Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

41 results about "Facial reconstruction" patented technology

Treatment of conditions that present with low bone mass by continuous combination therapy with selective prostaglandin ep4 receptor agonists and an estrogen

InactiveUS20070191319A1High cure rateLong bone extension is enhancedBiocideSkeletal disorderPresent methodCarboxylic acid
This invention is directed to methods for treating conditions which present with low bone mass in a patient in need thereof using continuous combination therapy with a synergistically effective combination of an EP4 receptor selective agonist or a pharmaceutically acceptable salt thereof, such as 5-(3-{2S-[3R-hydroxy-4-(3-trifluoromethyl-phenyl)-butyl]-5-oxo-pyrrolidin-1-yl}-propyl)-thiophene-2-carboxylic acid or a pharmaceutically acceptable salt thereof; and an estrogen or a pharmaceutically effective salt thereof, The present methods are useful for treating conditions that present with low bone mass including osteoporosis, osteotomy, osteoporotic fracture, childhood idiopathic bone loss, periodontitis and low bone mass and for enhancing bone healing following facial reconstruction, maxillary reconstruction or mandibular reconstruction, inducing vertebral synostosis, enhancing long bone extension, enhancing the healing rate of a bone graft or a long bone fracture or enhancing prosthetic ingrowth in a patient in need thereof.
Owner:PFIZER INC

Three-dimensional facial reconstruction method

InactiveCN101751689AGeometry reconstruction speed reducedImplement automatic rebuild3D-image rendering3D modellingAdaBoostFace model
The invention relates to a three-dimensional facial reconstruction method, which can automatically reconstruct a three-dimensional facial model from a single front face image and puts forward two schemes. The first scheme is as follows: a deformable face model is generated off line; Adaboost is utilized to automatically detect face positions in the inputted image; an active appearance model is utilized to automatically locate key points on the face in the inputted image; based on the shape components of the deformable face model and the key points of the face on the image, the geometry of a three-dimensional face is reconstructed; with a shape-free texture as a target image, the texture components of the deformable face model are utilized to fit face textures, so that a whole face texture is obtained; and after texture mapping, a reconstructed result is obtained. The second scheme has the following differences from the first scheme: after the geometry of the three-dimensional face is reconstructed, face texture fitting is not carried out, but the inputted image is directly used as a texture image as a reconstructed result. The first scheme is applicable to fields such as film and television making and three-dimensional face recognition, and the reconstruction speed of the second scheme is high.
Owner:INST OF AUTOMATION CHINESE ACAD OF SCI +1

Computer auxiliary three-dimensional craniofacial rejuvenation method

InactiveCN101339670ARapid refactoringRealistic and accurate reconstruction3D modellingPattern recognitionTriangulation
The invention discloses a computer-aided 3D facial reconstruction method which comprises the following steps: 1) a skull is scanned to acquire a 3D digital skull model; 2) the 3D digital skull model with caverns is carried out acquisition of skull caverns and insertion of discrete points in the cavern area, and then the caverns are filled by adopting triangulation of spatial polygon, finally, the least squares fit and the interpolation method of the radial basis function are adopted to smoothly optimize a curved surface for partial and overall optimization to acquire a complete digital skull model; 3) the facial feature points are acquired by a method of manually marking feature points and a calculation method of adding normal soft tissue thickness along the normal direction of the curved surface, and the discrete feature points are carried out interpolation of the radial basis function and triangulation to acquire a facial reconstruction rudiment of the skull; 4) the reconstructed facial rudiment is generated into the 3D human face model with a sense of reality by a binding texture mapping algorithm. The computer-aided 3D facial reconstruction method has the advantages of good rapidity, high accuracy and reliability.
Owner:ZHEJIANG UNIV OF TECH

Zonal statistic model based facial reconstruction method

The invention belongs to the field of computer image processing, and particularly relates to a zonal statistic model based a facial reconstruction method. In the method, by a priori knowledge of calculating human facial model shapes, the skull to be reconstructed is subjected to face skin reconstruction, which means that: partitioning the skull and the face skin model according to different organs, and establishing a zone based statistic model; and respectively reconstructing each face skin zone of the skull zone, and splicing each face skin zone into a facial integral model. After the skull face skin is partitioned, the representation capability of the statistic model is improved, and the error of the reconstruction result is reduced. The zonal statistic model based facial reconstructionmethod has important application value in archaeology, forensic medicine, virtual surgery and other fields.
Owner:NORTHWEST UNIV(CN)

Three-dimensional facial reconstruction method based on multi-view cellphone selfie pictures

The invention discloses a three-dimensional facial reconstruction method based on multi-view cellphone selfie pictures. The three-dimensional facial reconstruction method includes automatically positioning mark points on selfie face images of a same person from n different angles; setting up a first energy function according to the mark points and solving a camera parameter Pk (k=1,....,N), wherein in the first energy function, I is pixel serial number, k is input image vision number, mi is the ith mark point, Xi is three-dimensional point coordinate corresponding to the ith mark point, and Pk is a projection transformation matrix from a three-dimensional point to the corresponding image; reconstructing a target function E=Edata+Ecolor+Esmooth according to the camera parameter, optimizing the target function and using a multi-tag image partition algorithm to solve the target function to obtain a three-dimensional facial model. By the three-dimensional facial reconstruction method, the accurate three-dimensional facial model can be reconstructed quickly by the cellphone selfie images.
Owner:WISESOFT CO LTD

3D face reconstruction from gate camera

A method of creating a 3-dimensional facial reconstruction of a user of a transit system includes detecting a user within a range of an image capture device positioned at a transit access point. A plurality of images of a first portion of the user's face are captured using the image capture device while the user passes through the range of the image capture device. A plurality of positions of the user may be detected as the user passes through the range of the image capture device. The plurality of images are combined with the plurality of positions and a relative angle and position of the user's face are calculated based on the combination of the plurality of images and the plurality of positions. A 3-dimensional model of the first portion of the user's face is generated based on the calculated relative angle and position and the 3-dimensional model is stored.
Owner:CUBIC CORPORATION

Bioactive graded zirconia-based structures

The present invention provides a functionally graded bioactive glass / ceramic composite structure or bioactive glass / ceramic / bioactive glass sandwich structure for use in such applications as damage resistant, ceramic dental implants, immediate tooth replacement, endodontic posts, orthopedic prostheses, orthopedic stems, bone substitutes, bone screws, plates, and anchors, nonunion fractures repair, alveolar ridge augmentation, missing small bone parts (e.g. fingers, toes, etc), maxilla facial reconstruction, spinal fusion, and scaffolds for bone regeneration, comprising a residual bioactive glass or glass-ceramic layer at all accessible surfaces, followed by an underlying graded glass-ceramic layer, and then an dense interior ceramic. The residual bioactive glass or glass-ceramic layer can be further transformed to a carbonate apatite (CHA) layer by immersing in calcifying solution or simulated body fluid (SBF) with electrolyte composition similar to that of serum. The interior ceramic preferably contains yttria-tetragonal zirconia polycrystal (Y-TZP) or ceria stabilized tetragonal zirconia polycrystal (Ce-TZP) or magnesia stabilized zirconia (Mg-PSZ) or calcia stabilized zirconia (Ca-PSZ) or alumina or zirconia-alumina composites. Further, the invention provides methods for making the same functionally graded bioactive glass / ceramic composite structure or graded bioactive glass / ceramic / bioactive glass sandwich structure.
Owner:NEW YORK UNIV

Criminology-oriented computer-assisted facial reconstruction method for skulls of unknown body sources

The invention belongs to the fields of forensic anthropology and computer graphics and relates to a criminology-oriented computer-assisted facial reconstruction method for skulls of unknown body sources. The criminology-oriented computer-assisted facial reconstruction method mainly includes steps of 1 three-dimensional modeling of a skull of an unknown body source, 2 gender discrimination of the skull of the unknown body source, 3 dense point based facial soft tissue rule analysis, 4 dense point registration based skull facial reconstruction method, 5 principal component analysis based facial estimation of the skull of the unknown body source, 6 generating of investigated photos based on three-dimensional facial model. The criminology-oriented computer-assisted facial reconstruction method can fast achieve facial reconstruction for skulls of unknown body sources, and can predict the facial features of victims before their death for criminal case investigation.
Owner:BEIJING NORMAL UNIVERSITY

Hands on computerized emulation of make up

A system for computerized simulation of a make-up process is provided herein. The system includes: one or more capturing device configured to capture images of a face of a human user in controlled lighting conditions; a face reconstruction module configured to generate a 3D model of the face, based on the captured images; a display configured to present the reconstructed 3D model to the human user; a touch / 3D user interface configured to receive a sequence of hand gestures and postures forming a virtual make-up session which imitates a real a make- up process; a virtual make-up simulator configured to apply virtual make-up features to the 3D model, to yield a 3D make-up model, based on said received hand gestures and postures, wherein said virtual make-up simulator repeatedly presents updated appearance of the 3D make-up model, over the display, responsive to changes made over said virtual make-up session.
Owner:INUITIVE

Three-dimensional human body reconstruction method and device, computer equipment and storage medium

The invention is applicable to the technical field of computer vision, and particularly relates to a three-dimensional human body reconstruction method and device, computer equipment and a storage medium.The three-dimensional human body reconstruction method comprises the steps of obtaining a human body image of a target object; extracting a face image and a body image in the human body image; utilizing the facial image to obtain facial parameters according to a facial parameter prediction model; based on the body image, obtaining body parameters by utilizing a body parameter prediction model;inputting the human body image into a gender classifier model to obtain a gender parameter; and obtaining a human body three-dimensional model of the target object through an SMPL-X model according to the face parameters, the body parameters and the gender parameters. Compared with an existing human body prediction model, the problem that face reconstruction is ignored based on a three-dimensional human body model can be solved.
Owner:SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI

Facial reconstruction method based on non-supervision automatic encoder

The invention provides a facial reconstruction method based on a non-supervision automatic encoder. The main content of the facial reconstruction method based on a non-supervision automatic encoder includes a semantic code vector, a decoder based on a parameter model and a loss layer. The process of the facial reconstruction method based on a non-supervision automatic encoder includes the steps: scene description is given in a semantic code vector mode; the parameter decoder generates a composite image corresponding the face, and a reverse image is formed through standard reverse propagation, and then end-to-end training without supervision is realized, and the parameter decoder includes an image forming model, a lighting model, image formation and reverse propagation; and a loss function is defined by three items, and the loss layer includes dense luminosity calibration, sparse landmark alignment, statistical regularization and reverse propagation. The facial reconstruction method based on a non-supervision automatic encoder can encode the details of the face, such as posture, shape, expression, skin color and scene lighting, is more exquisite, does not need supervision and allows end-to-end learning. Compared with a network of synthesizing face data training, the network can be preferably popularized to real data.
Owner:SHENZHEN WEITESHI TECH

Method and apparatus for creating three-dimensional montage

Disclosed is a method and apparatus for creating a three-dimensional (3D) montage. The apparatus for creating a 3D montage may include an image information extraction unit to extract image information from a face image to be reconstructed, using a face area based on statistical feature information and a feature vector, a 3D unique face reconstruction unit to reconstruct a 3D unique face model by fitting a 3D standard face model to face images of each view for the face image and feature information of each part for the face area, a 3D montage model generation unit to generate a 3D montage model by combining the reconstructed 3D unique face model with 3D face expression model information and 3D decoration model information, and a montage image generation unit to generate a montage image by projecting the generated 3D montage model from each view.
Owner:ELECTRONICS & TELECOMM RES INST

Deep learning-based three-dimensional facial reconstruction system

A 3D facial reconstruction system includes a main color range camera, a plurality of auxiliary color cameras, a processor and a memory. The main color range camera is arranged at a front angle of a reference user to capture a main color image and a main depth map of the reference user. The plurality of auxiliary color cameras are arranged at a plurality of side angles of the reference user to capture a plurality of auxiliary color images of the reference user. The processor executes instructions stored in the memory to generate a 3D front angle image according to the main color image and the main depth map, generate 3D side angle images according to the 3D front angle image and the plurality of auxiliary color images, and train an artificial neural network model according to a training image, the 3D front angle image and 3D side angle images.
Owner:ARCSOFT CORP LTD

Face recognition system and method for expression capture

The invention discloses a face recognition system and method for facial expression capture. The face recognition system comprises a face image acquisition system and a face feature recognition module;the real three-dimensional face reconstruction system is used for establishing a three-dimensional face model according to the structured light imaging principle of the face image acquisition system,and re-determining a three-dimensional coordinate system of the three-dimensional face model; the virtual character three-dimensional model system is used for establishing a three-dimensional virtualcontour in the same three-dimensional coordinate system and filling a virtual feature part in the three-dimensional virtual contour; the posture matching module is used for selecting a plurality of active selection feature points of each facial feature part and determining a proportional relation; the feature point association module is used for determining passively selected feature points according to the proportional relation; and the expression dynamic tracking module determines three-dimensional coordinate changes of passive selection feature points of the virtual feature part in a three-dimensional coordinate system according to a proportional relation. According to the invention, the similarity between the face features of the real face and the face features of the virtual character is ensured through the face recognition technology.
Owner:中影年年(北京)文化传媒有限公司

Multi-style face feature point detection method based on convolutional neural network

The invention belongs to the technical field of face recognition, and particularly relates to a multi-style face feature point detection method based on a convolutional neural network. According to the invention, fine tuning training is carried out on a residual network (ResNet-152) by inputting multiple styles of face images, so that style discrimination features are obtained; style clustering isperformed on the original image by using K-means by using style discrimination features; a style-aggregated face image set is generated through a generative adversarial network; finally, the originalface image and the style aggregation face image are jointly used as input, and face feature point prediction is generated through a cascade strategy. According to the method, errors caused by multiple styles to face detection are reduced, the accuracy of face detection is improved, and the method can be applied to face recognition, head posture estimation, face reconstruction, 3D face reconstruction and the like.
Owner:HARBIN ENG UNIV

Real-time three-dimensional eyelid reconstruction method and device

ActiveCN107862732AReal-time reconstructionImprove realismDetails involving 3D image dataAnimationDiscrepancy functionWeight coefficient
The invention discloses a real-time three-dimensional eyelid reconstruction method and device. The method comprises the steps that the pixel points of each channel of a four-channel boundary map including semantic information are fitted into a polynomial curve with the grayscale value acting as the weight; the three-dimensional characteristic vertexes corresponding to the four boundaries includingthe semantic information of the image on a linear three-dimensional eyelid model are defined and the corresponding relation between the three-dimensional characteristic vertexes and the two-dimensional characteristic points on the corresponding boundaries of the image is determined; a difference function is determined by the distance between the projection of the three-dimensional characteristicvertexes and the two-dimensional characteristic points, and the optimal weight coefficient of the two sets of linear three-dimensional eyelid models is solved; and the three-dimensional reconstructionresult of the eyelids is integrated in the face reconstruction result. According to the method, the four boundaries including the semantic information of the eye areas can be utilized, and real-timethree-dimensional eyelid reconstruction can be realized by optimizing the weight coefficient of the two sets of linear three-dimensional eyelid models so that the overall sense of reality of the three-dimensional facial animation can be enhanced.
Owner:TSINGHUA UNIV

Calibration method of virtual three-dimensional face reconstruction system

The invention discloses a calibration method for a virtual three-dimensional face reconstruction system, and the method comprises the steps: S1, solving a transformation relation between a world coordinate system and a CT three-dimensional coordinate system through employing a model coordinate system of a cylindrical die as the world coordinate system; S2, solving internal parameters of the monocular camera by using a checkerboard calibration board to obtain a transformation relationship between a camera coordinate system and a camera image coordinate system; s3, shooting a phantom at an initial point through a monocular camera, and solving a transformation relation between a world coordinate system and a camera image coordinate system; S4, according to the known coordinate transformationrelationship, finally obtaining the transformation relationship from the CT three-dimensional coordinate system to the camera image coordinate system; and S5, since the monocular camera is fixed on the CBCT, when the cantilever rotates, solving the coordinate transformation relation at any position. The method is used for realizing system calibration of the monocular camera and the CBCT, hardwareand data bases are laid for three-dimensional face reconstruction, and the problem that a binocular vision scanner is required to reconstruct a three-dimensional face in the prior art is solved.
Owner:深圳市深图医学影像设备有限公司

Deep Learning-Based Three-Dimensional Facial Reconstruction System

A 3D facial reconstruction system includes a main color range camera, a plurality of auxiliary color cameras, a processor and a memory. The main color range camera is arranged at a front angle of a reference user to capture a main color image and a main depth map of the reference user. The plurality of auxiliary color cameras are arranged at a plurality of side angles of the reference user to capture a plurality of auxiliary color images of the reference user. The processor executes instructions stored in the memory to generate a 3D front angle image according to the main color image and the main depth map, generate 3D side angle images according to the 3D front angle image and the plurality of auxiliary color images, and train an artificial neural network model according to a training image, the 3D front angle image and 3D side angle images.
Owner:ARCSOFT CORP LTD

Computer auxiliary three-dimensional craniofacial rejuvenation method

InactiveCN101339670BRapid refactoringRealistic and accurate reconstruction3D modellingPattern recognitionTriangulation
The invention discloses a computer-aided 3D facial reconstruction method which comprises the following steps: 1) a skull is scanned to acquire a 3D digital skull model; 2) the 3D digital skull model with caverns is carried out acquisition of skull caverns and insertion of discrete points in the cavern area, and then the caverns are filled by adopting triangulation of spatial polygon, finally, theleast squares fit and the interpolation method of the radial basis function are adopted to smoothly optimize a curved surface for partial and overall optimization to acquire a complete digital skull model; 3) the facial feature points are acquired by a method of manually marking feature points and a calculation method of adding normal soft tissue thickness along the normal direction of the curvedsurface, and the discrete feature points are carried out interpolation of the radial basis function and triangulation to acquire a facial reconstruction rudiment of the skull; 4) the reconstructed facial rudiment is generated into the 3D human face model with a sense of reality by a binding texture mapping algorithm. The computer-aided 3D facial reconstruction method has the advantages of good rapidity, high accuracy and reliability.
Owner:ZHEJIANG UNIV OF TECH

Face changing method and device for face image, electronic device and storage medium

The embodiment of the invention provides a face changing method and device for a face image, an electronic device and a storage medium. The method comprises the following steps: performing three-dimensional face reconstruction on a to-be-changed image and a specified image for changing the face of the to-be-changed image to obtain three-dimensional face posture information and three-dimensional face key points of the two images; deforming the specified image into an image of which the face posture information is the same as that of the to-be-changed face image, and taking the image as a secondspecified image; controlling the three-dimensional face key points, and performing predetermined face deformation processing on the to-be-changed face image and the second specified image to obtain two images matched with the three-dimensional face key points; and updating the face texture of the to-be-changed face image after the face deformation processing by using the face texture of the second specified image after the face deformation processing to obtain a face-changed image. The face changing method of the face image provided by the embodiment of the invention is relatively strong in robustness, and can still realize face changing of the to-be-changed image when the face postures in the specified image and the to-be-changed image are inconsistent.
Owner:BEIJING DAJIA INTERNET INFORMATION TECH CO LTD

Image processing method and related device

The embodiment of the invention discloses an image processing method and a related device in the field of artificial intelligence, and the method comprises the steps: obtaining a target image which comprises the face of a target object; determining a three-dimensional face reconstruction parameter corresponding to the target object according to the target image; based on the three-dimensional face reconstruction parameters corresponding to the target object, constructing a three-dimensional face grid corresponding to the target object; converting the three-dimensional face grid corresponding to the target object into a target UV image, wherein the target UV image is used for bearing position data of each vertex on the three-dimensional face grid corresponding to the target object; determining a target face pinching parameter according to the target UV graph; and generating a target virtual face image corresponding to the target object based on the target face pinching parameter. According to the method, the three-dimensional structure of the virtual face image generated by face pinching can be consistent with the three-dimensional structure of a real face, and the accuracy of the virtual face image generated by face pinching is improved.
Owner:TENCENT TECH (SHENZHEN) CO LTD

3D face reconstruction from gate camera

A method of creating a 3-dimensional facial reconstruction of a user of a transit system includes detecting a user within a range of an image capture device positioned at a transit access point. A plurality of images of a first portion of the user's face are captured using the image capture device while the user passes through the range of the image capture device. A plurality of positions of the user may be detected as the user passes through the range of the image capture device. The plurality of images are combined with the plurality of positions and a relative angle and position of the user's face are calculated based on the combination of the plurality of images and the plurality of positions. A 3-dimensional model of the first portion of the user's face is generated based on the calculated relative angle and position and the 3-dimensional model is stored.
Owner:CUBIC CORPORATION

3D face reconstruction method based on multi-view mobile phone selfie images

The invention discloses a three-dimensional facial reconstruction method based on multi-view cellphone selfie pictures. The three-dimensional facial reconstruction method includes automatically positioning mark points on selfie face images of a same person from n different angles; setting up a first energy function according to the mark points and solving a camera parameter Pk (k=1,....,N), wherein in the first energy function, I is pixel serial number, k is input image vision number, mi is the ith mark point, Xi is three-dimensional point coordinate corresponding to the ith mark point, and Pk is a projection transformation matrix from a three-dimensional point to the corresponding image; reconstructing a target function E=Edata+Ecolor+Esmooth according to the camera parameter, optimizing the target function and using a multi-tag image partition algorithm to solve the target function to obtain a three-dimensional facial model. By the three-dimensional facial reconstruction method, the accurate three-dimensional facial model can be reconstructed quickly by the cellphone selfie images.
Owner:WISESOFT CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products