Cage-based Performance Capture

Detalles Bibliográficos
Autor Principal: Savoye, Yann
Formato: Libro
Lengua:inglés
Datos de publicación: Cham : Springer International Publishing : Imprint: Springer, 2014.
Series:Studies in Computational Intelligence, 509
Temas:
Engineering.
Image processing.
Computational intelligence.
Artificial Intelligence (incl. Robotics).
Image Processing and Computer Vision.
Acceso en línea:http://dx.doi.org/10.1007/978-3-319-01538-5
Resumen:Nowadays, highly-detailed animations of live-actor performances are increasingly easier to acquire and 3D Video has reached considerable attentions in visual media production. In this book, we address the problem of extracting or acquiring and then reusing non-rigid parametrization for video-based animations. At first sight, a crucial challenge is to reproduce plausible boneless deformations while preserving global and local captured properties of dynamic surfaces with a limited number of controllable, flexible and reusable parameters. To solve this challenge, we directly rely on a skin-detached dimension reduction thanks to the well-known cage-based paradigm. First, we achieve Scalable Inverse Cage-based Modeling by transposing the inverse kinematics paradigm on surfaces. Thus, we introduce a cage inversion process with user-specified screen-space constraints. Secondly, we convert non-rigid animated surfaces into a sequence of optimal cage parameters via Cage-based Animation Conversion. Building upon this reskinning procedure, we also develop a well-formed Animation Cartoonization algorithm for multi-view data in term of cage-based surface exaggeration and video-based appearance stylization. Thirdly, motivated by the relaxation of prior knowledge on the data, we propose a promising unsupervised approach to perform Iterative Cage-based Geometric Registration. This novel registration scheme deals with reconstructed target point clouds obtained from multi-view video recording, in conjunction with a static and wrinkled template mesh. Above all, we demonstrate the strength of cage-based subspaces in order to reparametrize highly non-rigid dynamic surfaces, without the need of secondary deformations. To the best of our knowledge this book opens the field of Cage-based Performance Capture.
Descripción Física:x, 141 p. : il.
ISBN:9783319015385
ISSN:1860-949X ;
DOI:10.1007/978-3-319-01538-5

MARC

LEADER 00000Cam#a22000005i#4500
001 INGC-EBK-000225
003 AR-LpUFI
005 20220927105724.0
007 cr nn 008mamaa
008 130917s2014 gw | s |||| 0|eng d
020 |a 9783319015385 
024 7 |a 10.1007/978-3-319-01538-5  |2 doi 
050 4 |a Q342 
072 7 |a UYQ  |2 bicssc 
072 7 |a COM004000  |2 bisacsh 
100 1 |a Savoye, Yann.   |9 260492 
245 1 0 |a Cage-based Performance Capture   |h [libro electrónico] /   |c by Yann Savoye. 
260 1 |a Cham :  |b Springer International Publishing :  |b Imprint: Springer,  |c 2014. 
300 |a x, 141 p. :   |b il. 
336 |a text  |b txt  |2 rdacontent 
337 |a computer  |b c  |2 rdamedia 
338 |a online resource  |b cr  |2 rdacarrier 
347 |a text file  |b PDF  |2 rda 
490 1 |a Studies in Computational Intelligence,  |x 1860-949X ;  |v 509 
505 0 |a General Introduction -- Sparse Constraints Over Animatable Subspaces -- Reusing Performance Capture Data -- Toward Non-Rigid Dynamic Cage Capture. 
520 |a Nowadays, highly-detailed animations of live-actor performances are increasingly easier to acquire and 3D Video has reached considerable attentions in visual media production. In this book, we address the problem of extracting or acquiring and then reusing non-rigid parametrization for video-based animations. At first sight, a crucial challenge is to reproduce plausible boneless deformations while preserving global and local captured properties of dynamic surfaces with a limited number of controllable, flexible and reusable parameters. To solve this challenge, we directly rely on a skin-detached dimension reduction thanks to the well-known cage-based paradigm. First, we achieve Scalable Inverse Cage-based Modeling by transposing the inverse kinematics paradigm on surfaces. Thus, we introduce a cage inversion process with user-specified screen-space constraints. Secondly, we convert non-rigid animated surfaces into a sequence of optimal cage parameters via Cage-based Animation Conversion. Building upon this reskinning procedure, we also develop a well-formed Animation Cartoonization algorithm for multi-view data in term of cage-based surface exaggeration and video-based appearance stylization. Thirdly, motivated by the relaxation of prior knowledge on the data, we propose a promising unsupervised approach to perform Iterative Cage-based Geometric Registration. This novel registration scheme deals with reconstructed target point clouds obtained from multi-view video recording, in conjunction with a static and wrinkled template mesh. Above all, we demonstrate the strength of cage-based subspaces in order to reparametrize highly non-rigid dynamic surfaces, without the need of secondary deformations. To the best of our knowledge this book opens the field of Cage-based Performance Capture. 
650 0 |a Engineering.  |9 259622 
650 0 |a Image processing.  |9 259604 
650 0 |a Computational intelligence.  |9 259845 
650 2 4 |a Artificial Intelligence (incl. Robotics).  |9 259846 
650 2 4 |a Image Processing and Computer Vision.  |9 259608 
776 0 8 |i Printed edition:  |z 9783319015378 
856 4 0 |u http://dx.doi.org/10.1007/978-3-319-01538-5 
912 |a ZDB-2-ENG 
929 |a COM 
942 |c EBK  |6 _ 
950 |a Engineering (Springer-11647) 
999 |a SKV  |c 27653  |d 27653 

Ejemplares similares