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

23results about How to "Realistic visual effects" patented technology

Optimization method, system and equipment for particle system

The invention is suitable for the technical field of computers, and provides an optimization method, system and equipment for a particle system, and the method comprises the steps: loading the particle system, and randomly initializing the particle attributes of particles in the particle system; based on motion and interaction rules of particles, quantum calculation is adopted to predict behaviors of the particles in real time, and dynamic special effects of corresponding scenes are generated; according to the scene and the state of the player, the special effect attributes of the particles are dynamically adjusted, and the special effect attributes comprise the transparency, the color and the texture of the particles; the method comprises the following steps: tracking the life state of each particle in real time, marking each particle, generating a particle multiplexing pool, and generating a particle multiplexing strategy based on the particle multiplexing pool, and the particle multiplexing strategy is used for dynamic distribution of reusable particles. And the overall adaptability and rendering performance of the particle system are improved, so that a more real and vivid visual effect can be obtained.
Owner:GUANGZHOU YINGFENG NETWORK TECH CO LTD

Media picture rendering optimization method and system based on artificial intelligence

The invention relates to the technical field of picture rendering, in particular to a media picture rendering optimization method and system based on artificial intelligence. The method comprises the following steps: acquiring a terminal video stream; performing RGB format conversion on the terminal video stream to generate an RGB type frame image set; pixel partitioning is carried out on the RGB type frame image set, and RGB pixel matrix blocks are generated; performing color space acceleration conversion on the RGB pixel matrix block to generate a YUV cache data matrix; the YUV storage data matrix is sent to a DSP internal processing unit for key frame selection, and YUV key video frame data and YUV non-key video frame data are obtained; and performing intra-frame coding on the YUV key video frame data so as to generate YUV key frame coded data. According to the method, the media picture rendering efficiency is improved by optimizing data processing, transmission and rendering and combining user visual focus analysis.
Owner:ZHUZHOU HUATONG TECH

Head and neck tumor operation simulation training system based on UE5 engine

PendingCN119091708Aimprove surgical skillsRealistic visual effectsMedical simulationInput/output for user-computer interactionHead and neck tumorsHead and neck
The invention provides a head and neck tumor operation simulation training system based on a UE5 engine. The system comprises a rendering system, a display system, an interaction system, a control system, a physical simulation system, an operation process simulation system and a data recording and feedback system. According to the method, a more vivid 3D model and scene are created by utilizing the UE5 engine, a more real visual effect is provided, meanwhile, the physical simulation function of the UE5 engine can simulate interaction between the surgical instrument and the tissue, a more vivid tactile feedback effect is provided, the reality sense and effectiveness of simulation are greatly improved, and the method is suitable for popularization and application. According to the system, a safe and low-cost training platform is provided for medical workers through a highly-vivid 3D graph and a real operation process, and a user can perform simulation training of a half-tongue resection operation without depending on a real patient. Meanwhile, due to the fidelity and interactivity of the simulation system, the surgical skills of the user can be effectively improved.
Owner:SHANGHAI NINTH PEOPLES HOSPITAL SHANGHAI JIAO TONG UNIV SCHOOL OF MEDICINE

Water body effect rendering method and device, equipment and storage medium

The invention relates to a water body effect rendering method and device, equipment and a storage medium. The method comprises the steps that a target scene set in a target game engine is acquired; determining a target object in the target scene; generating a binary mask map based on the position of the target object in the target scene; the binary mask map comprises a first color area and a second color area; determining a water body rendering area in the first color area based on the second color area; and performing preset effect rendering on an effect rendering region in the water body model to obtain a water body model with the preset effect, the effect rendering region corresponding to the water body rendering region. According to the method, the position of the target object in the target scene is determined, the binary mask map is generated, and the water body rendering area is determined in the first color area of the binary mask map, so that dependence on a scene depth map is avoided, and the implementation process of the water body effect is simplified.
Owner:GUANGZHOU SNAP FINGER UNIVERSE TECH CO LTD

Coloring method based on AI image processing algorithm

The invention discloses a coloring method based on an AI image processing algorithm, and relates to the technical field of artificial intelligence, the method can speculate the original color Cp (Si) of a faded area through the combination of a color attenuation model and a historical color database Hd, the speculated color is subjected to historical correction, and a historical color correction result Ch (Si) consistent with a historical style is obtained. On the basis, the surface light reflection characteristic is combined, painting simulation is carried out on the mural, fine adjustment of illumination and materials is further carried out through an illumination model L and a material optimization function M, and a final painting result Tz (Si) is generated. Through multi-dimensional optimization, it can be guaranteed that the painting effect is kept consistent under different light rays and angles, the painting effect can be highly matched with the surface material of the mural, and finally it is guaranteed that the painting restoration result reaches the preset quality standard through multiple times of evaluation and adjustment.
Owner:SHANGHAI TITANIUM MAGNESIUM NETWORK TECH CO LTD

Visual three-dimensional reconstruction method and device and storage medium

The invention provides a visual three-dimensional reconstruction method and device and a storage medium, and the method comprises the steps: taking data generated by a first non-visual sensor as supervision, and carrying out the motion structure recovery of visual data generated by a visual sensor; constructing joint observation by using the first non-visual sensor and the visual sensor, and screening out effective visual data; and performing position supervision on the screened effective visual data by using data generated by a second non-visual sensor, and optimizing visual three-dimensional reconstruction. According to the method, depth information supervision and position supervision are respectively realized by using data acquired by the first non-visual sensor, the second non-visual sensor and the visual sensor, visual three-dimensional reconstruction is performed on a high-speed and large-scale outdoor scene, the reconstructed scene is more accurate, the visual effect is more vivid, and the efficiency and effect of visual three-dimensional reconstruction are improved.
Owner:BEIJING QINGZHOUZHIHANG INTELLIGENT TECH CO LTD

Dynamic adaptive sampling rate optimization method and device based on artificial intelligence, and medium

The invention relates to the technical field related to rendering, in particular to a dynamic adaptive sampling rate optimization method and device based on artificial intelligence and a medium. The method is applied to a real-time rendering system, and comprises the steps that a neural network model is constructed and trained, and the neural network model is used for automatically predicting the optimal sampling rate according to an input scene and a rendering quality target; constructing a dynamic adaptive sampling rate algorithm for automatically adjusting the sampling rate based on the output of the neural network model; in the real-time rendering process, the optimal sampling rate is predicted in real time through the neural network model, and the sampling rate of rendering is adjusted to the optimal sampling rate based on the dynamic adaptive sampling rate algorithm in the rendering process.
Owner:SHENZHEN RENDERBUS 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

Interactive naked eye 3D measurement system, method and device, electronic device and storage medium

PendingCN119273619AImprove experienceRealistic visual effectsImage enhancementImage analysis
The invention discloses an interactive naked-eye 3D measurement system, method and device, an electronic device and a storage medium. The interactive naked-eye 3D measurement system comprises a data reading module, an image preprocessing module, a 3D image visualization module, a 3D interaction module and a 3D space object measurement module. The data reading module is used for identifying and reading set image data; the image preprocessing module is used for carrying out image filtering and denoising operation on the image data; the 3D image visualization module is used for performing 3D reconstruction and visualization processing on the preprocessed image; the 3D interaction module is used for performing interaction or / and rotation or / and pickup operation on the visual 3D data; the 3D space object measuring module is used for measuring and calculating the distance between two points of an object in the space. According to the interactive naked-eye 3D measurement system, method and equipment, the electronic equipment and the storage medium, 3D measurement and naked-eye 3D display of medical data can be efficiently, accurately and visually completed.
Owner:上海易维视科技有限公司

VR-based panoramic display system and panoramic image splicing method

The invention relates to a panoramic display system based on VR and a panoramic image stitching method. The system comprises a closed panoramic display screen and a video stitching server. The video stitching server is used for stitching a plurality of panoramic images to merge, generating a panoramic video, and outputting the panoramic video to the closed panoramic display screen for panoramic display; according to the invention, the closed panoramic display screen can display the content at 360 degrees without dead angles, and audiences can freely rotate the visual angle in the display screen to feel immersive experience. The first feature extraction algorithm and the second feature extraction algorithm are combined, the advantages of different algorithms can be fully utilized, and the accuracy and robustness of feature point extraction are improved. The feature points are screened according to the local gradient of the feature points, the difference of the descriptors and the positions of the feature points in the to-be-spliced image, the feature points which are unstable or do not meet requirements are removed, the feature points with higher representativeness and stability are reserved, and the matching accuracy and reliability are improved.
Owner:SHIJIAZHUANG QICAI LIANCHUANG OPTOELECTRONICS TECH CO LTD

A type of electric piano black key and electric piano

ActiveCN224519496URealistic visual effectseasy maintenance
This utility model discloses a black key for an electric piano and an electric piano, relating to the technical field of electric pianos. It is used to mount on a keyboard base and includes a key body and an outer cover. The key body includes a mounting base for connecting to the keyboard base, with a protrusion at the upper end of the mounting base. The outer cover is made of a translucent material and has an open bottom. The outer cover is fitted onto the protrusion. Through the cooperation of the outer cover and the key body, a jelly-like visual effect is produced, unlike existing technologies where the effect is directly derived from the keys themselves. This not only creates a more realistic visual effect but also eliminates the need to disassemble the entire electric piano when these keys with special visual effects show signs of aging such as yellowing after prolonged use, making maintenance convenient.
Owner:QUANZHOU LAMBOS FURNITURE CO LTD

Cloud image efficient synthesis method

The application provides a cloud image efficient synthesis method, belonging to the field of image processing, comprising the following steps: calculating the edge distance transform of the mask of the foreground image to generate a multi-level boundary information graph; converting the background image and the foreground image to the Lab color space, and inputting the Lab channel, the mask and the multi-level boundary information graph into a generator network to output a preliminary fusion image in the Lab color space; using a brightness discriminator and a chroma discriminator to respectively judge the local texture consistency of the preliminary fusion image and a real fusion image in the L channel, and the global color harmony of the preliminary fusion image and the real fusion image in the a and b channels; performing the adversarial training of the generator network and the discriminator based on a total loss function until the network model converges, and using the converged generator network to generate a final fusion image. The application can guarantee the high realism and consistency of the fusion image in the details and the overall color tone.
Owner:CHANGCHUN INST OF TECH

Method for optimizing control parameters of organic electroluminescence driving system

InactiveCN119028274AImprove the display effectComfortable and satisfying viewing experienceStatic indicating devicesHemt circuitsComputational physics
The invention relates to the technical field of organic electroluminescence operation and maintenance, provides a control parameter optimization method for an organic electroluminescence driving system, and aims to solve the problem of insufficient brightness and color control precision caused by factors such as current fluctuation and material change. The method comprises the steps of obtaining basic data and a user instruction of the organic light-emitting device, preprocessing the instruction and converting the instruction into a driving parameter, matching and sending the parameter to an electrical element, collecting operation data and comparing the operation data with a user demand, correcting the parameter and optimizing a driving model by using a simulated annealing algorithm. By finely adjusting and optimizing the parameters of the driving circuit, the brightness and color control precision of the organic electroluminescence panel is effectively improved.
Owner:GUOJING HECHUANG (QINGDAO) TECH CO LTD +1

Curling player face reconstruction method based on rebroadcast video

The invention provides a curling player face reconstruction method based on a rebroadcast video. According to the method, the facial features of the curling player in the rebroadcast video are optimized, the deep learning technology is utilized, a mask network strategy is combined, the limitation of a traditional method in processing reflective and weak texture areas is overcome, and a more real and vivid digital human image is provided for the fields of element universe, digital human, sports event rebroadcast and the like.
Owner:HARBIN INST OF TECH +1

Adjustable holographic fan

The invention relates to an image display device, and particularly discloses an adjustable holographic fan, which comprises a machine body, a rotating seat, a first slip ring and a second slip ring sleeve, a plurality of first light-emitting blades are fixed on the rotating seat, the first slip ring and the second slip ring can move back and forth along the rotating seat, a first butt joint terminal and a first combination part are fixed on the first slip ring, and a second butt joint terminal is fixed on the second slip ring. The first butt joint terminal is connected with the light-emitting control module through a flexible flat cable. The second slip ring is located on the rear side of the first slip ring, a plurality of second light-emitting blades are fixed to the first slip ring, a second butt-joint terminal and a second combination part are installed on the first slip ring, and the second butt-joint terminal is electrically connected with the second light-emitting blades; the second sliding ring is rotationally connected with a traction base, a threaded hole is formed in the traction base and matched with a screw rod, and the screw rod is driven by a position adjusting motor. According to the adjustable holographic fan, the visual effect is remarkably improved based on cooperation of the second light-emitting blades and the first light-emitting blades, and the adjustable holographic fan is scientific and reasonable in structure, low in implementation cost and compact in structure.
Owner:DONGGUAN WEIGAO INFORMATION TECH CO LTD

Model motion control method, device and medium

The invention discloses a model motion control method, which comprises the following steps: loading a model, and obtaining a first front vector and a first initial position of the model; loading a preset motion path of the model, and sequentially setting a plurality of intermediate target points on the preset motion path according to the path type to realize path segmentation; constructing a first motion direction vector of the model by taking the first initial position as a starting point and the first intermediate target point as an ending point; based on the first front vector, taking the first motion direction vector as an adjustment target, and obtaining an angle and a direction needing to be rotated by the model; and adjusting the pose of the model based on the angle and direction that the model needs to rotate, and controlling the model to move to the first intermediate target point. According to the method, real-time calculation is carried out only through the coordinates between the current position of the model and the target point, the effect that the direction of the model is adjusted to be consistent with the movement direction can be achieved, the visual effect of object movement is more vivid, the real movement situation can be better simulated, dependence on network requests is avoided, and time delay is lower.
Owner:WUHAN GUIDE SENSMART TECH CO LTD

Method and system for automatically generating video according to 3D scene

The invention discloses a method for automatically generating a video according to a 3D scene. The method comprises the following steps: 1) automatically generating a video of a 3D scene of a decoration space according to a style and a type selected by a user; 2) automatically calculating a video path in the 3D decoration scene, selecting one region as a starting region, entering other regions through a reasonable path, and then returning to the starting region; 3) automatically generating animations and characters corresponding to each style type in the 3D scene; and 4) automatically generating introduction copywriting according to the type and style of the 3D scene. The invention further discloses a system for automatically generating the video according to the 3D scene. The video production time is greatly shortened, the labor cost is reduced, and the efficiency is improved. Through optimization and intelligent planning, high video quality and vivid visual effect are ensured, and the video quality is improved. The decoration effect is visually and dynamically displayed, customers are helped to better understand the design scheme, the satisfaction degree is improved, and the experience feeling is enhanced.
Owner:北京轻而易举智能科技有限责任公司

Face video forgery detection method

The invention discloses a face video forgery detection method, which comprises the following steps of: 1, acquiring a data set, adopting a diffusion model as a core generation framework, extracting a stable and high-discrimination identity embedding vector from the input data set, and injecting the stable and high-discrimination identity embedding vector into a generation process of the diffusion model in a conditional constraint manner so as to generate a forgery data set; and 2, completing face counterfeiting detection by using the counterfeiting data set generated in the step 1 based on a fine-grained distribution migration strategy. The method provided by the invention is used for solving the technical problems of insufficient quality of forged data, lack of time sequence consistency, lack of identity feature modeling, poor cross-identity forging adaptability, insufficient sensitivity of a detection model to fine-grained artifacts and poor robustness.
Owner:WEIHAI BLUE OCEAN BANK CO LTD

Humanoid robot simulation environment based on Isaac Sim and implementation method thereof

The invention discloses a humanoid robot simulation environment based on Isaac Sim and an implementation method thereof, relates to the technical field of robot simulation, is suitable for construction and verification of an industrial inspection and test laboratory scene, and accurately constructs equipment, obstacles and scene layout models by collecting detailed parameters of equipment and obstacles in the industrial scene and utilizing a 3D modeling tool, so as to realize the simulation of the humanoid robot. The method comprises the steps that firstly, a humanoid robot model is established, topological optimization and material detail processing are conducted, then the humanoid robot model is deployed in a simulation environment, movement, interaction and experimental operation of the robot in a laboratory are simulated through an integrated control system and a high-precision physical engine, and real-time movement control over the robot in simulation is achieved in combination with ROS2 and MoveIt2. According to the invention, the accuracy and reliability of task execution of the robot in a laboratory environment are improved, and effective verification and support are provided for application of the robot to an actual industrial experiment scene.
Owner:SHANGHAI YUANZHI INFORMATION TECH

Super-resolution image reconstruction method based on WPSN and CNN

The invention provides a super-resolution image reconstruction method based on WPSN and CNN. The method comprises the following steps: constructing a training data set by using LR image data and HR image data; constructing a new feature extractor wave packet scattering network WPSN, and setting experimental parameters; constructing a new super-resolution image reconstruction model WPSN-CNN based on the WPSN, setting model hyper-parameters, training a network model WPSN-CNN through the training data set, and obtaining a trained WPSN-CNN network model; and carrying out super-resolution image reconstruction by using the trained WPSN-CNN network model. According to the method, the wave packet system is introduced into the WSN, the modulo operation in the WSN and the convolution operation with the low-pass filter are removed, and the new feature extractor is established, so that the newly extracted features have translation exchangeability, and the multi-direction, multi-scale and multi-band features of the image can be fully utilized. The WPSN-CNN is used for performing a super-resolution image reconstruction task, so that richer image features can be extracted, a high-frequency structure and complex textures of an image can be reconstructed more accurately, the convergence speed on a small-scale data set is higher, PSNR and SSIM indexes are remarkably improved, and the visual effect is more vivid.
Owner:BEIJING JIAOTONG UNIV

D-NeRF image noise reduction method and system based on MSAF-DT

The invention relates to the technical field of image noise reduction, in particular to a D-NeRF image noise reduction method and system based on MSAF-DT. The method comprises the following steps: processing an acquired image data set based on a D-NeRF model to generate an RGB image; feature extraction is carried out on the RGB image based on an MSAF-DT method; feature fusion is carried out on the extracted features based on BatchNorm; image noise reduction is carried out on the adapted features based on a Transform; carrying out dimension conversion on the denoised image data; according to the D-NeRF sparse view image denoising method, the denoising quality and the processing efficiency of the D-NeRF sparse view image are remarkably improved by combining a multi-scale fusion attention mechanism (MSAF) and a denoising module based on a Transformer.
Owner:YANTAI UNIV

Method and device for generating dynamic evolution process of three-dimensional pore structure of soil aggregates

The method and device for generating the dynamic evolution process of the three-dimensional pore structure of soil aggregates belong to the field of agricultural information technology, and solve the problems that the method for generating the dynamic evolution process of the three-dimensional pore structure of soil aggregates is destructive, cannot observe the dynamic changes of the soil pore structure in real time, and is inefficient. The method of the present invention includes: obtaining a three-dimensional pore substructure data set of soil aggregates; training a three-dimensional pore generative adversarial network model of soil aggregates based on the pore substructure; using a differential strategy to obtain an input noise vector corresponding to the starting point pore characteristics and the end point pore characteristics; using spherical linear interpolation to obtain an intermediate noise vector; inputting the noise vector into the generation model to obtain the dynamic evolution process of the pore three-dimensional structure. The present invention is suitable for real-time and accurate reconstruction and prediction of the change process of the soil pore structure.
Owner:JILIN AGRICULTURAL UNIV +1

Three-dimensional scene program modeling method and device

The present application relates to a method and device for programmatic modeling of a three-dimensional scene, and belongs to the technical field of programmatic modeling. The method comprises: obtaining basic geographic data corresponding to a three-dimensional art scene to be modeled; making a node-based editor in three-dimensional software, the editor comprising: a simple change generator and a complex change generator; pre-building parameter nodes in the three-dimensional software; pre-building operator parameter nodes in the three-dimensional software; making component models of roads and component models of buildings in the three-dimensional software, the component models being established according to preset modeling rules; using a simple change generator, generating the required programmatic road model based on the component model of the road and storing it in a library; using a complex change generator, generating the required programmatic building model based on the component model of the building and storing it in a library; it has significant advantages in improving production efficiency, reducing memory usage, ensuring rendering quality, and maintaining visual consistency.
Owner:SUZHOU IND PARK SURVEYING MAPPING & GEOINFORMATION CO LTD