公开(公告)号：JP2000113217A

公开(公告)日：2000-04-21

申请号：JP27936999

申请日：1999-09-30

Applicant: CSELT CENTRO STUDI LAB TELECOM

Inventor： FRANCINI GIANLUCA ,  QUAGLIA MAURO

IPC: G06T11/00 ,  G06T15/04 ,  G06T17/10 ,  G06T17/20 ,  G06T17/00

Abstract: PROBLEM TO BE SOLVED: To provide a method capable of producing a face model with reality in both a still state and an animation state. SOLUTION: This method is capable of producing a 3D face model and being used, for instance, for the realization of an incarnation (avatar), video communication use, a video game, video production and the production of an advanced man-machine interface. At least one human facial image is given together with a 3D face model M having a summit structure. The 3D face model M includes several surfaces selected from a set consisting of a face surface V, a right eye surface OD, a left eye surface OS, an upper teeth surface DS and a lower teeth surface DI. A set of corresponding points among vertexes of the model M surface and a set of corresponding points on at least one facial image are respectively selected. Next, the model structure M is corrected so that the respective sets of the corresponding points can be coincided with each other.

公开(公告)号：IT1320002B1

公开(公告)日：2003-11-12

申请号：ITTO20000303

申请日：2000-03-31

Applicant: CSELT CENTRO STUDI LAB TELECOM

Inventor： FRANCINI GIANLUCA ,  LANDE CLAUDIO ,  LEPSOY SKJALG ,  QUAGLIA MAURO

IPC: G06T13/20 ,  G06T13/40 ,  G10L13/00 ,  G10L21/06

公开(公告)号：ITTO980828A1

公开(公告)日：2000-04-03

申请号：ITTO980828

申请日：1998-10-02

Applicant: CSELT CENTRO STUDI LAB TELECOM

Inventor： FRANCINI GIANLUCA ,  QUAGLIA MAURO

IPC: G06T11/00 ,  G06T15/04 ,  G06T17/10 ,  G06T17/20

Abstract: The described method of creating a texture for 3-D models (M) starting from a plurality of images (I) comprises the operations of: providing said plurality of images (I) corresponding to different points of sight; providing a 3-D model (M) having a vertex structure; modifying the structure of said 3-D model (M) starting from said plurality of images (I); creating the texture to be applied to said model (M) by generating, for each of said images, a respective texture information in the form of right triangles of constant size; coupling two by two the right triangles relating to the texture information generated from the plurality of images so as to obtain, as a result of the coupling, respective rectangles; and applying said texture to said modified 3-D model in the form of a matrix of said rectangles.

公开(公告)号：ITTO20000303A1

公开(公告)日：2001-10-01

申请号：ITTO20000303

申请日：2000-03-31

Applicant: CSELT CENTRO STUDI LAB TELECOM

Inventor： FRANCINI GIANLUCA ,  LANDE CLAUDIO ,  LEPSOY SKJALG ,  QUAGLIA MAURO

IPC: G06T13/20 ,  G06T13/40 ,  G10L13/00 ,  G10L21/06

公开(公告)号：CA2284348A1

公开(公告)日：2000-04-02

申请号：CA2284348

申请日：1999-10-01

Applicant: CSELT CENTRO STUDI LAB TELECOM

Inventor： FRANCINI GIANLUCA ,  QUAGLIA MAURO

IPC: G06T11/00 ,  G06T15/04 ,  G06T17/10 ,  G06T17/20

Abstract: The method allows the creation of 3-D facial models, which can be used, for instance, for the avatar implementation, video-communication applications, video games, video productions, and for the creation of advanced man-machine interfaces. At least one image of a human face is provided together with a 3D facial model (M) having a vertex structure and comprising a number of surfaces chosen within the set formed by a face surface (V), surfaces of the right eye (OD) and left eye (OS), respectively, and surfaces of the upper teeth (DS) and lower teeth (DI), respectively. Among the vertices of the structure of the model (M) and on such at least one face image, respective sets of homologous points are chosen. The model structure (M) is then modified in such a way that the above respective sets of homologous points are made to coincide (Figure 2).

公开(公告)号：IT1315446B1

公开(公告)日：2003-02-11

申请号：ITTO980828

申请日：1998-10-02

Applicant: CSELT CENTRO STUDI LAB TELECOM

Inventor： FRANCINI GIANLUCA ,  QUAGLIA MAURO

IPC: G06T11/00 ,  G06T15/04 ,  G06T17/10 ,  G06T17/20

Abstract: The described method of creating a texture for 3-D models (M) starting from a plurality of images (I) comprises the operations of: providing said plurality of images (I) corresponding to different points of sight; providing a 3-D model (M) having a vertex structure; modifying the structure of said 3-D model (M) starting from said plurality of images (I); creating the texture to be applied to said model (M) by generating, for each of said images, a respective texture information in the form of right triangles of constant size; coupling two by two the right triangles relating to the texture information generated from the plurality of images so as to obtain, as a result of the coupling, respective rectangles; and applying said texture to said modified 3-D model in the form of a matrix of said rectangles.

公开(公告)号：CA2284348C

公开(公告)日：2006-06-06

申请号：CA2284348

申请日：1999-10-01

Applicant: CSELT CENTRO STUDI LAB TELECOM

Inventor： QUAGLIA MAURO ,  FRANCINI GIANLUCA

IPC: G06T17/20 ,  G06T11/00 ,  G06T15/04 ,  G06T17/10

Abstract: The method allows the creation of 3-D facial models, which can be used, f or instance, for the avatar implementation, video-communication applications, video games, video productions, and for the creation of advanced man-machine interfaces. At least one image of a human face is provided together with a 3D facial mod el (M) having a vertex structure and comprising a number of surfaces chosen within the set formed by a face surface (V), surfaces of the right eye (OD) and left eye (OS), respectively, and surfaces of the upper teeth (DS) and lower teeth (DI), respectively. Among the vertices of the structure of the model (M) and on such at least on e face image, respective sets of homologous points are chosen. The model structure (M) is then modified in such a way that the above respective sets of homologous points are made to coincide.