[go: up one dir, main page]

WO2018010535A1 - Procédé et appareil basés sur un modèle de source 3d destinés à l'édition d'un modèle cible 3d - Google Patents

Procédé et appareil basés sur un modèle de source 3d destinés à l'édition d'un modèle cible 3d Download PDF

Info

Publication number
WO2018010535A1
WO2018010535A1 PCT/CN2017/089715 CN2017089715W WO2018010535A1 WO 2018010535 A1 WO2018010535 A1 WO 2018010535A1 CN 2017089715 W CN2017089715 W CN 2017089715W WO 2018010535 A1 WO2018010535 A1 WO 2018010535A1
Authority
WO
WIPO (PCT)
Prior art keywords
source
model
target
deformation
transformation matrix
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2017/089715
Other languages
English (en)
Chinese (zh)
Inventor
吴松城
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
XIAMEN HUANSHI NETWORK TECHNOLOGY Co Ltd
Original Assignee
XIAMEN HUANSHI NETWORK TECHNOLOGY Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by XIAMEN HUANSHI NETWORK TECHNOLOGY Co Ltd filed Critical XIAMEN HUANSHI NETWORK TECHNOLOGY Co Ltd
Publication of WO2018010535A1 publication Critical patent/WO2018010535A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T19/00—Manipulating 3D models or images for computer graphics
    • G06T19/20—Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts

Definitions

  • the present application relates to the field of 3D model design, and in particular, to a method and device for editing a 3D model.
  • 3D is the abbreviation of English “3Dimensions”
  • Chinese refers to three-dimensional, three-dimensional or three-coordinates
  • 3D represents a space composed of three directions of length, width and height, which is relative to a plane with only length and width.
  • the 3D model refers to a three-dimensional, three-dimensional model, usually a three-dimensional model constructed with three-dimensional design software, including various buildings, characters, vegetation, machinery, etc., such as a 3D model map of a building, a 3D model map of a character, and the like.
  • the user After the user reconstructs the 3D model based on the actual object, it may be desirable to adjust the 3D model.
  • the 3D model of a person the user may wish to adjust the face of the 3D model and various parts of the body, such as wanting to sharpen the nose and enlarge the eyes.
  • the user may wish to make similar adjustments to their 3D model in accordance with other user adjustments.
  • the prior art can only simply reconstruct the 3D model, and cannot adjust it freely and flexibly.
  • the embodiment of the present application provides a method and apparatus for editing a 3D target model based on a 3D source model, and aims to provide a user with a 3D source model to edit their own 3D target model.
  • the method meets the actual needs of the user.
  • a method for editing a 3D target model based on a 3D source model includes:
  • the preset condition includes one or more of the following conditions:
  • a first difference between a target transformation matrix of the 3D target model and the source transformation matrix is minimum
  • the weighted summation of the first gap and the second gap is the smallest.
  • the 3D target model that meets a preset condition is determined according to the source transformation matrix and the first original coordinate.
  • the first new coordinates of each vertex including:
  • the method for determining the first new coordinate according to the target transformation matrix and the first original coordinate includes:
  • the source transformation matrix when the 3D source model is deformed is obtained, which includes:
  • the source parameter information includes at least two of a source variant of the 3D source model, a second original coordinate of each vertex, and a second new coordinate of each vertex, And the sum of the second original coordinate and the source deformation formula is equal to the second new coordinate;
  • a product of a matrix formed by the second new coordinates and an inverse matrix of a matrix formed by the second original coordinates is calculated as the source transformation matrix.
  • the source deformation type when the 3D source model is deformed is obtained, including:
  • the source deformation formula is determined according to a source deformation parameter of the 3D source model.
  • the source deformation parameter includes at least one source deformation amount and a corresponding source deformation amount weight thereof, according to the 3D source model.
  • the source deformation parameter determines that the source deformation formula is specifically:
  • a sum of products of the respective source deformation amounts and their corresponding source deformation amount weights is calculated as the source deformation equation.
  • the source deformation type when the 3D source model is deformed is obtained, including:
  • the difference between the second new coordinate and the second original coordinate is taken as the source deformation formula.
  • the first original coordinate, the first new coordinate, and the target deformation are satisfied:
  • the sum of the first original coordinate and the target deformation is equal to the first new coordinate.
  • the application also provides an apparatus for editing a 3D target model based on a 3D source model, including:
  • a first acquiring module configured to acquire a source transformation matrix when the 3D source model is deformed
  • a second acquiring module configured to acquire first original coordinates of each vertex of the 3D target model
  • a first calculating module configured to determine, according to the source transformation matrix and the first original coordinate, a first new coordinate of each vertex of the 3D target model when a preset condition is met;
  • the preset condition includes one or more of the following conditions:
  • the weighted summation of the first gap and the second gap is the smallest.
  • the 3D target model refers to a model that the user desires to perform deformation
  • the 3D source model refers to a model that the user desires to refer to for deformation.
  • the user calculates the vertex coordinates after the deformation of the 3D target model that satisfies the preset condition, and determines the vertex coordinates to determine the 3D target model after the deformation, which achieves the technical purpose of the present application.
  • the preset condition may be taken as any one or combination of the following three conditions: the first difference between the target transformation matrix of the target model and the source transformation matrix is minimum; the target deformation of the target model The second difference from the source variant of the source model is minimal; the weighted sum of the first gap and the second gap is minimal.
  • the transformation matrix of the target model and/or the source model represents a nonlinear relationship before and after the deformation of the model, and the deformation of the target model and/or the source model represents a linear relationship before and after the deformation of the model, and the target model is required by an alternative or a combination.
  • the linear relationship and/or the nonlinear relationship of the source model are as close as possible (requiring the minimum gap), so that the target model after the deformation calculated on the premise of satisfying the above preset conditions is a model deformed by the reference source model.
  • FIG. 1 is a schematic flow chart of a method for editing a 3D target model based on a 3D source model in an embodiment of the present application
  • FIG. 2 is a schematic flow chart of a method for editing a 3D target model based on a 3D source model in the embodiment of the present application;
  • FIG. 3 is a schematic flow chart of a third method for editing a 3D target model based on a 3D source model in an embodiment of the present application
  • FIG. 4 is a schematic structural diagram of an apparatus for editing a 3D target model based on a 3D source model in an embodiment of the present application.
  • a method for editing a 3D target model based on a 3D source model is provided in an embodiment of the present application.
  • the 3D target model refers to a model that the user desires to deform
  • the 3D source model refers to a model that the user desires to be deformed as a reference, that is, the user desires to refer to the deformation mode of the 3D source model to be similar to the 3D target model. Transformation.
  • a method for editing a 3D target model based on a 3D source model includes:
  • S101 Acquire a source transformation matrix and/or a source deformation formula when the 3D source model is deformed
  • S103 Determine, according to the source transformation matrix and the first original coordinate, a first new coordinate of each vertex of the 3D target model when the preset condition is met; wherein the preset condition includes one or more of the following conditions:
  • step S101 and step S102 are not divided, and may not be limited.
  • the purpose of performing step S101 is to obtain a manner in which the 3D source model is deformed, and is represented by a source transformation matrix and/or a source deformation equation when the 3D source model is deformed.
  • the source transformation matrix embodies a nonlinear transformation relationship before and after deformation of the 3D source model.
  • X represents a matrix composed of second original coordinates of each vertex before deformation of the 3D source model
  • Y represents a deformation of the 3D source model.
  • the matrix formed by the second new coordinates of each vertex, with T representing the source transformation matrix of the 3D source model satisfies:
  • the source transformation matrix T of the 3D source model can be obtained by multiplying the constructed matrix by the inverse matrix of the matrix formed by the second original coordinates, as shown in FIG.
  • step S1011 may be performed to obtain source parameter information of the 3D source model.
  • the source parameter information includes a source deformed form of the 3D source model, a second original coordinate of each vertex, and a second new coordinate of each vertex. Since the source deformation type reflects the linear transformation relationship before and after the deformation of the 3D source model, the sum of the second original coordinate and the source deformation is satisfied, which is equal to the second new coordinate. Therefore, when performing step S1011, only two of the source parameter information are acquired. The third item can be determined.
  • a matrix composed of the second original coordinates of the vertices before the deformation of the 3D source model is represented by X
  • a matrix composed of the second new coordinates of the vertices after the deformation of the 3D source model is represented by Y
  • the 3D source is represented by TAR.
  • the source variant of the model, then X, Y, and TAR satisfy:
  • the source deformation formula may be preferably determined according to the source deformation parameter of the 3D source model.
  • the source deformation parameter may be selected by the user in a plurality of source deformation parameters preset by the system, and when selected, by clicking different buttons, It can be performed by dragging different progress bars and other methods; the source deformation parameter can also be set by the user directly inputting the value, and the system can preset the value range and/or the change step size to adjust the value input by the user;
  • the deformation parameter can also be automatically set and/or selected according to a preset rule according to the user's login status and/or usage.
  • the system can automatically Set the source deformation parameter of the user 3D source model, so that the user's 3D source model becomes fat, and the source deformation parameter set by the system can be associated with the user's continuous unregistered time, thereby making the 3D source model fatter and the user
  • the continuous unregistered time also establishes a correspondence.
  • the source deformation parameter includes at least one source deformation amount and a corresponding source deformation amount weight thereof
  • determining the source deformation type according to the source deformation parameter of the 3D source model is: calculating each source deformation amount and its corresponding source deformation amount weight The sum of the products as the source deformation.
  • the source deformation amount of the 3D source model is represented by target, and the source deformation amount weight corresponding to the source deformation amount target is represented by w.
  • the source deformation TAR of the 3D source model can be expressed as:
  • the interactive interface that deforms the 3D source model pops up a plurality of target source deformation targets, and the user can select the target that he wants to adjust according to the needs, and set the source with the slider or the like.
  • target represents the change value. Through this change value, we can know which part of the 3D source model and its corresponding change amount we want to adjust; w represents the weight of the change value corresponding to the target. For example, the target is to sharpen the nose, then the role of w is to specify the degree of this sharpening.
  • the source deformation amount target is a preset value, and the degree of the deformation can be changed by adjusting the source deformation amount weight w. For example, initially the nose has a sharpness of 0, and the target is to sharpen the nose to 5 (assuming the larger the value, the sharper the nose). By adjusting w to 0 to 2, the range of the nose can be sharpened to 0-10.
  • the user's 3D avatar is composed of vertex and face, and a 3D avatar includes about 6000 vertices and more than 10,000 faces. Therefore, for simplification, the change in the source deformation amount target is preferably for the vertices of the 3D avatar.
  • Each adjusted attribute will have a corresponding target and w, so this part of the data contains w 1 , target 1 , w 2 , target 2 and so on.
  • the source deformation amount target corresponds to the same or different vertices, and represents the amount of deformation of the vertices in the 3D source model.
  • the first one is that these changes are different, that is, each target is deformed for different vertices, assuming that the entire 3D avatar has 5 vertices, and the value of target 1 is [0, 0.1, 0, 0,0], indicating a change of 0.1 to the second vertex; for the value of target 2 is [0,0,0.1,0,0], indicating a change of 0.1 to the third vertex; for target 3
  • target 4 is [0, 0.1, 0, 0, 0], indicating a change of 0.1 to the second vertex.
  • the difference between the new coordinate and the second original coordinate is used as the source deformation.
  • the user's 3D source model model1 already exists, and then the user inputs another picture, such as a picture with an expression, and the user wishes to transform the 3D source model model1 into a 3D source model model model2 with an expression on the picture, and the user bases
  • the input image determines the second new coordinate of each vertex of the 3D source model, and the 3D source model model2 can be reconstructed.
  • the target transformation matrix For the 3D target model, there is also a linear transformation represented by the target deformation formula between the first original coordinate of each vertex of the 3D target model before the transformation and the first new coordinate of each vertex of the transformed 3D target model.
  • the relationship and the nonlinear transformation relationship embodied by the target transformation matrix.
  • a matrix composed of the second original coordinates of the vertices before the deformation of the 3D target model is represented by X t
  • a matrix composed of the second new coordinates of the vertices after the deformation of the 3D target model is represented by Y t
  • T t is used.
  • the target transformation matrix representing the 3D target model, and the TAR t representing the target deformation of the 3D target model satisfies:
  • the preset condition includes one or more of the following conditions:
  • the preset condition of item (1) can be expressed as min
  • the preset condition of item (2) can be expressed as min
  • the preset condition can be expressed as min(m*
  • the calculation process of the first new coordinate of each vertex of the 3D target model when the preset condition is satisfied is described below by taking the preset condition of the item (1) as an example.
  • the precondition (1) can be expressed as:
  • V 1 , V 2 and V 3 respectively, and constitute a triangle i.
  • (V 4 - V 1 ) is a cross multiplication value of (V 2 - V 1 ) and (V 3 - V 1 ), and represents a normal vector of the source model plane triangle i. It will be appreciated by those skilled in the art that other triangles of the face triangle i can also be used to express the triangle.
  • the source model face triangle i is deformed to obtain a new source model face triangle i', and the three vertices of the source model face triangle i' are V 1 ', V 2 ', and V 3 ', respectively.
  • Vertex V 1 ' corresponding to the coordinates of the vertices of V 1' (V 1x ', V 1y', V 1z ')
  • the vertex V 2' corresponding to the coordinates of the vertices of V 2 '(V 2x', V 2y ', V 2z' )
  • the vertex V 3 ' correspond to the coordinates of the vertex V 3' (V 3x ', V 3y', V 3z ')
  • the second obtained new coordinates can be expressed as:
  • (V 4 '-V 1 ') is a cross-multiplier value of (V 2 '-V 1 ') and (V 3 '-V 1 '), and represents a normal vector of the source model surface triangle i' after the deformation.
  • min
  • the source transformation matrix T(i) can be expressed as:
  • b 11 -(a 11 +a 21 +a 31 )*V 1x '+a 11 *V 2y '+a 22 *V 3y '+a 32 *V 4y ',
  • b 12 -(a 12 +a 22 +a 32 )*V 1y '+a 12 *V 2y '+a 22 *V 3y '+a 32 *V 4y ',
  • the target transformation matrix T t (i) can be expressed as Among them, you can Matrixing, expressed as:
  • the parameter is the above matrix A t Required for expression [a ij] t, in particular, determined by the first known target model original coordinate X t (i) [a ij ] t.
  • Coordinate vector Indicates the first new coordinate Y t (i) after the deformation of the target model.
  • min
  • can be converted to calculate min
  • the matrix A t is determined by the coordinates of the first original target model, a known quantity
  • transformation matrix B is determined by the source of the source model, a known quantity. Therefore, the first new coordinate V t ' of the 3D target model can be obtained by solving the above formula.
  • the target transformation matrix of the 3D target model when the preset condition is satisfied may also be calculated by referring to the above method; then, the first transformation is determined according to the target transformation matrix and the first original coordinate.
  • the new coordinates are shown in Figure 2.
  • the above is an example of calculating the first new coordinates of the vertices of the 3D target model when the preset condition of the item (1) is satisfied.
  • the second difference between the target deformed TAR t of the target model and the source deformed TAR of the source model is required to be the smallest, that is, it is required to satisfy min
  • the pre-conditions of this item can be jointly examined in conjunction with the pre-set conditions of item (1) and/or item (3).
  • the weighted summation of the first gap and the second gap is required to be the smallest, that is, the requirement to satisfy min(m*
  • both the linear transformation relationship before and after the deformation of the model is considered, and the nonlinear transformation relationship before and after the deformation of the model is considered, which can better transplant the deformation mode of the source model to the target model, and achieve better.
  • Technical effect
  • the present application also provides an apparatus for editing a 3D target model based on a 3D source model, as shown in FIG. 3, including:
  • the first obtaining module 101 is configured to acquire a source transformation matrix and/or a source deformation formula when the 3D source model is deformed;
  • a second acquiring module 102 configured to acquire first original coordinates of each vertex of the 3D target model
  • a first calculating module 103 configured to determine, according to the source transformation matrix and the first original coordinate, a first new coordinate of each vertex of the 3D target model when the preset condition is met; wherein the preset condition includes one or more of the following conditions One:
  • the first difference between the target transformation matrix and the source transformation matrix of the 3D target model is minimal
  • the second difference between the target deformation of the 3D target model and the source deformation of the source model is minimal
  • the weighted summation of the first gap and the second gap is minimal.
  • the device corresponds to the foregoing embodiments and implementation principles of the method for editing a 3D object model based on a 3D source model, and details are not described herein again.
  • embodiments of the present invention can be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware. Moreover, the invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
  • computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in a block or blocks of a flow or a flow and/or a block diagram of a flowchart Step.
  • a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • the memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory.
  • RAM random access memory
  • ROM read only memory
  • Memory is an example of a computer readable medium.
  • Computer readable media includes both permanent and non-persistent, removable and non-removable media.
  • Information storage can be implemented by any method or technology.
  • the information can be computer readable instructions, data structures, modules of programs, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory. (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape storage or other magnetic storage devices or any other non-transportable media can be used to store information that can be accessed by a computing device.
  • computer readable media does not include temporary storage of computer readable media, such as modulated data signals and carrier waves.
  • embodiments of the present application can be provided as a method, system, or computer program product.
  • the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment in combination of software and hardware.
  • the application may be embodied in one or more of A computer program product embodied on a computer usable storage medium (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer usable program code.

Landscapes

  • Engineering & Computer Science (AREA)
  • Architecture (AREA)
  • Computer Graphics (AREA)
  • Computer Hardware Design (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Processing Or Creating Images (AREA)

Abstract

La présente invention concerne un procédé et un appareil basés sur un modèle de source 3D destinés à l'édition d'un modèle cible 3D. Le procédé consiste : à obtenir une matrice de transformation de source et/ou d'une forme de transformation de source lorsqu'un mode de source 3D est transformé ; à obtenir de premières coordonnées originales de chaque sommet d'un modèle cible 3D ; et à déterminer, en fonction de la matrice de transformation de source et des premières coordonnées d'origine, des premières nouvelles coordonnées de chaque sommet du modèle cible 3D lorsque des conditions prédéterminées sont satisfaites, les conditions prédéfinies comprenant une ou plusieurs des conditions suivantes : une première différence entre une matrice de transformation cible du modèle cible 3D et la matrice de transformation source est la plus petite, une seconde différence entre une forme de transformation cible du modèle cible 3D et la forme de transformation source du modèle source étant la plus petite, et une somme pondérée de la première différence et de la seconde différence est la plus petite. La présente invention concerne un appareil basé sur un modèle de source 3D destiné à l'édition d'un modèle cible 3D. L'appareil comprend un premier module d'obtention, un second module d'obtention et un premier module de calcul. La présente invention porte sur un procédé et un appareil destinés à éditer un modèle cible 3D en se référant à un modèle source 3D, et satisfait les exigences réelles des utilisateurs.
PCT/CN2017/089715 2016-07-11 2017-06-23 Procédé et appareil basés sur un modèle de source 3d destinés à l'édition d'un modèle cible 3d Ceased WO2018010535A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610542436.2 2016-07-11
CN201610542436.2A CN106204750B (zh) 2016-07-11 2016-07-11 一种基于3d源模型编辑3d目标模型的方法及装置

Publications (1)

Publication Number Publication Date
WO2018010535A1 true WO2018010535A1 (fr) 2018-01-18

Family

ID=57476285

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/089715 Ceased WO2018010535A1 (fr) 2016-07-11 2017-06-23 Procédé et appareil basés sur un modèle de source 3d destinés à l'édition d'un modèle cible 3d

Country Status (2)

Country Link
CN (1) CN106204750B (fr)
WO (1) WO2018010535A1 (fr)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106204750B (zh) * 2016-07-11 2020-06-30 厦门黑镜科技有限公司 一种基于3d源模型编辑3d目标模型的方法及装置
CN107103646B (zh) * 2017-04-24 2020-10-23 厦门黑镜科技有限公司 一种表情合成方法及装置
CN109409274B (zh) * 2018-10-18 2020-09-04 四川云从天府人工智能科技有限公司 一种基于人脸三维重建和人脸对齐的人脸图像变换方法
CN114733201A (zh) * 2022-04-19 2022-07-12 网易（杭州）网络有限公司 虚拟装备模型的适配方法、装置及终端设备

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101071514A (zh) * 2006-05-12 2007-11-14 中国科学院自动化研究所 一种直接传递三维模型姿态的方法
US8112254B1 (en) * 2008-05-01 2012-02-07 Lucasfilm Entertainment Company Ltd. Transferring surface attributes across geometric models
CN104183002A (zh) * 2013-05-27 2014-12-03 索尼公司 三维模型的变化方法和装置
CN104732585A (zh) * 2015-03-23 2015-06-24 腾讯科技（深圳）有限公司 一种人体体型重构的方法及装置
CN105654334A (zh) * 2015-12-17 2016-06-08 中国科学院自动化研究所 虚拟试衣方法和系统
CN106204750A (zh) * 2016-07-11 2016-12-07 厦门幻世网络科技有限公司 一种基于3d源模型编辑3d目标模型的方法及装置

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103035022B (zh) * 2012-12-07 2015-04-01 大连大学 基于特征点的人脸表情合成方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101071514A (zh) * 2006-05-12 2007-11-14 中国科学院自动化研究所 一种直接传递三维模型姿态的方法
US8112254B1 (en) * 2008-05-01 2012-02-07 Lucasfilm Entertainment Company Ltd. Transferring surface attributes across geometric models
CN104183002A (zh) * 2013-05-27 2014-12-03 索尼公司 三维模型的变化方法和装置
CN104732585A (zh) * 2015-03-23 2015-06-24 腾讯科技（深圳）有限公司 一种人体体型重构的方法及装置
CN105654334A (zh) * 2015-12-17 2016-06-08 中国科学院自动化研究所 虚拟试衣方法和系统
CN106204750A (zh) * 2016-07-11 2016-12-07 厦门幻世网络科技有限公司 一种基于3d源模型编辑3d目标模型的方法及装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
QU, HANBING ET AL.: "Probabilistic Graphical Model for Robust Point Set Matching", ACTA AUTOMATICA SINICA, vol. 41, no. 4, 30 April 2015 (2015-04-30), pages 694 - 710 *

Also Published As

Publication number Publication date
CN106204750B (zh) 2020-06-30
CN106204750A (zh) 2016-12-07

Similar Documents

Publication Publication Date Title
KR102170105B1 (ko) 신경 네트워크 구조의 생성 방법 및 장치, 전자 기기, 저장 매체
US10089781B2 (en) Three-dimensional point cloud model reconstruction method, computer readable storage medium and device
CN110162567B (zh) 基于颜色表优化的二维标量场数据可视化方法及系统
Campen et al. Practical anisotropic geodesy
WO2020228522A1 (fr) Procédé et appareil de suivi de cible, support de stockage et dispositif électronique
US9536339B1 (en) Processing unordered point cloud
CN109767466B (zh) 画面渲染方法、装置、终端及对应的存储介质
CN108399383A (zh) 表情迁移方法、装置存储介质及程序
WO2017092592A1 (fr) Procédé, appareil et dispositif de fusion d'image
WO2018010535A1 (fr) Procédé et appareil basés sur un modèle de source 3d destinés à l'édition d'un modèle cible 3d
US10559116B2 (en) Interactive caricature generation from a digital image
WO2018145568A1 (fr) Procédé et dispositif permettant de générer un modèle de surface d'arc
US20160335758A1 (en) Methods and systems for characterizing concept drawings and estimating three-dimensional information therefrom
CN109584145A (zh) 卡通化方法和装置、电子设备和计算机存储介质
CN111768353B (zh) 一种三维模型的孔洞填补方法及装置
CN115004293B (zh) 估计图像中的三维手势的方法、装置和计算机系统
Bodzioch et al. On the degenerate oblique derivative problem for elliptic second-order equation in a domain with boundary conical point
US10115009B2 (en) Body relationship estimation method and apparatus
Zhan et al. Boundary correspondence for iso-geometric analysis based on deep learning
CN113111687A (zh) 数据处理方法、系统及电子设备
CN110246224B (zh) 网格模型的表面去噪方法及系统
Liu et al. An adaptive texture-preserved image denoising model
US12217364B2 (en) 3D modeling user interfaces by introducing improved coordinates for triquad cages
Zhou et al. A degree-based topological optimization method for triangular meshes
US12243135B2 (en) Vector object blending

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17826873

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 25.04.2019)

122 Ep: pct application non-entry in european phase

Ref document number: 17826873

Country of ref document: EP

Kind code of ref document: A1