Cage-based Performance Capture

  • Yann Savoye

Part of the Studies in Computational Intelligence book series (SCI, volume 509)

Table of contents

  1. Front Matter
    Pages i-x
  2. Yann Savoye
    Pages 1-15
  3. Yann Savoye
    Pages 53-92
  4. Yann Savoye
    Pages 93-134
  5. Yann Savoye
    Pages 135-141

About this book


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.


Cage-Based Performance Computational Intelligence Computer Vision Graphic to Vision Performance Animation Performance Capture

Authors and affiliations

  • Yann Savoye
    • 1
  1. 1.LyonFrance

Bibliographic information

  • DOI
  • Copyright Information Springer International Publishing Switzerland 2014
  • Publisher Name Springer, Cham
  • eBook Packages Engineering
  • Print ISBN 978-3-319-01537-8
  • Online ISBN 978-3-319-01538-5
  • Series Print ISSN 1860-949X
  • Series Online ISSN 1860-9503
  • About this book