Ministerio de Industria, Turismo y Comercio LogoMinisterior
 

Alerta

Resultados 91 results.
LastUpdate Updated on 22/11/2026 [07:23:00]
pdfxls
Solicitudes publicadas en los últimos 30 días / Applications published in the last 30 days
previousPage Results 50 to 75 of 91 nextPage  

METHOD AND SYSTEM FOR GENERATING A GRAPH REPRESENTING A TECHNICAL SYSTEM

Publication No.:  EP4835642A1 04/11/2026
Applicant: 
SIEMENS AG [DE]
Siemens Aktiengesellschaft
EP_4835642_PA

Absstract of: EP4835642A1

0001 The invention relates to generating a graph representing a technical system. A decoder iteratively constructs the graph as a graph token sequence in a structure-preserving graph serialization format, wherein each graph token represents a node of the graph or an aspect of the structure of the graph. In each iteration, the current state of the graph token sequence is used as an input token sequence (ITS). A decoder-only transformer (DOT) composed with a language model head (LMH) receives a textual prompt describing the technical system and the input token sequence (ITS) as input and computes a probability distribution over a token vocabulary (TV), which is a set of possible next tokens (PNT) that could be appended to the input token sequence (ITS). A graph parser (GP) receives partial token sequences as input and builds a partial graph (PG) for each partial token sequence. Each partial token sequence consists of the input token sequence (ITS) followed by one of the possible next tokens (PNT). A discriminator graph neural network (GNN) determines for each partial graph (PG) a probability score indicating how likely the partial graph (PG) is to occur in the real world. Finally, a next token sampler (NTS) receives as input the probability distribution and the probability scores, samples a next graph token from the token vocabulary (TV), and adds the next graph token to the graph token sequence. This multi-modal ensemble decoder outperforms traditional generation approaches

COMPUTER-IMPLEMENTED METHOD FOR DETERMINING AN OCCLUSION IN AN IMAGE

Publication No.:  EP4835835A1 04/11/2026
Applicant: 
IDENTY INC [US]
Identy Inc.
EP_4835835_PA

Absstract of: EP4835835A1

Computer-implemented method for determining an occlusion in an image, comprising the steps:Obtaining the image, wherein the image comprises a biometric feature;Processing the image by a neural network, wherein the neural network comprises a plurality of convolutional layers;Obtaining a heatmap from an intermediate output of the neural network, wherein the intermediate output is obtained after one of the convolutional layers;Determining an occlusion based on the heatmap;Providing an output based on the determined occlusion, wherein if the output indicates that at least part of the biometric feature is occluded, rejecting the image as invalid and/or providing information to a user that the image comprises occlusion.

MIXTURE-OF-EXPERTS NEURAL NETWORKS WITH SOFT ROUTING

Publication No.:  EP4835907A2 04/11/2026
Applicant: 
GOOGLE LLC [US]
Google LLC
EP_4835907_A2

Absstract of: EP4835907A2

0001 A system including a neural network configured to process a network input and to generate a network output is described. The neural network includes a sequence of one or more network blocks, e.g., one or more expert network blocks. At least one expert network block is configured to perform operations including: obtaining a block input representing an intermediate representation of the network input and comprising multiple input tokens; generating a plurality of input slots from the input tokens; for each of multiple expert subnetworks of the at least one expert network block: processing a respective subset of the plurality of input slots using the expert subnetwork to generate, for each input slot in the respective subset, a respective output slot for the input slot; updating the plurality of input tokens using the output slots to generate multiple output tokens; and generating a block output from at least the output tokens.

METHOD AND SYSTEM FOR CALCULATING A COMPRESSION POLICY

Publication No.:  EP4835741A1 04/11/2026
Applicant: 
NXP BV [NL]
NXP B.V.
EP_4835741_PA

Absstract of: EP4835741A1

0001 The present disclosure relates to a computing system and a method for calculating and using a compression policy of a neural network, comprising the steps of: selecting a plurality of compression methods, a plurality of compression ratios associated with the plurality of compression methods, and a target global compression ratio for the neural network; compressing each of the plurality of layers of the neural network according to each combination of the plurality of compression methods and of the plurality of compression ratios; for each of the plurality of layers, calculating a value for a loss function and a value for a cost function; calculating the compression policy for the target global compression ratio using the value for the loss function and the value for the cost function for each of the plurality of layers, and compressing the neural network according to the compression policy.

ADVERSARIAL PATCH DETECTION

Publication No.:  EP4835834A1 04/11/2026
Applicant: 
FUJITSU LTD [JP]
B G NEGEV TECH AND APPLICATIONS LTD [IL]
FUJITSU LIMITED
B.G. Negev Technologies and Applications Ltd.
EP_4835834_PA

Absstract of: EP4835834A1

A computer-implemented method for removing an adversarial patch from an image, comprising, receiving an input image, generating a noise image comprising random noise, inputting the input image and the noise image into a neural network;, extracting, using the neural network, a semantic content from the input image and a style from the noise image and constructing a de-styled image of the input image from the semantic content with the style from the noise image removed.

EYE TRACKING AND GAZE ESTIMATION USING OFF-AXIS CAMERA

Publication No.:  EP4835737A2 04/11/2026
Applicant: 
MAGIC LEAP INC [US]
Magic Leap, Inc.
EP_4835737_PA

Absstract of: EP4835737A2

Techniques related to the computation of gaze vectors of users of wearable devices are disclosed. A neural network may be trained through first and second training steps. The neural network may include a set of feature encoding layers and a plurality of sets of task-specific layers that each operate on an output of the set of feature encoding layers. During the first training step, a first image of a first eye may be provided to the neural network, eye segmentation data may be generated using the neural network, and the set of feature encoding layers may be trained. During the second training step, a second image of a second eye may be provided to the neural network, network output data may be generated using the neural network, and the plurality of sets of task-specific layers may be trained.

Method and device for proposing multi-stage candidate regions based on neural network structure search for object detection

Publication No.:  KR20260157268A 30/10/2026
Applicant: 
INDUSTRY ACADEMY COOPERATION FOUNDATION OF SEJONG UNIV [KR]
\uC138\uC885\uB300\uD559\uAD50\uC0B0\uD559\uD611\uB825\uB2E8

Absstract of: KR20260157268A

본 발명은 객체 검출 장치에 의해 수행되는 방법에 있어서, 사용자 단말로부터 데이터를 로드하는 단계, 로드된 데이터를 전처리 하는 단계, 전처리 된 데이터를 기초로, 딥 러닝 알고리즘을 학습하는 단계, 학습된 딥 러닝 알고리즘으로 입력 데이터를 입력하는 단계, 딥 러닝 알고리즘에서 출력된 출력 데이터를 기초로, 사용자 단말로 제공하는 객체 검출에 관한 제공 데이터를 생성하는 단계, 및 제공 데이터를 사용자 단말로 제공하는 단계를 포함하며, 상기 딥 러닝 알고리즘은 NAS-FPN (Neural Architecture Search - Feature Pyramid Network)과 Cascade RPN을 하나의 네트워크로 통합한 것인 객체 검출을 위한 신경망 구조 탐색 기반 다단계 후보 영역 제안 방법 및 장치일 수 있다.

ARTIFICIAL INTELLIGENCE-BASED METHOD FOR THE ELECTROCHEMICAL MODIFICATION OF SUCROSE TO DEVELOP ALTERNATIVES TO SUGAR

Publication No.:  MA71290A1 30/10/2026
Applicant: 
UNIV SULTAN MOULAY SLIMANE [MA]
UNIVERSIT\u00C9 SULTAN MOULAY SLIMANE
MA_71290_A1

Absstract of: MA71290A1

The invention relates to a method for applying artificial intelligence to the analysis and optimization of the electrochemical modification of sucrose, with the aim of developing sugar alternatives with improved health-related properties. The method comprises the use of convolutional neural networks to analyze cyclic voltammetry data, Bayesian optimization to determine optimal experimental conditions, and deep generative models to design sucrose derivatives. In particular, the invention makes it possible to identify the synergistic effects of Mg²⁺ and Cr²⁺ metal ions as catalysts in the controlled transformation of sucrose using titanium dioxide-modified carbon paste electrodes.

TRAINING NEURAL NETWORKS WITH GRADIENT CHECKPOINTING

Publication No.:  US20260340378A1 29/10/2026
Applicant: 
ARM LTD [GB]
Arm Limited

Absstract of: US20260340378A1

A data processing system for training a neural network. The data processing system comprises a storage circuitry configured to store checkpoint data for training the neural network and training configuration data indicative of a data partition for training the neural network. The data processing system also comprises a processing circuitry configured to perform a checkpoint operation for a layer of the neural network. The checkpoint operation comprises: obtaining input feature map data for a layer of the neural network, obtaining the training configuration data, selecting a portion of the input feature map data based on the training configuration data, processing the selected input feature map data in the layer of the neural network to obtain output feature map data, selecting a portion of the output feature map data based on the training configuration data, and storing, in the storage circuitry, checkpoint data derived from the selected output feature map data.

FLEXIBLE EXPLORATION OF FUSED LAYER EXECUTION FOR ARTIFICIAL INTELLIGENCE INFERENCE ENGINES USING HYPERPARAMETER OPTIMIZATION

Publication No.:  US20260340418A1 29/10/2026
Applicant: 
SAMSUNG ELECTRONICS CO LTD [KR]
SAMSUNG ELECTRONICS CO., LTD.
US_20260340418_A1

Absstract of: US20260340418A1

Methods and devices for performing neural network (NN) optimization, and a NN processing device for implementing an optimized NN. The method includes: obtaining a directed acyclic graph (DAG) that represents a NN model including a plurality of layers, wherein the DAG includes a plurality of nodes representing the plurality of layers, and a plurality of edges representing data paths between the plurality of layers; defining a plurality of hyperparameters corresponding to the DAG; performing a black box optimization on the NN model based on the DAG to optimize the plurality of hyperparameters; implementing the NN model using a NN processing device according to the optimized plurality of hyperparameters; and performing an inference operation based on input data using the NN processing device.

Real-Time Sales Intelligence and Deal Recommendation System Using Temporal Knowledge Graphs and Reinforcement Learning

Publication No.:  US20260340459A1 29/10/2026
Applicant: 
JAZWIECKI CURTIS DE [US]
IRVINE DAVID [AE]
TRAN BAO [US]
Jazwiecki Curtis De
Irvine David
Tran Bao
US_20260340459_A1

Absstract of: US20260340459A1

A method collects heterogeneous sales-related data from sources such as CRM systems, communication platforms, quoting systems, inventory databases, and marketing tools to continuously construct a temporal knowledge graph, known as the Deal Memory Graph. This graph is built by performing entity resolution and inferring both explicit and implicit relationships among customers, products, and interactions using techniques like graph neural networks and transformer-based cross-dataset matching. Real-time graph analytics, which include temporal pattern detection, cross-modal attention, and reinforcement learning, identify sales patterns, customer preferences, and key engagement signals during active interactions. Based on this analysis, the system generates personalized, context-aware prompts and actionable suggestions—such as recommended talking points, objection handling strategies, and follow-up content—that are tailored to individual sales representative behaviors and prospect characteristics. The system continuously refines its outcomes by updating the Deal Memory Graph, improving AI models through feedback, and incorporating market signals, competitor activities, and synthetic stress testing, while employing graph motif extraction, few-shot learning, and differential privacy-preserving updates to maintain adaptive, compliant, and energy-efficient operations for both immediate guidance and long-term sales pipeline management.

SOFTWARE AND METHODS FOR GUIDING INDUSTRY TRANSITION TO NET-ZERO EMISSIONS

Publication No.:  US20260340555A1 29/10/2026
Applicant: 
UNIV ARIZONA STATE [US]
OHIO STATE INNOVATION FOUNDATION [US]
Arizona Board of Regents on Behalf of Arizona State University
Ohio State Innovation Foundation
US_20260340555_A1

Absstract of: US20260340555A1

0000 A method for leveraging artificial neural networks (ANNs) to develop a transition roadmap toward net-zero emissions and circularity. The method involves obtaining datasets that quantify circularity and life-cycle environmental impact thresholds over a configurable time horizon, along with quantified technology readiness levels (TRLs) for multiple transition technologies. An ANN is trained using these datasets and a training algorithm, which incorporates an evolution function to model technology progressions and a trade-off function to evaluate threshold satisfaction at various stages. The trained ANN identifies a subset of technologies that meet the circularity and environmental impact thresholds across the entire timeline. The resulting roadmap outlines these technologies relative to the time horizon, providing a data-driven guide for achieving sustainability goals while balancing technological advancements and environmental considerations.

DATA GENERATION METHOD AND APPARATUS

Publication No.:  WO2026223310A1 29/10/2026
Applicant: 
YINWANG INTELLIGENT TECHNOLOGIES CO LTD [CN]
\u5F15\u671B\u667A\u80FD\u6280\u672F\u6709\u9650\u516C\u53F8
WO_2026223310_A1

Absstract of: WO2026223310A1

A data generation method and apparatus. The method comprises: acquiring moving object control information, which at least indicates a first motion attribute of a first moving object and a second motion attribute of a virtual vehicle, wherein the first moving object is an object having a first interaction relationship with the virtual vehicle; on the basis of the moving object control information, generating at least one group of trajectory points, wherein each of the at least one group of trajectory points comprises a plurality of pairs of trajectory points, and each of the plurality of pairs of trajectory points respectively indicates the positions of the first moving object and the virtual vehicle at the same moment; and then, on the basis of a first group of trajectory points among the at least one group of trajectory points, generating a first group of images so as to train a first algorithm model, wherein the first algorithm model is used for planning a traveling path for a first vehicle. The technical solution is applicable to the field of neural network model training, and facilitates an improvement in the capability of a vehicle to cope with a long-tail problem during autonomous driving, thereby improving the traveling safety of the vehicle.

NEURAL NETWORK MATRIX OPERATION OPTIMIZATION

Publication No.:  US20260340365A1 29/10/2026
Applicant: 
NVIDIA CORP [US]
NVIDIA Corporation
US_20260340365_A1

Absstract of: US20260340365A1

Apparatuses, systems, and techniques to optimize matrix operations within a neural network. In at least one embodiment, a matrix operation within a portion of a neural network is bypassed based on a difference between operands associated with the portion of the neural network.

Marine Detection System and Method

Publication No.:  US20260341158A1 29/10/2026
Applicant: 
OERSTED WIND POWER AS [DK]
\u00D8rsted Wind Power A/S
WO_2024240447_PA

Absstract of: US20260341158A1

Marine detection system and method for detecting marine bodies (8). The system includes a first sensor (6) for detecting marine bodies in a first detection region. A second sensor (3) is provided for detecting marine bodies in a second detection region. The second sensor is a different type of sensor to the first sensor and the second detection region overlaps with or is adjacent to the first. A controller (5) is provided including a neural network for processing data from the first and second sensors, where the neural network is trained to determine the presence of a marine body (8) based on the sensor data characteristics, and a signal indicating the presence of the marine body is output based on the determination by the neural network.

INDICATING MODEL PARAMETERS FOR CONTINUAL LEARNING OF COMMUNICATIONS NETWORK MODELS

Publication No.:  WO2026224600A1 29/10/2026
Applicant: 
LENOVO UNITED STATES INC [US]
LENOVO (UNITED STATES) INC.
WO_2026224600_A1

Absstract of: WO2026224600A1

Various aspects of the present disclosure relate to adapting (or updating) an artificial intelligence/machine learning (AI/ML) model (e.g., a deep neural network) to unknown/new target domains while minimizing any loss of knowledge of previous domains within which the model was deployed or adapted. For example, an adaptation procedure may determine or identify knowledge intensive (e.g., important) parameters of the model and adapt the model to a new domain while minimizing changes to values of the knowledge intensive parameters. The procedure may determine a metric for each parameter of the model (e.g., a knowledge coefficient or importance metric) and minimize changes to values of any parameters having relatively high importance metrics during adaptation/updating of the model.

Joint Training of Neural Networks using Multi-Scale Hard Example Mining

Publication No.:  US20260340979A1 29/10/2026
Applicant: 
INTEL CORP [US]
Intel Corporation
WO_2018184195_PA

Absstract of: US20260340979A1

An example apparatus for mining multi-scale hard examples includes a convolutional neural network to receive a mini-batch of sample candidates and generate basic feature maps. The apparatus also includes a feature extractor and combiner to generate concatenated feature maps based on the basic feature maps and extract the concatenated feature maps for each of a plurality of received candidate boxes. The apparatus further includes a sample scorer and miner to score the candidate samples with multi-task loss scores and select candidate samples with multi-task loss scores exceeding a threshold score.

Interactive Image Generation Method

Publication No.:  US20260341003A1 29/10/2026
Applicant: 
REVEALIT CORP [US]
Revealit Corporation
US_2021090449_A1

Absstract of: US20260341003A1

An interactive image generation method receives a communication that requests that a described imaginative scenario is generated that is to be embodied by at least one image. The description of the imaginative scenario is interpreted by applying attentions in association with applying a trained neural network that is trained using a training set comprising syntactical elements and images. Pixels are generated in accordance with learned training correspondences and the imaginative scenario by applying the trained neural network. The pixels may be further generated in accordance with an inference of a user preference that is based on usage behaviors that occur prior to the communication. An image that includes the generated pixels is provided to a user.

Reinforcement learning of tactile grasp policies

Publication No.:  AU2026253872A1 29/10/2026
Applicant: 
NVIDIA CORP
NVIDIA Corporation
AU_2026253872_A1

Absstract of: AU2026253872A1

One or more processors comprising: circuitry to enable one or more robotic devices to grasp one or more objects by: identifying, in one or more images depicting a scene that includes the one or more objects, one or more bounding volumes enclosing the one or more objects; using one or more neural networks to identify a target pose of one or more robotic devices to interact with the one or more objects based, at least in part, on one or more measurements from one or more tactile sensors attached to the one or more robotic devices and the bounding volumes enclosing the one or more objects identified in the one or more images; and causing the one or more robotic devices to grasp the one or more objects based, at least in part, on the identified target pose. measurements from one or more tactile sensors attached to the one or more robotic devices ct c t m e a s u r e m e n t s f r o m o n e o r m o r e t a c t i l e s e n s o r s a t t a c h e d t o t h e o n e o r m o r e r o b o t i c d e v i c e s

TECHNIQUES TO PROCESS LAYERS OF A THREE-DIMENSIONAL IMAGE USING ONE OR MORE NEURAL NETWORKS

Publication No.:  US20260340885A1 29/10/2026
Applicant: 
NVIDIA CORP [US]
NVIDIA Corporation
GB_2600328_PA

Absstract of: US20260340885A1

Apparatuses, systems, and techniques to identify one or more layers of a three-dimensional graphical image to generate a two-dimensional representation. In at least one embodiment, one or more layers of a three-dimensional graphical image are identified to generate one or more two-dimensional representations.

PROCESSING IMAGES USING MIXTURE OF EXPERTS

Publication No.:  US20260340783A1 29/10/2026
Applicant: 
GOOGLE LLC [US]
Google LLC
WO_2022251717_PA

Absstract of: US20260340783A1

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating predictions about images. One of the systems includes a neural network comprising a sequence of one or more network blocks that are each configured to perform operations comprising: obtaining a block input that represents an intermediate representation of an input image; determining a plurality of patches of the block input or of an updated representation of the block input, wherein each patch comprises a different subset of elements of the block input or of the updated representation of the block input; assigning each patch to one or more respective expert modules of a plurality of expert modules of the network block; for each patch of the plurality of patches, processing the patch using the corresponding expert modules to generate respective module outputs; and generating a block output by combining the module outputs.

ENHANCED LIFE ASSESSMENT METHOD FOR HIGH-VOLTAGE CIRCUIT BREAKER

Publication No.:  WO2026222905A1 29/10/2026
Applicant: 
ELECTRIC POWER RESEARCH INST OF GUANGXI POWER GRID CO LTD [CN]
\u5E7F\u897F\u7535\u7F51\u6709\u9650\u8D23\u4EFB\u516C\u53F8\u7535\u529B\u79D1\u5B66\u7814\u7A76\u9662
WO_2026222905_A1

Absstract of: WO2026222905A1

The present invention is applicable to the technical field of life assessment, and provides an enhanced life assessment method for a high-voltage circuit breaker. The method comprises: constructing a dynamic evolution model for the wear rate of a contact material; constructing a dynamic prediction model for nozzle degradation; constructing a probability distribution of the remaining life of an insulating material; on the basis of the dynamic evolution model for the wear rate of the contact material, the dynamic prediction model for nozzle degradation, and the probability distribution of the remaining life of the insulating material, constructing a comprehensive life assessment index; inputting the comprehensive life assessment index into a preset hierarchical prediction architecture for assessment, wherein a first layer generates a basic life distribution by means of a Bayesian network, a second layer outputs a correction parameter of a posterior life distribution by means of a convolutional neural network, and a third layer optimizes the posterior distribution by means of a KL divergence minimization algorithm to obtain a probability density function and a confidence interval of the remaining electrical life; and dynamically correcting model parameters of the hierarchical prediction architecture. The present invention can reduce errors in life assessment under complex operating conditions.

METHODS FOR COFFEE BEAN DEFECT DETECTION BASED ON SIAMESE NEURAL NETWORKS

Publication No.:  US20260340809A1 29/10/2026
Applicant: 
KUNMING UNIV [CN]
KUNMING UNIVERSITY
CN_120525807_PA

Absstract of: US20260340809A1

Disclosed is a method for coffee bean defect detection based on a Siamese neural network. The method includes: obtaining image data of normal coffee beans and four types of defective coffee beans, performing a preprocessing operation on the image data, and dividing the preprocessed image data into a training set, a validation set, and a test set according to a preset ratio; constructing a coffee bean defect detection model based on a dual-branch Siamese neural network, and training the coffee bean defect detection model using the training set to obtain a similarity score; validating and adjusting the trained coffee bean defect detection model using the validation set by employing a mixed-precision training strategy and a dynamic learning rate adjustment technique; and performing defect detection inference on the validated and adjusted coffee bean defect detection model using the test set to complete the coffee bean defect detection.

ONLINE EVALUATION METHOD FOR ERROR OF CAPACITIVE VOLTAGE TRANSFORMER

Publication No.:  WO2026223030A1 29/10/2026
Applicant: 
STATE GRID HUBEI ELECTRIC POWER CO LIMITED HUANGGANG POWER SUPPLY CO [CN]
\u56FD\u7F51\u6E56\u5317\u7701\u7535\u529B\u6709\u9650\u516C\u53F8\u9EC4\u5188\u4F9B\u7535\u516C\u53F8
WO_2026223030_A1

Absstract of: WO2026223030A1

The present invention relates to the technical field of online monitoring of capacitive voltage transformers (CVT), and in particular to an online evaluation method for an error of a CVT, comprising the following steps: step 1: collecting a large amount of historical operating data having error labels of a CVT; step 2: selecting suitable main features affecting errors; step 3: preprocessing the historical data and operating errors and constructing a data set; step 4: establishing an operating error evaluation model combining a variational autoencoder and a convolutional neural network; step 5: using a training set and a test set to train the operating error evaluation model; and step 6: when the trained model is put into use, subjecting online monitoring data of a CVT of the same model to the same preprocessing, and then inputting the preprocessed data into the trained operating error evaluation model to obtain an operating error. Online analysis and evaluation of the operating error of the CVT is realized; and further, building the evaluation model combining the variational autoencoder and the convolutional neural network improves the analysis accuracy.

THREE-DIMENSIONAL TARGET RECONSTRUCTION AND INDIVIDUALIZATION METHOD AND SYSTEM

Nº publicación: WO2026223112A1 29/10/2026

Applicant:

XIAMEN GREAT POWER GEO INFORMATION TECH CO LTD [CN]
STATE GRID LOCATION BASED SERVICE CO LTD [CN]
STATE GRID INFORMATION & TELECOMMUNICATION GROUP CO LTD [CN]
\u53A6\u95E8\u4EBF\u529B\u5409\u5965\u4FE1\u606F\u79D1\u6280\u6709\u9650\u516C\u53F8
\u56FD\u7F51\u601D\u6781\u4F4D\u7F6E\u670D\u52A1\u6709\u9650\u516C\u53F8
\u56FD\u7F51\u4FE1\u606F\u901A\u4FE1\u4EA7\u4E1A\u96C6\u56E2\u6709\u9650\u516C\u53F8

WO_2026223112_A1

Absstract of: WO2026223112A1

The present disclosure relates to a three-dimensional target reconstruction and individualization method and system. The method comprises the following steps: using an unmanned aerial vehicle to capture an image and a video; using a colmap tool to extract pose information and capturing information; using a SegFormer model to perform first segmentation to obtain original target images and corresponding original masks; processing the original target images to generate target images; using a Siamese neural network to perform image similarity measurement, so as to obtain matching similarities and pose overlap degrees; performing weighted calculation to select target images belonging to a same type, and performing second segmentation to obtain three-dimensional target images and corresponding target masks; using three-dimensional Gaussian splatting to perform rendering, so as to obtain rendering results, and initializing labels; performing differential matching on the rendering results and the corresponding target masks, comprising constructing and solving a label assignment optimization problem to obtain an optimal label assignment scheme; and on the basis of the optimal label assignment scheme, performing reconstruction and individualization.

traducir