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

1073results about How to "Improve realism" patented technology

Video perspective method based on virtual reality

A video perspective method based on virtual reality relates to the technical field of virtual reality, and comprises: at least two cameras for capturing video information in real time, the cameras being provided with spatial positions and angles; performing geometric correction on the video information; the eye movement tracking module monitors the gazing direction of the eyes of the user in real time and adjusts the display position; the eye movement tracking module tracks eyeball movement; reconstructing a three-dimensional model of the surrounding environment of the user; based on the three-dimensional model, determining a relative position relationship between the virtual object and the real object; the head posture sensor obtains head movement information of a user; performing semantic segmentation on the video frame through a deep learning algorithm; and synthesizing the video information and the virtual content on the head-mounted display device, and outputting the synthesized video information and virtual content. The technical problems of visual discomfort and dizziness caused by position mismatching can be solved, and natural fusion of a real scene and a virtual scene is realized.
Owner:QINGDAO VIRTUAL REALITY RES INST CO LTD

Immersive space virtual-real interaction method and system

The invention discloses an immersive space virtual-real interaction method and system, and relates to the technical field of virtual reality interaction, and the method comprises the steps: collecting a full-view scene picture and illumination data through a camera, carrying out the preprocessing, simulating the real optical characteristics according to the scene picture and illumination data, and building a virtual scene; the virtual scene is evaluated and optimized; acquiring a user gesture image for analysis, identifying a user interaction command for virtual scene interaction, and displaying an interaction result in real time; and recording and storing the user interaction command and the interaction result. According to the method, the trueness and quality of the virtual scene are effectively improved, meanwhile, the user interaction command is recognized and analyzed by collecting the user gesture image and converting the user gesture image into the three-dimensional coordinate for virtual scene interaction, the gesture recognition accuracy is improved, and the experience effect of user virtual scene interaction is greatly improved.
Owner:ZHONGYI INSTECH TECH CO LTD

Virtual fitting method and device

The invention provides a virtual fitting method and device, multi-target personalized virtual fitting is realized through a multi-target and multi-mode virtual fitting model, and the virtual fitting device comprises a multi-mode feature interlaced learning attention module (MFILA) and a parallel denoising UNet module. Wherein the MFILA module realizes multi-modal condition feature coding through a multi-modal feature fusion module (MFF) and a multi-reference target texture feature extraction module (MRSTF), and the parallel denoising UNet module is mainly responsible for denoising generation. A user uploads a model clothes graph, a target fitting clothes style graph and corresponding text cues, and the system gradually generates a denoised virtual fitting result from pure noise through an MM-VTON model by taking the inputs as conditions. According to the method, the reality sense and the accuracy of virtual fitting are improved by utilizing an advanced image generation technology and multi-modal learning, meanwhile, the demand of computing resources is reduced, and the method has relatively high practical application value and a wide market prospect.
Owner:QINGDAO TRISTATE BIT TECHNOLOGY CO LTD

Indoor decoration simulation display method and system based on BIM

The invention discloses a BIM-based indoor decoration simulation display method and system, and relates to the technical field of indoor decoration, and the system automatically calculates an optimal furniture placement position through an algorithm by using modeling information in a BIM technology. The algorithm not only considers the distance between the furniture and collision detection, but also comprehensively considers the actual demand of the indoor space, so as to ensure the reasonable utilization and functionality of the indoor space. The intelligent layout algorithm can avoid a crowded or disordered layout condition, and ensures that the indoor space is full of vitality and not crowded by optimizing the placement position and the space utilization rate of furniture. The overall attractiveness and comfort of the space can be improved, and residents can live and work more pleasantly. The system simulates reflection, refraction and diffuse reflection processes of light on the surface of an indoor decoration object by using a light tracing technology. The system carries out detailed analysis on illumination conditions of different areas.
Owner:SHENZHEN CHINATANG DECORATION DESIGN ENG CO LTD

Multi-agent online collaborative discussion system

The invention belongs to the technical field of education, and particularly discloses a multi-agent online cooperative discussion system, which comprises a discussion module used for completing a discussion process together with a user based on a pre-created agent, the agent being driven by a large language model, and the user being driven by the large language model; the discussion process comprises the steps that a first prompt word and a second prompt word are input into a large language model, and a first type of agents and a second type of agents are determined; the first-class intelligent agent issues a discussion task; performing multiple rounds of discussion until each second-class agent and each user complete the discussion target; according to the system, on one hand, a large amount of time and labor cost can be saved, on the other hand, the online collaborative learning effect can be improved, and students are helped to better participate in discussion and grasp knowledge.
Owner:HUAZHONG NORMAL UNIV

Intelligent dialogue method and system

The invention provides an intelligent dialogue method and system, and belongs to the technical field of intelligence, the intelligent dialogue method and system comprise an intelligent dialogue system method, the intelligent dialogue system method comprises an intelligent dialogue module, and the intelligent dialogue system is used for processing natural language interaction between a player and an AI assistant (space-time secrete). Comprising functional modules of semantic comprehension, sentiment analysis, context memory and the like; due to the addition of the emotion interaction unit, the system can identify the emotion of the player, such as happiness, disappointment or anger, and dynamically adjust a reply strategy through an emotion mapping strategy, such as giving comfort or encouragement at proper time, so that the reality sense and interestingness of interaction are greatly increased, the player feels understood and concerned, and the user experience is improved. Therefore, the viscosity and the satisfaction degree of the game are improved.
Owner:王光辉

Marketing commodity short video generation method and device based on AI, medium and product

The invention discloses an AI-based marketing commodity short video generation method and device, a medium and a product, and relates to the field of short video generation. The method comprises the following steps: constructing a short video industry knowledge base; obtaining question information input by a user; searching answers from a short video industry knowledge base according to the question information; obtaining a video selected from the answers by the user as a reference short video, and obtaining commodity information uploaded by the user; the commodity information comprises commodity selling points and commodity materials; retrieving a reference copywriting from the short video industry knowledge base according to the commodity selling point, taking the reference copywriting as knowledge supplementary information, generating a script copywriting according to the reference short video and the knowledge supplementary information, and generating picture information according to the script copywriting and the commodity material; and editing the picture information to obtain a short video of the commodity information. The output efficiency of the running amount materials can be improved.
Owner:DALI MIRACLE (HANGZHOU) TECHNOLOGY CO LTD

Efficient graphic rendering system based on artificial intelligence core computing power

The invention relates to the field of graphic rendering, in particular to a high-efficiency graphic rendering system based on artificial intelligence core computing power, which comprises an intelligent task decoupling module for performing task decoupling on a graphic rendering task; the AI enhanced texture generation optimization module is used for learning a dynamic scene change rule to generate a texture map in real time, reducing calculation overhead in a repeated texture region by using a multiplexing algorithm, and performing super-resolution compensation on low-resolution textures by using a deep convolutional neural network; the AI driving illumination and shadow calculation module is used for predicting an illumination transmission path in a scene by using AI and reconstructing a dynamic shadow effect so as to realize high global illumination and shadow simulation; the task result synchronization module is used for synchronizing rendering data output by each subtask; according to the method, the high-quality texture map is dynamically generated, super-resolution compensation is carried out on the low-resolution texture, repeated calculation is avoided through a texture multiplexing algorithm, the calculation overhead is remarkably reduced, and the real-time rendering efficiency of a large-scale complex scene is improved.
Owner:CHANGSHA SHAOGUANG SEMICONDUCTOR CO LTD

Environment self-adaptive meta-universe scene sensing system and method

The invention discloses an environment adaptive meta-universe scene perception system and method, and belongs to the technical field of data transmission, and the method specifically comprises the steps: collecting and preprocessing multi-dimensional environment and sensory data in a meta-universe scene in real time through a sensor array, and constructing a full sensory environment data set; radar scanning and depth camera technologies are utilized to accurately obtain three-dimensional information of a physical environment, and a super-reality three-dimensional model is established to simulate a complex ecological system and environment characteristics of the physical world; in combination with real-time full-sensory environment data, an intelligent algorithm is adopted to dynamically adjust meta-universe scene elements, a user behavior prediction technology is introduced, scene layout and an interaction mode are intelligently adjusted according to user history and current states, and user experience is improved; user feedback is collected through VR immersive interaction, a scene perception method is evaluated, and iterative optimization is implemented according to an evaluation result so as to continuously improve the sense of reality and interactivity of the meta-universe scene; and efficient construction and intelligent management of the meta universe scene are realized.
Owner:JIANGXI ZHOUYUYUAN INFORMATION TECHNOLOGY CO LTD

Infrared and visible light image fusion method for improving image details and textures

The invention relates to the technical field of digital image processing, and provides an infrared and visible light image fusion method for improving image details and textures, and the method comprises the steps: splicing the feature vectors of an original infrared image and an original visible light image; performing initial feature map extraction of different spatial scales on the obtained source image features by adopting a plurality of serial residual parallel visual Mama network models; taking the initial feature map obtained by the last iteration as a basic feature map, and identifying fusion feature information of the basic feature map by adopting a multi-channel parallel visual Mama network model; expanding the fusion feature information to the initial feature maps of different spatial scales to obtain initial fusion feature maps of different spatial scales; performing up-sampling on the initial fusion feature map on each spatial scale to the resolution of the original infrared image and generating a fusion image; and performing iterative optimization according to the feature loss of the fused image and the original image. According to the invention, the detail definition and texture expression in the fused image can be obviously improved.
Owner:GUANGZHOU NANSHA DISTRICT BEIKE PHOTON SENSING TECH RES INST +1

Speech enhancement method and system based on time-frequency graph convolutional network

The invention discloses a speech enhancement method and system based on a time-frequency graph convolutional network in the technical field of speech signal processing, and the method comprises the steps: obtaining to-be-enhanced noisy speech data, inputting the to-be-enhanced noisy speech data into an improved metric generative adversarial network (CMGAN), and outputting an enhanced speech time domain signal; the improvement method of the metric generative adversarial network CMGAN comprises the following steps: replacing an encoder module of the metric generative adversarial network CMGAN with a time-frequency graph convolution encoder module; in the time-frequency graph convolution encoder module, a time convolution network and a graph convolution network are used for respectively extracting a long-time dependency relationship and global frequency characteristic information of noise-containing voice data to be enhanced, and dense residual error connection is introduced to fuse multi-scale characteristic information at the same time. The speech enhancement performance is improved under the condition of less model parameter quantity and calculation quantity.
Owner:NANJING UNIV OF POSTS & TELECOMM

Middle and primary school multi-person interactive teaching method and system based on VR technology

The invention provides a middle and primary school multi-person interactive teaching method and system based on a VR technology, and relates to the technical field of virtual reality, and the method comprises the steps: generating a model through deep learning based on pre-obtained teaching aid model data, determining subcomponents, combining a teaching aid generation engine, and constructing a virtual teaching aid; a color image and a depth image are obtained through a structured light depth camera, two-dimensional pixel coordinates are obtained, depth information is combined, a three-dimensional skeleton curve of limb movement of a student is generated, an optical motion capture result is obtained, an inertial motion capture result is obtained through inertial drift calibration based on the three-dimensional skeleton curve, and a limb movement three-dimensional track of the student is reconstructed; generating a force feedback signal by solving a kinetic equation through a collision detection algorithm based on the three-dimensional trajectory of the limb movement of the trainee; and rendering the virtualization model into a virtual teaching scene, synchronizing the limb movement three-dimensional track and the force feedback signal in real time, and generating a multi-person collaborative interaction process of the virtual teaching aid.
Owner:ZHONGKE LEMU (JIANGSU) TECH CO LTD

Character animation generation method and device based on voice driving, equipment and medium

The embodiment of the invention provides a character animation generation method and device based on voice driving, equipment and a medium, and belongs to the technical field of financial science and technology. The method comprises the following steps: acquiring an audio signal input by a user, a target human portrait picture and a target scene reference video; encoding the audio signal to obtain an audio code; generating a three-dimensional face model motion coefficient according to the portrait picture of the target person and the audio code; extracting blink information and head posture information from the target scene reference video; correcting the motion coefficient of the three-dimensional face model according to the blinking information and the head posture information to obtain a corrected motion coefficient of the three-dimensional face model; and taking a three-dimensional deformable head model as a potential vector, mapping the three-dimensional deformable head model to the corrected three-dimensional face model motion coefficient frame by frame, converting the three-dimensional face model motion coefficient into a video frame, and generating a head speech video of the target person. According to the embodiment of the invention, the quality and reality of character animation generation driven by voice can be improved.
Owner:PING AN TECH (SHENZHEN) CO LTD

Virtual tourism experience method based on large model

The invention provides a virtual tourism experience method based on a large model, and aims to provide personalized and immersive tourism experience by integrating advanced artificial intelligence and virtual / augmented reality technologies. The method comprises the following steps: firstly, collecting interest and preference information of a user, such as historical travel records, scenic spot preferences, travel time preferences, social media activities and the like, so as to capture detailed demands of the user; thirdly, generating personalized tourist routes and suggestions according to the information by utilizing a large-scale artificial intelligence model and combining deep learning and natural language processing technologies; in addition, the system renders scenic spots in a tour route in real time through a virtual reality or augmented reality technology, and the reality sense of vision and hearing is improved by applying advanced graphic and physical simulation technologies. And finally, an interactive interface is designed, so that the user can interact with the virtual tour guide through voice, text or gestures, more scenic spot information is obtained, a tour route is adjusted in real time, and the individuation and participation sense of user experience are greatly enhanced.
Owner:CHONGQING TECH & BUSINESS UNIV

Virtual scene construction method based on point cloud data, medium and equipment

The invention discloses a virtual scene construction method based on point cloud data, a medium and equipment. The method comprises the following steps: constructing an initial virtual scene based on original point cloud data; constructing a depth map corresponding to the point cloud data in the initial virtual scene, and determining a shielding relationship among the objects in the initial virtual scene based on the depth map; performing physics-based rendering on an object in the initial virtual scene, and processing the rendered initial virtual scene by adopting global illumination; and integrating the occlusion relationship into the rendered initial virtual scene to generate a new virtual scene. Through the above mode, the method can improve the trueness of building the virtual scene through the radar point cloud data.
Owner:SHENZHEN DEEPROUTE AI CO LTD

Naked eye 3D interaction method and system based on OSG

The invention is suitable for the technical field of naked eye 3D, and provides a naked eye 3D interaction method and system based on OSG, and the method comprises the following steps: loading an OSG library and a deep learning model, loading a 3D model, a map and a light source through OSG, and obtaining an OSG scene; collecting interaction data of a user in real time, inputting the interaction data into the deep learning model, and performing real-time analysis; outputting the visual angle parameter and the model parameter obtained through analysis, and adjusting the camera position and the model posture in the OSG scene according to the visual angle parameter and the model parameter; according to the optimized OSG scene, utilizing a computer vision technology to generate a parallax image, and utilizing a deep learning algorithm to optimize the parallax image so as to improve the reality sense and the stereoscopic sense of the 3D effect; and synthesizing the optimized parallax image into a naked eye 3D image. According to the invention, real-time and intelligent adjustment can be carried out according to the actual interaction behavior of the user, and the reality sense and stereoscopic impression of the 3D effect are strong.
Owner:JIANGXI SHUIJINGSHI TECH CO LTD

Tensile detection device for gauze for spinning processing

The invention relates to the technical field of spinning processing, and particularly discloses a spinning processing gauze tensile strength detection device which comprises a bottom plate, a first fixing plate and two second fixing plates are mounted at the top of the bottom plate, clamping mechanisms are arranged above the two second fixing plates, an automatic feeding mechanism is arranged above the first fixing plate, and a feeding mechanism is arranged above the automatic feeding mechanism. Stand columns are installed at the four corners of the top of the bottom plate, third fixing plates are jointly installed at the top ends of the two matched stand columns, a mounting plate is arranged at the bottoms of the two third fixing plates, and a cutting mechanism is arranged at the bottom of the mounting plate. In the process of detecting the tensile property of the gauze, different conditions of the to-be-detected gauze in the actual use process can be simulated by virtue of mutual cooperation of a plurality of components of the cutting mechanism and the automatic feeding mechanism, so that the tensile property of the gauze can be detected more comprehensively; the credibility and the trueness of the detection of the tensile property of the gauze are improved.
Owner:ANHUI SHANGZONG TEXTILE CO LTD

Real scene three-dimensional model construction method based on ground multi-source heterogeneous point cloud fusion

The invention belongs to the technical field of live-action three-dimensional model construction, and particularly relates to a live-action three-dimensional model construction method based on ground multi-source heterogeneous point cloud fusion. The method comprises the steps of unmanned aerial vehicle image acquisition and three-dimensional modeling, ground multi-source heterogeneous point cloud data acquisition, ground multi-source heterogeneous point cloud registration, ground fusion point cloud processing, and unmanned aerial vehicle image three-dimensional model and ground fusion point cloud space registration and fusion modeling. According to the method, the unmanned aerial vehicle image and the ground multi-source heterogeneous point cloud are fused, so that the problem of detail missing in large-range scene modeling is solved. The high precision of the ground point cloud and the wide coverage of the unmanned aerial vehicle image are combined, and the integrity and fineness of the model are significantly improved. In addition, the point cloud color endowing technology enhances the sense of reality of the model, and provides efficient and reliable technical support for the fields of smart cities, cultural heritage protection and the like.
Owner:QINGDAO INST OF SURVEYING & MAPPING SURVEY

Digital human control method and device based on multiple modes and electronic equipment

The invention provides a digital human control method and device based on multiple modes and electronic equipment, and relates to the technical field of data processing. In the method, voice data, facial expression data and body movement data of a user are acquired, and the user interacts with a digital human; performing semantic analysis on the voice data by adopting a Transform model to obtain an emotional state and a language habit corresponding to the user; performing feature extraction on the facial expression data by adopting a convolutional neural network model to obtain a facial expression type corresponding to the user; performing action analysis on the limb action data by adopting a hidden Markov model to obtain effective action features corresponding to the user; generating a fusion result based on the emotional state, the language habit, the facial expression type and the effective action features; and adjusting the multi-modal output corresponding to the digital human according to the fusion result. By implementing the technical scheme provided by the invention, the interaction experience feeling of the user can be improved.
Owner:UNION MOBILE PAY

Method for dynamically constructing coal mine geology digital twinborn body based on multi-source heterogeneous information

The invention provides a method for dynamically constructing a coal mine geology digital twinborn body based on multi-source heterogeneous information. Comprising the steps of AIGC-assisted geological result reading, end-to-end structured information self-adaptive generation, primary geologic body model construction through a generalized triangular prism algorithm, geometric smooth subdivision based on Kriging interpolation, special geological element dynamic updating and coal mine digital twinborn matrix generation. According to the method, the AIGC is introduced to assist in reading the geological result innovatively from the remarkable characteristics of the data intensive normal form of the geological information, and intelligent generation of structured information matched with an automatic modeling updating algorithm is realized through big data assimilation of multi-source heterogeneous information; a quick response process of information processing, primary geologic body generation, geometric smoothing, abnormal geologic body encryption and global geologic body construction is formed, and a high-precision coal mine geologic digital model is dynamically constructed by utilizing geologic information of different geologic survey stages. And the requirements of high precision, renewability and automation of the coal mine digital twinborn body are met.
Owner:CHONGQING UNIV

Diffusion three-dimensional medical image generation method for mask generation and image decoupling

The invention discloses a mask generation and image decoupling diffusion three-dimensional medical image generation method, relates to the technical field of image processing and analysis, and solves the problems of poor generalization ability, low calculation efficiency and high dependence on training data during image conversion in the prior art. The method comprises the following steps: acquiring a mask image, and processing the mask image by using a multi-condition diffusion probability model to obtain a multi-label mask sequence; screening the three-dimensional medical image data according to a screening condition, determining an informed slice set, and inputting the multi-label mask sequence and the informed slice set into a volume diffusion generation model to obtain a three-dimensional composite image; random noise is added to the three-dimensional composite image, a diffusion semantic refinement generation model is utilized, the three-dimensional composite image added with the random noise is refined, and a refined three-dimensional image is obtained; according to the invention, data decoupling and model generation volume consistency are realized, and a three-dimensional medical image with higher quality can be generated.
Owner:XIDIAN UNIV

Human setting, image, sound and life trajectory integrated construction method and system of digital human

The invention discloses an integrated construction method and system for human settings, images, sounds and life tracks of a digital human, and belongs to the technical field of the Internet. The method comprises the following steps: generating a virtual digital human; constructing a life track, an image and voice of the virtual digital human; and performing behavior analysis on the virtual digital person, and updating the life track, image and voice of the virtual digital person. According to the invention, the defects of too long time and low efficiency of traditional digital human creation are overcome; the method solves the problems that the personality of the digital person in the traditional digital person creation depends on a model too singly, so that the characteristics of the digital person are too single, and the digital person cannot automatically learn and grow.
Owner:ZHEJIANG FENGWO IOT TECH CO LTD

Text-driven digital human high-precision sound and lip synchronization system and text-driven digital human high-precision sound and lip synchronization method

The invention discloses a text-driven digital human high-precision sound and lip synchronization system and method, and the system comprises a text module which is used for converting an input text into linguistic features, including phonemes and rhythms; the acoustic module is used for converting the linguistic features into acoustic features and phoneme animation data; the audio module is used for sampling the acoustic features to generate audio clips; and the digital human interface module is used for receiving the phoneme animation data and the audio clips and synchronously playing the phoneme animation data and the audio clips so as to realize digital human lip synchronization. According to the system, high-precision audio and lip synchronization of the digital human is driven by a text, high-quality audio and lip animation data can be generated at the same time, the voice interaction fluency, the natural sense and the trueness of the digital human are greatly improved, and the user experience is improved. And meanwhile, the generation cost is reduced, and the generation efficiency is improved. Besides, a unified model of audio and phoneme animation data is generated from the text by using the neural network, so that synchronous learning of the sound spectrum and the animation data can be ensured, and the precision is higher.
Owner:DMAI (GUANGZHOU) CO LTD

Voice cloning method, voice cloning system, storage medium and program product

The invention discloses a voice cloning method, a voice cloning system, a storage medium and a program product, and relates to the field of artificial intelligence, and the method comprises the steps: collecting the original voice of a target speaker; performing preprocessing operation on the original voice to obtain optimized voice data; extracting voice feature data from the optimized voice data; training the voice feature data through a preset deep learning model to obtain a trained voice clone model; based on the voice clone model, generating clone voice according to the input text content; calculating the similarity between the cloned voice and the original voice; and when the similarity exceeds a preset similarity threshold, outputting the cloned voice. By implementing the method, the accuracy of voice cloning is improved.
Owner:BEIJING SPECIAL MEDICAL INTERNET BIOTECHNOLOGY CO LTD

Heart point cloud reconstruction method and system for echocardiography

The invention provides a heart point cloud reconstruction method and system for echocardiography, and the method comprises the following steps: obtaining three-dimensional heart structure data, and carrying out the preprocessing of the data; reading voxel data of the three-dimensional heart structure data, and performing point clouding to form voxel reconstruction point cloud data; performing standardization processing on the voxel reconstruction point cloud data to obtain all-center point cloud data, and performing segmentation acquisition to obtain standard section point cloud data; establishing a scanning guide network based on the heart structure data to be processed and the standard section point cloud data; and obtaining a test sample, inputting the test section point cloud data in the test sample into the scanning guide network, and outputting the three-dimensional heart structure data of the test sample and the heart point cloud data of the section where the test section point cloud data is located. After the scheme is adopted, an echocardiogram scanning guide network based on the point cloud is provided, a complete three-dimensional heart model is constructed, and meanwhile, the tangent plane where the two-dimensional echocardiogram is located is determined in the three-dimensional heart model.
Owner:HAIYAN COUNTY NANBEIHU MEDICAL ARTIFICIAL INTELLIGENCE RES INST +1

Monocular video face reconstruction and driving method based on Gaussian splash and 3DMM model

The invention discloses a monocular video face reconstruction and driving method based on Gaussian splashing and a 3DMM model. The monocular video face reconstruction and driving method comprises the following steps: S1, converting each frame of a face RGB video into an explicit expression face grid based on the 3DMM model; s2, constructing a geometric enhancement module, and carrying out geometric alignment on eye and tooth regions by adopting an improved iterative nearest point algorithm; s3, initializing a 3D Gaussian ball, and driving the dynamic change of the 3D Gaussian ball according to the point change of the face grid under different expressions; s4, based on the characteristics of different face areas, adaptive optimization learning strategy coefficients are distributed; and S5, increasing confidence information for each 3D Gaussian ball, generating a confidence image through rendering, multiplying the confidence image by a rendered image, calculating high-dimensional feature similarity with the input image, and optimizing attribute parameters and rendering effects of the 3D Gaussian balls. According to the method, Gaussian splashing and a 3DMM model are combined, and high-precision reconstruction and driving of a monocular video face are realized.
Owner:UNIV OF SCI & TECH OF CHINA

Spacecraft-oriented multi-task data set construction method

The invention provides a spacecraft-oriented multi-task data set construction method. A high-precision satellite geometric model is created. The image rendered based on the PBR not only has a bright-eye visual effect, but also conforms to a physical optics principle, and particularly, a normal mapping simulates a star body wrinkle effect. A space simulation scene is constructed by using an unreal engine 4, and a vivid rendering effect is provided. A high-quality satellite image is generated by combining a scene capture component and a target rendering function of an unreal engine, and a semantic segmentation tag, an instance segmentation tag, a depth tag, a normal tag and a pose tag are automatically generated based on a 3D model 2D image automatic labeling method. And a large-scale data set can be quickly generated in a frame-by-frame rendering and automatic labeling mode. Semantic segmentation is carried out on the generated image through the deep learning model DeepLab V3 +, the accuracy and efficiency of model prediction are further improved, and the rendering trueness is greatly improved through detailed analysis and optimization.
Owner:BEIHANG UNIV

Face image super-resolution method based on facial structure prior fusion network

The invention discloses a facial image super-resolution method based on facial structure prior fusion network guidance. The method comprises the following steps: constructing a facial image super-resolution network based on facial structure prior; preprocessing the public data set, and dividing the data set into a training set and a test set; training a face image super-resolution network based on face structure prior guidance; and super-resolution is carried out on the images in the test set. A face image super-resolution model based on a generative adversarial network is constructed, a generator part is composed of a rough super-resolution module, a key point heat map extraction module, a fine super-resolution encoder and a fine super-resolution decoder, and a discriminator is composed of a convolutional layer and a maximum pooling layer. According to the face super-resolution model constructed by the method, the problems of detail missing and low trueness of a result image under a relatively large magnification factor in an existing face super-resolution method are solved, so that a high-resolution face image with high trueness and a maintained structure can be reconstructed by the method.
Owner:NANJING UNIV OF SCI & TECH

Intelligent directional and quantitative smell generation method in virtual reality olfaction interaction

The invention discloses an intelligent directional and quantitative smell generation method in virtual reality olfaction interaction, and relates to the technical field of virtual reality. The invention provides an intelligent, directional and quantitative smell generation method in order to solve the technical problems that in smell generation work in virtual reality in the prior art, the variety and generation precision of smell are limited, an accurate smell concentration control mechanism is lacked, and interactive linkage with user actions and a virtual environment is lacked. In combination with an odor molecule dynamic combination technology, a deep learning prediction model, closed-loop concentration control and a spatial orientation transmission system, richer, personalized and immersive olfactory interaction experience is provided. Comprising a smell synthesis module, a digital smell control unit, an intelligent smell prediction model, a directional smell transmission system and a virtual wind field simulation module. The method is suitable for being applied to the work of intelligent directional and quantitative smell generation in virtual reality olfaction interaction.
Owner:HEILONGJIANG HUAZHONG TECH CO LTD

Speech synthesis method and device

The invention is a divisional application of 202311870114.7, and discloses a speech synthesis method, which comprises the following steps: dividing a target text into a plurality of target text segments according to a text sequence; inputting the first target text segment in the plurality of target text segments into a speech synthesis model to obtain a first target audio segment; splicing the first target text segment and the first target audio segment to obtain a text-audio alternating sequence; acquiring a next target text segment, and adding the next target text segment to the text-audio alternating sequence; inputting the text-audio alternating sequence into a speech synthesis model to obtain a next target audio segment of the next target text segment, and adding the next target audio segment into the text-audio alternating sequence until a final target audio segment corresponding to the final target text segment is obtained; and splicing the target audio segments to generate a target audio. According to the invention, text understanding can be carried out by using contexts of texts and audios, and rhythms, melodies and emotions in a scene can be captured.
Owner:SHANGHAI XIYU JIZHI TECH CO LTD