32 results about "Facial reconstruction" patented technology

The invention relates to an obsessive-compulsive disorder diagnosis and symptom degree evaluation system, and belongs to the technical field of medical instruments. The evaluation system comprises a knowledge base module used for storing evaluation questions and used for responding to an evaluation request of a testee and randomly calling the evaluation questions stored in the knowledge base module, the question and answer evaluation module is used for acquiring face video data and electroencephalogram data of the testee in a detection time period and calling a next round of questions according to each round of voice or character answer information of the testee; the acquisition module is used for acquiring face video data and electroencephalogram data of the testee in the detection time period; and the analysis and evaluation module is used for analyzing the compulsive behavior and the compulsive thinking degree of the detected person in the detection time period. According to the invention, optical flow analysis and 3D face reconstruction sentiment analysis and evaluation are carried out based on face video data, the analysis and evaluation process is more efficient, and the analysis and evaluation result is more accurate; according to the method, multi-modal data such as electroencephalogram signals and 3D reconstruction are combined, and the emotion recognition effect can be further improved.

The invention provides a facial expression recognition optimization method and device based on deep learning and electronic equipment. The method comprises the following steps: acquiring facial expression data, and constructing a facial three-dimensional model by adopting a 3D facial reconstruction technology according to the facial expression data; extracting facial features from the facial three-dimensional model by adopting an SIFT algorithm, determining expression tags corresponding to the facial features, constructing a deep learning model, and training the deep learning model by adopting the facial features and the expression tags as training samples to obtain a facial expression recognition model; and at least adopting the facial expression recognition model to recognize the facial expression to be recognized, and generating a recognition result. By integrating 3D face reconstruction and SIFT algorithm technologies, the accuracy, robustness, fine expression recognition capability, dynamic expression processing capability and anomaly detection and processing capability of facial expression recognition are improved. The problem that an existing facial feature extraction algorithm is limited in fine expression recognition capacity is solved.

The invention provides a medical beauty-oriented AI face diagnosis feature and aesthetics analysis method and system, and relates to the technical field of intelligent medical beauty, and the method comprises the steps: collecting and preprocessing user face image data to obtain standardized face data; constructing a time sequence feature extraction model based on a deep convolutional neural network, and extracting facial dynamic features in combination with an optical flow estimation algorithm; and constructing a face reconstruction model based on the depth estimation network, and reconstructing a face three-dimensional structure by using a back projection mechanism and a geodesic distance partitioning strategy. According to the invention, accurate analysis of facial features can be realized, and the accuracy and individuation level of medical beauty diagnosis are improved.

The invention provides an image voice driving method and device and electronic equipment, and the method comprises the steps: carrying out the three-dimensional face reconstruction of a target object according to at least one frame of first original image containing the target object in an original video, and obtaining a three-dimensional face model of the target object, after the target voice used for driving the second original image different from the first original image in the original video is obtained, the three-dimensional face model is directly driven through the target voice, and the target face image for the target object is rendered according to the driven three-dimensional face model. And replacing the original face image of the target object in the second original image with the target face image to obtain a driving result of the second original image.

The present disclosure provides systems and methods that perform face reconstruction based on an image of a face. In particular, one example system of the present disclosure combines a machine-learned image recognition model with a face modeler that uses a morphable model of a human's facial appearance. The image recognition model can be a deep learning model that generates an embedding in response to receipt of an image (e.g., an uncontrolled image of a face). The example system can further include a small, lightweight, translation model structurally positioned between the image recognition model and the face modeler. The translation model can be a machine-learned model that is trained to receive the embedding generated by the image recognition model and, in response, output a plurality of facial modeling parameter values usable by the face modeler to generate a model of the face.

This application discloses a method and apparatus for training a facial modeling model, a modeling method and apparatus, an electronic device, a computer-readable storage medium, and a computer program product, which relate to the field of artificial intelligence. The method includes the steps of: acquiring sample facial images, where the sample facial images include facial images of the same object at the same time and from different viewpoints; performing feature encoding on the sample facial images by an encoder of the facial modeling model to obtain facial region latent codes corresponding to different facial regions and facial action latent codes corresponding to facial actions; performing 3D facial reconstruction on the object based on the facial region latent codes and the facial action latent codes via a neural radiation field of the facial modeling model to obtain a 3D facial image of the object; obtaining a 3D reconstruction loss between the 3D facial image and the sample facial image; and training the facial modeling model based on the 3D reconstruction loss.

This paper proposes a method for reconstructing the faces of curling athletes based on broadcast videos. This method optimizes the facial features of curling athletes in broadcast videos and utilizes deep learning techniques combined with a mask network strategy to overcome the limitations of traditional methods in processing reflective and weakly textured areas. This method provides more realistic and vivid digital human images for applications such as the metaverse, digital humans, and sports broadcasts.

The present disclosure provides a facial alignment tool to project a laser line or multiple lines onto a patient's face to assess symmetry and / or alignment during facial and / or nasal plastic surgery procedures such as rhinoplasty, nasal reconstruction, facial reconstruction, among other cosmetic or functional facial plastic surgery procedures. The facial alignment tool includes a moldable mouth guard specifically fabricated to be received in a patient's mouth, a support plate configured to receive the moldable mouth guard, a flange rigidly attached at its proximal edge to a front of the support plate, a positioning component attached to the distal edge of the flange, a rigid beam rigidly attached at its proximal end to the positioning component such that actuating the positioning component laterally translates the rigid beam, and a light source mounted to a distal end to the rigid beam by an adjustable laser mount configured to allow translation and rotation of the laser light source in the adjustable laser mount. The laser source is mounted such that when a patient has the support plate with the moldable mouth guard in their mouth the light source emits visible light projected onto the patient's face, and adjusting the positioning components moves the rigid beam and the light source attached thereto with respect to the patient's face.

The present disclosure provides a facial alignment tool to project a laser line or multiple lines onto a patient's face to assess symmetry and / or alignment during facial and / or nasal plastic surgery procedures such as rhinoplasty, nasal reconstruction, facial reconstruction, among other cosmetic or functional facial plastic surgery procedures. The facial alignment tool includes a moldable mouth guard specifically fabricated to be received in a patient's mouth, a support plate configured to receive the moldable mouth guard, a flange rigidly attached at its proximal edge to a front of the support plate, a positioning component attached to the distal edge of the flange, a rigid beam rigidly attached at its proximal end to the positioning component such that actuating the positioning component laterally translates the rigid beam, and a light source mounted to a distal end to the rigid beam by an adjustable laser mount configured to allow translation and rotation of the laser light source in the adjustable laser mount. The laser source is mounted such that when a patient has the support plate with the moldable mouth guard in their mouth the light source emits visible light projected onto the patient's face, and adjusting the positioning components moves the rigid beam and the light source attached thereto with respect to the patient's face.

A method and computing device for realistic real-time face rendering are provided. An example method includes receiving, by a computing device, visual data including a visible portion of a source face; determining, by the computing device and based on the visible portion of the source face, a first portion of a source face parameter associated with the parameterized face model, the first portion corresponding to the visible portion; predicting, by the computing device and in part based on the visible portion of the source face, a second portion of the source face parameter, the second portion corresponding to a remaining portion of the source face; receiving, by the computing device, a target video, the target video comprising a target face; determining, by the computing device, a target face parameter associated with the parameterized face model and corresponding to the target face based on the target video; and synthesizing, by the computing device, an output face based on the source face parameters and the target face parameters using the parameterized face model, the output face including the source face that mimics the facial expression of the target face.

The present disclosure provides a face processing method and apparatus, a computer device, and a storage medium. The method includes: obtaining three-dimensional face reconstruction coefficients of a three-dimensional face reconstruction model corresponding to face driving image data, and face posture information; determining initial character customization parameter information based on the face driving image data; and determining target character customization parameter information of the face driving image data based on the initial character customization parameter information, the three-dimensional face reconstruction coefficients, and the face posture information.

A fatigue-state detection method. The method comprises: acquiring facial key points of a user to be subjected to detection; on the basis of the facial key points and preset facial parameters, performing three-dimensional facial reconstruction on said user, so as to determine facial expression coefficients, wherein the preset facial parameters are facial feature information obtained after three-dimensional modeling is performed on a facial image; performing serialization processing on the facial expression coefficients within a set time, so as to obtain a timing sequence of the facial expression coefficients; and on the basis of the timing sequence of the facial expression coefficients, using a pre-trained detection model to detect a fatigue state of said user within the set time, so as to obtain a fatigue detection result.

The invention discloses a 3D head model generation method based on 2D facial expression analysis. The method comprises four steps of expression analysis, shielding object processing, multi-angle image generation and 3D model optimization. Firstly, expression parameters are extracted through an expression recognition model, and expressions are neutralized to generate expression-free images. Thirdly, automatically identifying and removing a shielding object by utilizing an image segmentation and deep learning inviting technology, and keeping the continuity of facial textures; then, a multi-angle view is generated from the non-shielded neutral expression image, and the consistency of the geometry and texture of the face is ensured; and finally, optimizing the shape and the chartlet of the 3D model by adopting a differentiable rendering technology to realize high consistency with the 2D image, thereby obtaining a high-precision and high-fidelity 3D head model. According to the multi-angle optimization method, the precision and consistency of 3D model generation are improved by combining differentiable rendering and deep learning. Geometric distortion is reduced through neutral expression generation, shielding objects are automatically removed, and the precision of face reconstruction is effectively improved. And the practical value is very high.

The present invention relates to the field of artificial intelligence technology, and specifically provides a method, device, electronic device and medium for three-dimensional face reconstruction, aiming to solve the technical problem of low accuracy of face reconstruction corresponding to the existing face reconstruction methods. For this purpose, the three-dimensional face reconstruction method of the present invention includes the following steps: obtaining an original speckle infrared image containing a human face; performing face detection on the original speckle infrared image to obtain a face region; determining the matching degree between each pixel in the face region and a reference image, and obtaining a depth map from the face region by using the matching degree; obtaining a high-resolution three-dimensional face image based on the depth map. In this way, the accuracy of three-dimensional face reconstruction is improved.

A three-dimensional head model generation method based on 2D facial expression analysis includes four steps of expression analysis, occlusion processing, multi-angle image generation and 3D model optimization. First, the expression parameters are extracted by the expression recognition model, and the expression is neutralized to generate expressionless images. Then, the image segmentation and deep learning inpainting technology are used to automatically identify and remove the occlusion, and the facial texture continuity is maintained. Then, multi-angle views are generated from the unoccluded neutral expression images to ensure the consistency of facial geometry and texture. Finally, the differentiable rendering technology is used to optimize the shape and map of the 3D model, realizing high consistency with the 2D image, so as to obtain high-precision and high-fidelity 3D head model. The multi-angle optimization method combines differentiable rendering with deep learning to improve the accuracy and consistency of 3D model generation. The neutral expression generation reduces geometric distortion, and the automatic removal of occlusion effectively improves the accuracy of facial reconstruction. It has strong practical value.

This invention discloses a method and apparatus for facial motion and expression transfer with detail optimization and compensation. The invention uses a 3D facial reconstruction model to model and encode facial motion and expression, achieving facial information acquisition and compression. A sliding window is used to ensure the consistency of the characters in the generated video. Multiple deep information fusion techniques are used to obtain the facial pixel flow field, initially distorting the original image to address the problems of poor generalization ability and missing motion and expression in keypoint-based expression transfer models for faces with significant differences. Multi-level facial detail encoding and optimization compensation models are used to specifically repair missing parts of the image, solving problems such as detail loss and edge distortion caused by information deficiency.

This application discloses an image generation method and related equipment. The relevant embodiments can be applied to various scenarios such as cloud technology, artificial intelligence, smart transportation, and assisted driving. The method can obtain the original facial image frame of the target object and the audio driving information of the target facial image frame to be generated; perform spatial feature extraction on the original facial image frame to obtain the original facial spatial features; perform temporal feature extraction on the audio driving information to obtain the facial local posture features; and perform facial reconstruction processing on the target object based on the original facial spatial features and the facial local posture features to generate the target facial image frame. This application can capture the facial posture details of the target object by extracting features from the audio driving information, and then perform facial adjustments on the original facial image frame based on the captured information, thereby obtaining the target facial image frame corresponding to the audio driving information. This is conducive to improving the generation efficiency and accuracy of the target facial image frame.

The application provides a medical and beauty-oriented AI face diagnosis feature and aesthetic analysis method and system, relates to the technical field of intelligent medical and beauty, and comprises the following steps: acquiring and preprocessing user face image data to obtain standardized face data; constructing a time sequence feature extraction model based on a deep convolutional neural network, and extracting face dynamic features in combination with an optical flow estimation algorithm; constructing a face reconstruction model based on a depth estimation network, and reconstructing a three-dimensional structure of the face by using a back projection mechanism and a geodesic distance partition strategy.The application can realize accurate analysis of face features and improve the accuracy and individualization level of medical and beauty diagnosis.

The invention provides a high-simulation virtual human generation method and system, and aims to gradually take a low-order virtual human as a generation source of a higher-order virtual human and carry out iterative approximation from basic image data. The technology comprises the following steps: firstly, obtaining a 2D image: step A, generating a virtual human head skeleton model file for preliminary three-dimensional face reconstruction, and then connecting the virtual human head skeleton model file to a body model bound with skeletons; b, training a neural network model for replacing the face in real time; in the step C, on one hand, the preliminary model generated in the step A is controlled through a program to realize changing actions, mouth shapes and expressions, and on the other hand, a low-order virtual human operation window is converted into virtual camera input to serve as video source input; and then performing real-time replacement with a higher simulation degree on the face by using the real-time replacement neural network model trained in the step B for the face so as to drive and form a virtual human with a higher simulation degree.

The invention discloses a restoration and 3D reconstruction method and system based on a polluted face picture, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining and preprocessing a polluted image containing a real prototype face image; processing the preprocessed face image through a preset generator-discriminator network; combining the initially generated prototype face image and the preprocessed public face data set as an input image, and processing the input image according to a parallel encoder network to obtain an initial 3D face model, a depth map and a reflectivity map; establishing a depth reflection loss function based on the depth map and the reflectivity map; and training the generator and the discriminator based on the updated generator loss function and a preset discriminator loss function to output a target 3D face reconstruction model. According to the method, the problem that the detail fidelity and the sense of reality of the 3D reconstruction result of a single polluted picture are poor is solved.

The invention discloses an image generation method and device, equipment, a medium and a program product, and relates to the field of artificial intelligence. The method comprises the following steps: encoding voice features of voice data; first face reconstruction is executed based on the voice features to obtain first face features, and the first face features are used for indicating a first face part related to the voice data; second face reconstruction is executed based on the voice feature and the first face feature to obtain a second face feature, the second face feature is used for indicating the first face part and a second face part irrelevant to the voice data, and the second face part is determined based on the anatomical relation with the first face part; and decoding the second facial feature to obtain a facial image corresponding to the voice data. According to the method, the face image can be generated based on the voice data, and the accuracy of the generated face image is improved.

Systems and methods for realistic real-time face rendering are provided. An example method includes receiving a target video, the target video including at least one target frame, the at least one target frame including a target face; receiving a scene comprising a series of source facial expressions; and determining one or more target facial expressions based on the target face in the at least one frame of the target video; and synthesizing an output face using the parameterized face model and the texture model, the output face including a target face wherein one or more target facial expressions are modified to mimic a source facial expression in the series of source facial expressions; and generate a mouth region and an eye region based on a deep neural network (DNN) and at least one previous frame of the target video; and combining the output face, mouth and eye regions to generate frames of the output video.

The present application relates to the field of artificial intelligence, and discloses a training method and apparatus for a face modeling model, a modeling method and apparatus, an electronic device, a computer readable storage medium, and a computer program product. The training method comprises: acquiring sample face images, wherein the sample face images comprise face images of a same object under different visual angles at a same moment; performing feature encoding on the sample face images by means of an encoder of a face modeling model to obtain face region latent codes corresponding to different face regions and face action latent codes corresponding to face actions; performing three-dimensional face reconstruction on the object on the basis of the face region latent codes and the face action latent codes by means of a neural radiance field of the face modeling model to obtain a three-dimensional face image of the object; and acquiring a three-dimensional reconstruction loss between the three-dimensional face image and the sample face images, and training the face modeling model on the basis of the three-dimensional reconstruction loss.

The present invention sets forth a technique for performing face micro detail recovery. The technique includes generating one or more skin texture displacement maps based on images of one or more skin surfaces. The technique also includes transferring, via one or more machine learning models, stylistic elements included in the one or more skin texture displacement maps onto one or more regions included in a modified three-dimensional (3D) facial reconstruction. The technique further includes generating a final 3D facial reconstruction that includes structural elements included in the 3D facial reconstruction and the stylistic elements included in the one or more skin texture displacement maps.

Exemplary embodiments include a computer-implemented method of training a neural network for facial reconstruction including collecting a set of 3D head scans, combining each feature of each 3D head scan with a weight to create a modified set of 3D head scans, training the neural network using the modified set of head scans, and inputting a real digital facial image into the neural network for facial reconstruction. Further exemplary embodiments include the set of 3D head scans comprising approximately a tenth or less in quantity in comparison to a quantity of the modified set of 3D head scans. The modified set of 3D head scans may comprise features found in the set of 3D head scans or the modified set of 3D head scans may consist of features found in the set of 3D head scans.

The invention provides an image processing method and a related device. The method comprises the following steps: performing three-dimensional face reconstruction based on a first real image to obtain a three-dimensional face model of the first real image; projecting the three-dimensional face model to an imaging plane to obtain a first face image; performing disturbance processing on the first face image to obtain a second face image; mapping the second face image to the three-dimensional face model to obtain a three-dimensional fusion image; and determining a false face image based on the three-dimensional fused image. According to the method and the device, the relatively accurate virtual face image can be generated, so that the negative sample quality for training the face recognition model is improved, and the accuracy of model recognition can be improved.

The present disclosure is directed to capturing a three-dimensional representation of a patient's face from multiple angles to integrate (fuse) it with at least one three-dimensional intraoral mesh of the patient's teeth to visualize a dental treatment plan. In one aspect, a method includes capturing media of a patient's face from a plurality of angles using at least one device; converting the media into a three-dimensional representation of the patient's face; and transmitting the three-dimensional representation of the patient's face to one or more processing components to integrate it with the three-dimensional representation of the patient's intraoral scan to visualize the patient's dental treatment plan.