40 results about "Model image" patented technology

The application relates to the technical field of image processing, and provides a model material replacement method and device for a design drawing. The method comprises the following steps: determining a target model from each model of a design drawing according to a received material selection instruction; obtaining a target material map corresponding to the material selection instruction from each material map of the target model; and merging the target material map, a light map, a diffuse reflection map and a reflection refraction map of the design drawing to obtain a model image of the target model in the design drawing; wherein the design drawing is an image obtained through rendering; the light map, the diffuse reflection map and the reflection refraction map are each layer obtained after the design drawing is rendered. The model material replacement method for the design drawing provided by the application can reduce the calculation amount of the model in the design drawing when the material is replaced, and reduce the resources consumed when the model material is replaced.

The present invention relates to a method for processing three-dimensional measurement data from a scanning probe microscopy system to provide three-dimensional topographic image data, as well as a method for performing scanning probe microscopy, a scanning probe microscopy system, a computer-implemented method, and a computer program product. The method comprises receiving 3D measurement data acquired by the SPM system into a processing device, the 3D measurement data typically mapping the topography of a structure provided by the substrate. The method further comprises digitally constructing model image data using shape contour data of the shape, and a regression operation to fit the model image data to the 3D measurement data. This results in a composite model image of the 3D measurement data that can be used as a topographic image.

The appearance customization method of a three-dimensional model, an electronic device and a storage medium provided by the present application relate to the technical field of three-dimensional modeling. The method comprises: obtaining a texture coordinate mapping diagram of a target three-dimensional model surface, the texture coordinate mapping diagram being used to represent a mapping relationship from the three-dimensional model surface to a two-dimensional plane; generating an appearance design texture file based on an image material selected by a user and a target region in the texture coordinate mapping diagram; and fitting the appearance design texture file to the target three-dimensional model surface based on the mapping relationship defined by the texture coordinate mapping diagram to obtain a virtual appearance model image. Thus, the present application can customize the appearance requirements of a three-dimensional model according to the personal preferences of a user, thereby avoiding the problem of aesthetic fatigue caused by fixed preset styles and improving the interactive interest and user participation of the three-dimensional model.

A kind of well safety valve on-line detection and calibration method, comprising the following steps: (1) deployment downhole television, obtains safety valve image;(2) given the ground pressure needing calibration, record the image of safety valve;(3) utilize three-dimensional modeling and calibration software to draw model;(4), adjust model parameters to make model image consistent with actual camera parameters, obtain the image of safety valve in well, and record model safety valve opening degree;The present application utilizes downhole camera to detect safety valve gate position, measures the opening degree of safety valve by three-dimensional model imaging and parameter matching, calibrates the relationship between ground hydraulic system pressure and downhole safety valve opening degree, to realize the detection and calibration of downhole safety valve.

This invention discloses a method, apparatus, equipment, and medium for controlling a tunnel ventilation fan based on tunnel environment monitoring, relating to the field of automated energy-saving control technology. The method includes: acquiring a vehicle model image set and vehicle images and spectral imaging images of vehicles entering the tunnel, wherein the vehicle model image set includes sample images of several different vehicle models; identifying the vehicle model; using the spectral imaging image of each vehicle as input, monitoring exhaust emissions according to the vehicle model using a vehicle exhaust emission model, obtaining exhaust emission monitoring values, and controlling the operating state of the tunnel ventilation fan based on the exhaust emission monitoring values. This solves the problems of existing ventilation methods for long-distance tunnels, which cannot be individually controlled according to the tunnel environment, resulting in high energy consumption and high maintenance and operating costs.

This invention discloses a robust wildfire identification method and apparatus for complex interference using a small-model collaborative approach, relating to the field of fire early warning technology. The method includes: training a robust wildfire identification model to be trained using training samples to obtain a trained robust wildfire identification model; acquiring an image and text to be identified, and inputting them into the trained robust wildfire identification model; obtaining visual features through the image to be identified, a small-model image encoder, and a large-model image encoder; obtaining text features through the text to be identified and a large-model text encoder; obtaining cross-modal fusion features of visual and verbal matching through a visual-language fusion module; and obtaining the wildfire identification result through the cross-modal fusion features and a fine-grained wildfire target detection network. Using this invention can improve robustness, stability, and recognition accuracy in smoke scenes under varying weather conditions, thereby improving the accuracy of wildfire target detection.

A method for calibrating a gantry is disclosed, the method comprising capturing with a camera, training images and a test image of a calibration dot; selecting a model image from the training images; scanning the model image and the test image to obtain model scan portions and test scan portions; for each test scan portion, shifting a model subpixel edge gradient derived from the model scan portion towards a test subpixel edge gradient derived from the test scan portion to obtain a corrected model subpixel edge gradient, which represents the shifted model subpixel edge gradient that exhibits the highest NCC with the test subpixel edge gradient; obtaining a denoised subpixel edge position based on the corrected model subpixel edge gradient; and determining a denoised dot center of the calibration dot based on the denoised subpixel edge positions.

Disclosed are systems, methods, and non-transitory computer-readable media for modeling images obtained from a vehicle using prompts. The system receives an image from a camera of a vehicle, the image depicting one or more objects. The system receives a prompt defining a target to be detected in the image. The system analyzes the image and data associated with the prompt using a machine learning model to generate a prediction indicating whether the one or more objects depicted in the image match the target defined by the prompt. The system causes a message to be displayed to an operator representing the prediction.

This invention discloses an image segmentation method based on neural operators, belonging to the technical field of image segmentation methods. The method includes: S1: preprocessing an RGB image; S2: image feature extraction; S3: image encoding; S4: distance encoding; S5: vector concatenation; S6: solving the Cheng Han equation using a solver; and S7: threshold segmentation. The beneficial effect of this invention is that it models image segmentation through solutions to partial differential equations, approximates a set of Cheng Han equations using implicit neural representations and convolutional neural networks, and achieves image segmentation by solving the zero-level set. This method does not require pre-segmentation input or multiple rounds of correction, and can generate high-resolution segmentation results from low-resolution images, significantly improving upon directly upscaling low-resolution segmentation results to high resolution.

This invention belongs to the field of image generation technology, specifically relating to a semantic alignment method and system for image generation based on a diffusion model with dual-loss optimization. The method includes: extracting cross-attention maps corresponding to each topic word in the text prompt during denoising; calculating aggregation loss and isolation loss based on the cross-attention maps, whereby the aggregation loss aggregates attention activations corresponding to the same topic word, and the isolation loss separates attention activations corresponding to different topic words; constructing a joint loss function based on the aggregation loss and isolation loss, and updating the latent representation along the gradient descent direction; inputting the updated latent representation into the denoising process at the next time step, until a preset number of denoising steps is reached, generating the output image. This invention optimizes the aggregation loss and isolation loss, simultaneously solving the problems of internal scattering and overlap in the attention maps, and can be applied to downstream tasks such as controllable layout generation and personalized generation.

This invention relates to the fields of computer vision and measurement technology, and proposes a method for precise localization of images without location information based on a real-world 3D model. The method includes four steps: Step 1: virtual projection image generation based on the real-world 3D model; Step 2: feature extractor construction and training; Step 3: feature library construction and feature matching; and Step 4: image pose calculation after retrieval. The virtual projection image generation method uses a real-world 3D model as a foundation, sets up a virtual camera according to preset observation distance, viewing angle range, and attitude parameters, performs multi-view virtual projection, and generates model image data associated with spatial location and height information. This invention requires no known shooting pose or spatial prior conditions, relying solely on the real-world 3D model as a reference data source to achieve high-precision spatial localization of images, filling the technical gap of being unable to locate images without location information, and greatly expanding the range of sources of locatable images.

The present disclosure relates to a resource planning method, device, electronic equipment, storage medium and program product, the method comprising: obtaining a model image, a hardware image and a scene image; generating at least two resource planning candidate schemes based on the hardware image; calculating the memory surplus of each resource planning candidate scheme based on the model image, the hardware image and the scene image; and selecting a target resource planning scheme from the at least two resource planning candidate schemes based on the calculated memory surplus of each resource planning candidate scheme. In this way, by taking the hardware image, the model image and the scene image as unified input, the feasibility determination and robust ordering of the resource planning scheme can be formed before resource deployment, avoiding the problem of long iteration cycle and high cost of resource planning scheme caused by relying only on pre-online stress testing or runtime trial and error, thereby improving the explainability, reproducibility and transferability of resource planning.

This invention provides a question-answering intelligent agent system and its construction method based on knowledge enhancement of oilfield inspection defect images, belonging to the field of petroleum industry equipment defect detection and operation and maintenance decision support technology. The solution adopts a closed-loop process of dual-source data processing, dual-model image knowledge extraction, heterogeneous graph knowledge graph construction, knowledge graph retrieval, large-scale model knowledge enhancement, and multimodal question-answering interaction, forming six core functional modules, and making targeted improvements to address the shortcomings of existing technologies. Relying on computer vision, natural language processing, knowledge graphs, and large-scale model technologies, through core designs such as image target localization, knowledge feature fusion, and model fine-tuning loss calculation, it achieves integrated realization of visual knowledge extraction, structured organization, and knowledge enhancement question-answering for oilfield defect images. This invention can provide operation and maintenance personnel with accurate and professional defect answers and handling decision support, significantly improving the intelligence and efficiency of oilfield inspection defect analysis and operation and maintenance decision-making.

The application relates to a method and device for deploying a model of a server, a computer device and a storage medium. The method comprises the following steps: obtaining a model deployment package corresponding to a to-be-deployed model, wherein the model deployment package comprises model configuration information corresponding to the to-be-deployed model; generating a model image corresponding to the to-be-deployed model based on the model deployment package; generating model service configuration information corresponding to the to-be-deployed model based on the model image and the model configuration information; creating a container control component and a service component corresponding to the container control component based on the model service configuration information; wherein the container control component is used for dynamically generating and controlling a model container set corresponding to the to-be-deployed model, and the container control component and the service component are used for cooperating to provide a model processing service corresponding to the to-be-deployed model, and the model processing service is used for distributing a model processing request corresponding to the to-be-deployed model into a model container in the model container set for processing. The method can improve the model management efficiency.

A method includes capturing at least one model image including a conduit between a tractor and a trailer, storing the model image, and classifying the model image as showing one of a connected position or an unconnected position of the conduit. The method includes capturing a second image including the conduit between a tractor and a trailer, comparing the second image to the model image, determining whether the conduit in the second image is in the connected position or the unconnected position based on the comparing, and notifying an operator whether the conduit is in the connected position or the unconnected position based on the determining.

The application discloses an image generation method and device, equipment and a storage medium, and relates to the technical field of picture processing. The method comprises the following steps: acquiring a current clothing image and a current model image; inputting the current clothing image and the current model image into a preset image generation model, wherein the preset image generation model is constructed based on a diffusion model and is trained through wavelet transform; extracting clothing features of the current clothing image through the preset image generation model, and performing feature fusion on the clothing features and the current model image to obtain a model clothing material picture. Compared with the existing process of relying on a photography team to shoot and manually processing pictures, the application can automatically reproduce a high-definition image through the preset image generation model, reduces the time consumption of manual operation, improves the efficiency of generating a model clothing material picture, and thus can meet the operation requirements of the e-commerce industry.

The application discloses a portrait splicing method and device based on an extended model, and a storage medium, comprising: obtaining a reference face image and a target model image; detecting head regions in the reference face image and the target model image respectively, and performing cropping processing on the detected head regions to obtain a reference face graph, a face key point graph, and a masked target model image; splicing the reference face graph, the face key point graph, and the masked target model image into an image condition; obtaining an expression text condition, inputting the expression text condition and the image condition into a pre-trained diffusion transformation model for processing and outputting a result image; and cropping an output region of the result image to obtain a head replacement result image. Through a dynamic mask strategy and a multiple condition control mechanism, the application realizes natural fusion with a target posture and expression while retaining source identity characteristics, and significantly improves the overall quality of the generated image.

The application provides an image processing method and device, electronic equipment, storage medium and program product, relates to the technical field of image processing, and the method comprises the following steps: based on a source image containing clothes to be changed and a model image containing a target object, an image pair is generated; based on structure prior information and a semantic mask of the target object extracted from the model image, a human body clothes mask is generated; the image pair, the human body clothes mask and a text prompt are input into a conditional diffusion model to obtain a virtual fitting image output by the conditional diffusion model. By adopting the conditional diffusion model, the image pair, the structure prior information, the semantic mask and the text prompt are introduced in the denoising process, high-quality and high-consistency image generation and editing are realized. While reducing the technical complexity and cost, the problems of structure distortion, detail loss and unnatural scene fusion of the generated image are solved, and the accuracy of virtual fitting is improved.

A file viewing method applies to a file viewing system including a first client electronic device and a second client electronic device. The second client electronic device includes a target object and an application program adapted to view the target object. The file viewing method includes receiving, by the second client electronic device, an instruction generated by the first client electronic device after determining that the second client electronic device has established a connection to the first client electronic device; executing, by the second client electronic device according to the instruction, the application program to open the target object, to further generate an operable model; and transmitting, by the second client electronic device, a model image corresponding to the operable model to the first client electronic device at an adjustable frame rate, and displaying the model image on a user interface of the first client electronic device.

The invention relates to a method for processing time series of noisy images of a same area, the method comprising: generating a set of time series of images from an input image time series by combining by first linear combinations each pixel of each image of the input image time series with selected neighboring pixels in the image and in an adjacent image of the input image time series; applying filtering operations in cascade to the set, each filtering operation combining each pixel of each image of each time series of the set by second linear combinations with selected neighboring pixels in the image and in an adjacent image in each time series of the set; performing an image combination operation to reduce each time series of the set to a single image; introducing a model image of the area as a filtered image in the set; and combining each image in the set into an output image, by third linear combinations.

This invention relates to the field of artificial intelligence, specifically disclosing a method, system, and medium for converting model images into 3D flat lay images based on physical perception. The method acquires a model image and text instructions, uses a prediction network to obtain a semantic mask and a 2.5D normalized deformation field, then extracts pure clothing content features based on the semantic mask, and uses the deformation field to reconstruct the spatial relationships of the content features, eliminating pose deformation in the feature space to obtain flattened clothing features. Finally, using the text instructions and flattened features as conditions, a high-fidelity flat lay image is generated through parallel decoding. This invention innovatively introduces a 2.5D physical perception mechanism and self-supervised training, effectively solving the problems of feature cross-contamination, pattern distortion, and generation speed bottlenecks, achieving high-speed, high-definition automatic generation of clothing flat lay images end-to-end without manual annotation.

The application discloses a clothing image generation method and device, equipment and a storage medium, and relates to the technical field of image processing. The method comprises the following steps: obtaining a target model image of a clothing to be put online and a target three-dimensional clothing image corresponding to the target model image, wherein the target three-dimensional clothing image is a three-dimensional clothing image conforming to a model posture in the target model image; extracting a clothing region image from the target model image; generating a key point image based on the target three-dimensional clothing image; and generating a high-quality clothing image corresponding to the clothing to be put online based on the clothing region image and the key point image through a preset clothing image generation model. The application can generate a high-quality clothing image based on a clothing region image and a key point image of a clothing to be put online through a preset clothing image generation model, thereby solving the technical problem that the production of clothing commodity pictures in the prior art depends on post-image processing, and the efficiency is low and the quality is not high.

Systems and methods for image processing include obtaining a guidance condition representing an image element and computing a conditioned tensor based the guidance condition and an unconditioned tensor independent of the guidance condition. An adaptive guidance strength is computed based on the guidance condition and the conditioned tensor and the unconditioned tensor are combined based on the adaptive guidance strength to obtain a scoring tensor. An image generation model generates a synthetic image depicting the image element based on the scoring tensor.

This invention provides a method and system for simulating jewelry wearing based on a generative image model, belonging to the field of image processing technology. The method includes: acquiring jewelry images and model images; extracting structural and detail features of the jewelry, as well as overall human structural features and target wearing area features; constructing a generative image model, injecting the jewelry structural and detail features, as well as the overall human structural features and target wearing area features, iteratively updating in stages, and finally generating a target image of the model wearing the jewelry. The system includes a raw image acquisition and processing module, a feature extraction and encoding module, and an image generation module. This invention overcomes the pain point of imbalance between the overall and details in traditional models by extracting jewelry and model features layer by layer, combined with a staged iterative injection mechanism, ensuring wearability and detail fidelity, and adapting to multiple scenarios such as e-commerce display, marketing material production, and design preview.

The application belongs to the technical field of medical image processing, and particularly relates to a classification model training method and system based on multi-modal mask self-supervised learning, aiming to solve the problems of excessive dependence of deep learning model image analysis on labeled data, insufficient multi-modal information fusion and poor recognition performance. The method comprises the following steps: acquiring pairs of multi-modal medical images and performing standardization processing; performing two-stage self-supervised pre-training, the pre-training is optimized through cross-modal reconstruction by constructing mixed images, and is optimized in combination with cross-modal semantic comparison, so as to learn robust feature representation; reserving the pre-trained encoder, combining the classification layer and fusing the classification loss function for supervised fine-tuning, so as to improve the discrimination performance on difficult samples. The application effectively utilizes unlabeled data through self-supervised pre-training, deeply fuses multi-modal information through cross-modal reconstruction and comparison learning, and improves the accuracy and robustness of medical image analysis tasks through difficult example mining fine-tuning strategy.

This application relates to an AI model image generation method, system, device, and medium, belonging to the technical field of image processing. It involves collecting multimodal data of the target garment, including mannequin images, flat static images, and material close-up images; selecting a reference image from a target pose library whose pose matches the desired pose, and extracting the corresponding pose skeleton image as the target pose skeleton image; inputting the flat static image and the material close-up image into a visual language model to generate a text description; and inputting the target pose skeleton image, mannequin image, and text description into a pre-trained LoRA diffusion model to generate a preliminary dressed image. The LoRA diffusion model's input layer includes an independent pose condition injection channel, through which the target pose skeleton image is input into the LoRA diffusion model. This application has the beneficial technical effect of avoiding stiff and unnatural AI model poses, thereby improving the aesthetics of the generated images.

Image quality can be assessed in a patient-specific manner using deep learning. Deep learning is used to extract image quality metrics (e.g. noise metrics, resolution metrics, noise correlation metrics) directly from image-based features, thereby enabling patient-specific image quality assessment. A neural network, or other suitable machine learning algorithm, is trained and implemented to generate noise maps from patient CT data, where the noise maps quantify the pixelwise noise level in the patient CT data.

This invention, entitled "A Method for Verifying Non-Coaxial Errors," belongs to the field of optical imaging and geometric correction technology. The technical problem it aims to solve is the geometric distortion in near-field observation images caused by the misalignment of the axis systems of the turntable and the field-of-view adjustment mechanism in existing imaging devices. The technical solution is as follows: S1, Establish a two-dimensional reference coordinate system in the XOY plane, setting the turntable angle as θ_r and the pointing angle of the field-of-view adjustment mechanism as 2*θ_m; S2, Based on the two-dimensional reference coordinate system established in step S1, establish a geometric model from the input quantities θ_r and 2*θ_m to the output quantity, the true field-of-view angle φ1; S3, Obtain the reference image and the original image under non-coaxial motion; S4, Verify the effect of the correction model image: Apply the accurate geometric model and the linear model with errors established in step S2 to process the original image in S3 to obtain geometrically corrected and uncorrected images.