three-dimensional surface reconstruction speed is greatly increased, and the reconstruction efficiency and real-time performance are improved on the premise that the reconstruction measurement precision is guaranteed.
Owner:SHANGHAI UNIV

Model generation method, model generation device, electronic equipment and storage medium

The invention provides a model generation method, a model generation device, electronic equipment and a computer readable storage medium, and belongs to the technical field of computers. The method comprises the steps of obtaining a to-be-processed human body image, and performing image segmentation on the to-be-processed human body image to obtain a first part image of a first part of a human body; processing the first part image through a first network to obtain first three-dimensional feature information of the first part; processing the to-be-processed human body image through a second network, and determining second three-dimensional feature information of a second part of the human body; and generating a three-dimensional human body model of the human body according to the first three-dimensional feature information and the second three-dimensional feature information. According to the invention, the three-dimensional human body model can be accurately and effectively generated.
Owner:CHINA TELECOM CORP LTD TECHNOLOGY INNOVATION CENTER +1

White light interference three-dimensional shape rapid reconstruction method

The invention discloses a white light interference three-dimensional morphology rapid reconstruction method. The method comprises the following steps: S1, continuously collecting N frames of interference images of a detected sample by using a white light interference system; s2, the collected interference images are preprocessed, and preprocessing comprises the steps that S21, interference interval positioning is conducted on all the interference images, and interference images to be reconstructed are obtained; s22, dividing each to-be-reconstructed interference image into a plurality of regions, and performing pixel point number reduction on each region to complete region pixel reconstruction to obtain a corresponding reconstructed image; s3, calculating a focusing metric value of each pixel point in each reconstructed image by using a focusing metric algorithm; and S4, searching zero optical path difference points of all pixel points in all the reconstructed images based on an improved gravity center method so as to recover the three-dimensional morphology of the tested sample. According to the method, the calculated amount and burr noise during three-dimensional shape reconstruction are greatly reduced, the timeliness is improved by nearly five times, and the reconstruction efficiency and accuracy are improved.
Owner:JIANGXI GAORUI OPTOELECTRONICS CO LTD

Efficient multi-view three-dimensional reconstruction method and system for outdoor scene

The invention discloses an outdoor scene-oriented efficient multi-view three-dimensional reconstruction method and system, and belongs to the field of multi-view three-dimensional reconstruction, and the method specifically comprises the steps: preparing a multi-view three-dimensional reconstruction data set for model training; constructing a multi-view three-dimensional reconstruction network comprising an adaptive feature extraction converter module based on big kernel attention, a cost regularization module and a depth estimation module; performing training and fine tuning on the network model to obtain a final model; building a multi-view three-dimensional reconstruction system and equipment; according to the method, the problems of poor accuracy and low integrity of a reconstruction result when an existing multi-view three-dimensional reconstruction method faces an outdoor large-scale scene can be solved, and the training reasoning time and the calculation cost of multi-view three-dimensional reconstruction can be reduced; and an important foundation is laid for application of outdoor large-scale scene image data in the field of multi-view three-dimensional reconstruction and development of a three-dimensional reconstruction technology.
Owner:CHANGCHUN UNIV OF SCI & TECH

Tomographic image reconstruction method, system, equipment and medium

The invention discloses a tomography image reconstruction method, system, device and medium wherein an image reconstruction model in the tomography image reconstruction method is obtained by the following steps: obtaining full-angle projection data, and preprocessing the full-angle projection data to obtain a back projection image; the back projection image comprises a full-angle back projection image, a sparse-angle back projection image and a limited-angle back projection image; performing constraint extraction on the back projection image to obtain a constraint image; performing double-domain image constraint reconstruction on the constraint image to obtain a double-domain constraint reconstruction result; and performing parameter constraint updating on the initialized image reconstruction model according to the constraint image and the double-domain constraint reconstruction result to obtain the trained image reconstruction model. According to the method, the difficulty of CT image reconstruction and required computing resources can be effectively reduced, and the efficiency of CT image reconstruction is improved. The invention relates to the technical field of CT image reconstruction.
Owner:GUANGZHOU MEDICAL UNIV

Transformer polymerization degree distribution visualization method, system, equipment and medium

The invention belongs to the technical field of data processing, and discloses a transformer polymerization degree distribution visualization method, system and device and a medium, and the method comprises the steps: generating an internal temperature field distribution simulation result of a transformer model through simulation software, and outputting transformer polymerization degree distribution data under different temperature changes; performing mesh generation on the transformer simulation model to obtain a triangular mesh model, and mapping the triangular mesh model to a plane parameter domain; selecting parameter points in the plane parameter domain, and generating corresponding data sampling points of the parameter points in the triangular mesh model by using an inverse mapping technology; and performing curved surface interpolation fitting on the data sampling points to obtain a curved surface fitting result, and performing visualization processing on the curved surface fitting result. According to the method, the sensor simulation model is subdivided to obtain the triangular mesh model, a complex model can be converted into a model with a small number of vertexes and a single boundary, the operation complexity of the fitting process is simplified, and the curved surface fitting efficiency is improved.
Owner:ELECTRIC POWER RESEARCH INSTITUTE OF STATE GRID SHANDONG ELECTRIC POWER COMPANY

Building three-dimensional model reconstruction method based on improved MVSNet and reconstruction system thereof

PendingCN119107426Aensure reliabilityachieve accurate reconstructionImage enhancementImage analysisData setPoint cloud
The invention belongs to the technical field of civil engineering structure health monitoring, and particularly relates to a building three-dimensional model reconstruction method based on an improved MVSNet and a reconstruction system thereof. Expanding a sparse depth map data set and an edge map data set corresponding to the picture set by using the DTU data set; training the proposed network ISENet to obtain an optimal weight; building appearance pictures of different visual angles are obtained to obtain a multi-visual-angle picture set; calculating and optimizing camera parameters and sparse depth maps corresponding to each picture in the multi-view picture set based on known camera internal reference and an SfM algorithm, and calculating an edge map corresponding to each picture; obtaining a corresponding depth map through an ISENet model by using the weight obtained by training; on the basis of a multi-view image set, a depth map and camera parameters, a dense building three-dimensional point cloud model is obtained based on a depth map synthesis point cloud algorithm. The method is used for solving the problems of incomplete active method model, inaccurate passive method model, inconsistent fusion method output and the like in building three-dimensional reconstruction in the prior art, and overcomes the problem of large building edge modeling error of a deep learning MVS method.
Owner:HARBIN INST OF TECH

Three-dimensional image reconstruction method and device

The invention provides a three-dimensional image reconstruction method and device, and belongs to the technical field of image processing, and the method comprises the steps: obtaining first point cloud data and second point cloud data; wherein the sources of the first point cloud data and the second point cloud data are different; determining a target registration demand based on the first point cloud data and the second point cloud data; a target registration strategy is determined from a plurality of point cloud registration strategies based on the target registration requirement, and the point cloud registration precisions of the plurality of point cloud registration strategies are different; registering the first point cloud data and the second point cloud data based on a target registration strategy to obtain point cloud registration data; and performing rendering processing on the point cloud registration data to obtain a three-dimensional image model. According to the three-dimensional image reconstruction method and device provided by the invention, the efficiency and accuracy of three-dimensional image reconstruction can be improved.
Owner:INST OF APPLIED MATHEMATICS HEBEI ACADEMY OF SCI

Human body three-dimensional model reconstruction method and device, equipment and storage medium

The invention provides a human body three-dimensional model reconstruction method, device and equipment and a computer readable storage medium, and the method comprises the steps: obtaining a sample video which comprises a human body image; performing feature extraction processing on each frame of image in the sample video based on the trained feature extraction model to obtain human body feature data corresponding to each frame of image; based on the attention calculation network of the human body three-dimensional reconstruction model, performing full connection and normalization processing on the human body feature data corresponding to the input image to obtain a feature weight value corresponding to the input image; based on a feature aggregation network of the human body three-dimensional reconstruction model, feature aggregation processing is carried out according to the feature weight value and the corresponding human body feature data, a prediction frame image is obtained, and human body features in the prediction frame image are different from human body features of the corresponding frame image in the sample video; and generating a target video according to the predicted frame image. According to the method, the data calculation complexity is reduced, and the reconstruction efficiency and effect of the human body three-dimensional model are improved.
Owner:PING AN TECH (SHENZHEN) CO LTD

Methods, apparatus, equipment and storage media for model training and 3D mesh reconstruction

PendingCN122798978Areduce computing costImprove repair stability
This application relates to the field of data processing technology, and in particular to a method, apparatus, device, and storage medium for model training and 3D mesh reconstruction, used to rapidly generate high-quality 3D results. The model training method includes: obtaining an initial repair model by distilling a student model to be trained; the initial repair model is used to make the input initial sample set, after M iterative repairs, present the shape of a 3D point cloud corresponding to the initial sample set; obtaining an intermediate repair model by distilling the initial repair model; the intermediate repair model is used to make the input intermediate sample set, after N iterative repairs, present the shape of a 3D point cloud corresponding to the intermediate sample set; and obtaining a target repair model by adversarial training of the intermediate repair model based on the initial repair model, so that the error between the results obtained by repairing the same target sample set using the target repair model and the initial repair model conforms to a preset error range.
Owner:TENCENT TECHNOLOGY (SHENZHEN) CO LTD

Sparse view angle X-ray light image three-dimensional reconstruction method based on mixed features

ActiveCN119107416Acapture moreDoes not affect reconstruction qualityDetails involving processing stepsBiological modelsComputer graphics (images)Algorithm
The invention discloses a sparse-view-angle X-ray light image three-dimensional reconstruction method based on mixed features, and the method comprises the steps: guiding sampling rays through employing a gradient value as a weight, and enabling the sampling rays to be distributed in a region which changes obviously as much as possible; three-plane decomposition features and hash coding features are mixed, the mixed features are sent to an attenuation field prediction network to predict attenuation values, an attenuation weight prediction network (W-NAF) is used to predict the attenuation weight of each sampling pixel point on an X-ray path, and the attenuation values and attenuation weight values at the sampling pixel points are obtained through the two networks; predicted projection pixel values are generated by accumulating attenuation values along the sampled rays, and then the network is optimized by minimizing the difference between the predicted projection and the real X-ray image.
Owner:ANHUI UNIV

Fingerprint library reconstruction method, device, equipment, readable storage medium and program product

ActiveCN120973313BImprove rebuild efficiencyreduce read
The application relates to a fingerprint library reconstruction method and device, equipment, a readable storage medium and a program product, and relates to the technical field of data recovery backup. The method comprises the following steps: reading the head part of a data file; acquiring the head part offset of each data block in the data file according to a bit set carried in the head part of the data file; reading the head part of each data block in parallel according to the head part offset of each data block, and obtaining the data block fingerprint and metadata carried in the head part of each data block; and inserting the data block fingerprint and metadata corresponding to each data block into a fingerprint library. The method can reduce the reading of invalid data and read the head part of each data block in parallel, so as to improve the fingerprint library reconstruction efficiency.
Owner:广州鼎甲计算机科技有限公司

A method and system for selecting a first reference image for MVS dense reconstruction

ActiveCN117788715BComplete and more accurate point cloud depth informationHigh precision
The application discloses a method and system for selecting a first reference image of MVS dense reconstruction, and belongs to the field of three-dimensional reconstruction, which comprises the following steps: inputting source image data; calculating the incidence angle of the source image; in each loop, calculating the incidence angle of other source images relative to the current source image, and obtaining the number of other source images within a certain threshold relative to the incidence angle of each source image; normalizing the number of other source images corresponding to each source image to obtain a first parameter for measuring the index; performing feature detection on all source images; performing feature matching and recording the total sum of feature point matching pairs of each source image; normalizing the total sum of feature point matching pairs of each source image to obtain a second parameter for measuring the index; calculating the product of the first parameter and the second parameter of each source image, and selecting the source image with the largest product result as the first reference image. The application can obtain a first reference image that can reconstruct a larger number of three-dimensional points, thereby obtaining a more accurate reconstruction in MVS and improving the efficiency of reconstruction.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA

A 3D model reconstruction method for remanufacturing blanks based on deep learning

The present application provides a method for reconstructing a three-dimensional model of a remanufactured blank based on deep learning, the method comprising: collecting images of the remanufactured blank according to pre-set acquisition parameters; generating sparse point cloud data of the remanufactured blank based on the images; extracting features of the remanufactured blank for each image to obtain feature images of the remanufactured blank of different sizes; generating feature-enhanced point cloud data based on the sparse point cloud data and feature images, and optimizing the feature-enhanced point cloud data using a deep learning network to obtain the optimal feature-enhanced point cloud data; generating a three-dimensional model of the remanufactured blank based on the optimal feature-enhanced point cloud data. The method achieves the improvement of the three-dimensional reconstruction accuracy and reconstruction efficiency of the remanufactured blank by pre-setting acquisition parameters and optimizing the feature-enhanced point cloud data using a deep learning network.
Owner:INNER MONGOLIA UNIV OF TECH

A Fast Reconstruction Method for Full-Scene Highway Reconstruction Based on Multi-Source Parallax Control and Adaptive Explicit Radiation Field

ActiveCN121962478BImprove implementation efficiencyAvoid time-consuming implicit training processParallaxComputer graphics (images)
This invention discloses a rapid reconstruction method for full-scene highway reconstruction based on multi-source parallax control and adaptive explicit radiance field, belonging to the field of 3D reconstruction technology. It includes: acquiring multi-source image data and calculating camera pose using differentiated strategies for scenes such as highways, bridges, and tunnels; representing the scene with an anisotropic set of 3D Gaussian spheres, and achieving accurate 3D-to-2D mapping through the covariance projection formula; iteratively optimizing Gaussian sphere properties using an adaptive density control strategy based on gradient threshold and volume constraints, automatically cloning / splitting in detail regions to improve accuracy; and achieving real-time rendering of over 60 FPS using tile-based parallel cardinality sorting and an alpha mixing formula. This method solves the problems of high cost, near-field blurring, disconnect between tunnel interiors and exteriors, and difficulty in real-time interaction associated with traditional methods, achieving rapid modeling and incremental updates within 24 hours, significantly improving reconstruction efficiency, detail fidelity, and user experience.
Owner:YUNNAN TRAFFIC PLANNING DESIGN RESEARCH INSTITUTE CO LTD

A magnetic resonance (MR) imaging method and system

The present application relates to a magnetic resonance (MR) imaging method and system, the method comprising: acquiring imaging data of an object collected by an MR imaging device within a scanning time; determining multiple reference images corresponding to multiple times within the scanning time based on at least part of the imaging data; determining time information of a dynamic image corresponding to the object within the scanning time based on the multiple reference images; determining spatial information of the dynamic image based on the time information and the imaging data; and reconstructing the dynamic image based on the time information and the spatial information.
Owner:SHANGHAI UNITED IMAGING HEALTHCARE

3D scene reconstruction method, device, electronic device and computer readable medium

The present application provides a 3D scene reconstruction method, device, electronic device and computer-readable medium, which relates to the field of computer vision technology, including: acquiring image data of a vehicle traveling in a target scene, performing sparse reconstruction using the image data to obtain a sparse point cloud of the target scene, and densely reconstructing the sparse point cloud through a pre-trained 3D Gaussian distribution representation model to obtain a first 3D scene reconstruction result, wherein the first 3D scene reconstruction result includes multiple first Gaussian distribution point clouds, the 3D Gaussian distribution representation model is used for dense reconstruction based on a 3D Gaussian splash algorithm, and the training samples of the 3D Gaussian distribution representation model are multiple real ground images and the sparse point clouds corresponding to each of the multiple real ground images. While improving the reconstruction efficiency, the weak texture area contained in the sparse point cloud obtained by sparse reconstruction is densely reconstructed to improve the accuracy of 3D scene reconstruction.
Owner:CHONGQING SELIS PHOENIX INTELLIGENT INNOVATION TECH CO LTD

A steel plate edge defect three-dimensional detection method and system based on full-matrix capture-full-focus imaging

This invention discloses a three-dimensional detection method and system for steel plate edge defects based on full-matrix capture-full-focus imaging, belonging to the field of ultrasonic non-destructive testing technology. The method includes: acquiring raw waveform data and encoder position information using full-matrix capture (FMC); performing three-dimensional reconstruction calculations using the full-focus imaging (TFM) method to obtain three-dimensional volume data; binarizing the three-dimensional volume data according to set edge geometric boundary conditions and generating a three-dimensional edge mask to extract candidate edge defect regions; calculating the three-dimensional defect volume and two-dimensional projected area of ​​the candidate edge defect regions and obtaining the ratio data; triggering an upgrade operation for the evaluation level of the candidate edge defect regions when the ratio data exceeds a set threshold, and outputting the evaluation result including the edge defect. This invention effectively eliminates the detection blind spots of traditional scanning of steel plate edge regions, truly reflects the three-dimensional spatial distribution of defects in the length, width, and thickness directions of the plate, and achieves highly reliable three-dimensional detection and quantitative evaluation of steel plate edge defects.
Owner:JIANGSU JINYU INTELLIGENT DETECTION SYST CO LTD

Method, device and readable storage medium for reconstructing dense three-dimensional model

The present invention discloses a method, device and readable storage medium for reconstructing a dense three-dimensional model. The method for reconstructing a dense three-dimensional model includes the following steps: S110, obtaining an input image, and extracting a multi-scale feature map in the input image; S120, performing a differentiable homography transformation operation on the multi-scale feature map to deform the multi-scale feature map into a corresponding feature body; S130, performing multi-level depth estimation on the feature body to obtain a target depth map of the same size as the input image; and S140, fusing the target depth map into a point cloud to reconstruct a dense three-dimensional model of the input image. The technical solution of the present invention can reconstruct a dense three-dimensional model of an input image, and at the same time has the advantages of reducing the complexity of image calculation, requiring less GPU resources, saving costs, having a simple structure, and having high reconstruction efficiency.
Owner:THE CHINESE UNIV OF HONG KONG (SHENZHEN)