Cage-based Performance Capture

Nonfiction, Computers, Advanced Computing, Artificial Intelligence, Application Software, Computer Graphics, General Computing
Cover of the book Cage-based Performance Capture by Yann Savoye, Springer International Publishing
View on Amazon View on AbeBooks View on Kobo View on B.Depository View on eBay View on Walmart
Author: Yann Savoye ISBN: 9783319015385
Publisher: Springer International Publishing Publication: September 17, 2013
Imprint: Springer Language: English
Author: Yann Savoye
ISBN: 9783319015385
Publisher: Springer International Publishing
Publication: September 17, 2013
Imprint: Springer
Language: English

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.

View on Amazon View on AbeBooks View on Kobo View on B.Depository View on eBay View on Walmart

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.

More books from Springer International Publishing

Cover of the book Management and Leadership Skills for Medical Faculty by Yann Savoye
Cover of the book Advances in Human Factors in Simulation and Modeling by Yann Savoye
Cover of the book Coping with Demographic Change: A Comparative View on Education and Local Government in Germany and Poland by Yann Savoye
Cover of the book Jaya: An Advanced Optimization Algorithm and its Engineering Applications by Yann Savoye
Cover of the book Recent Trends in Algebraic Development Techniques by Yann Savoye
Cover of the book Supporting Young Men as Fathers by Yann Savoye
Cover of the book Information Technology and Systems by Yann Savoye
Cover of the book Grandparents of Children with Disabilities by Yann Savoye
Cover of the book Nutrition and Health in a Developing World by Yann Savoye
Cover of the book Visible Light Photocatalyzed Redox-Neutral Organic Reactions and Synthesis of Novel Metal-Organic Frameworks by Yann Savoye
Cover of the book Cityscape in the Era of Information and Communication Technologies by Yann Savoye
Cover of the book Sustainable Business Models by Yann Savoye
Cover of the book New Directions in Third Wave Human-Computer Interaction: Volume 1 - Technologies by Yann Savoye
Cover of the book Intraocular Surgery by Yann Savoye
Cover of the book Mind in Action by Yann Savoye
We use our own "cookies" and third party cookies to improve services and to see statistical information. By using this website, you agree to our Privacy Policy