Iterative cage-based registration for dynamic shape capture

  • Authors:
  • Yann Savoye

  • Affiliations:
  • INRIA Bordeaux University, France

  • Venue:
  • ACM SIGGRAPH 2012 Posters
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Recent advances in low-cost dynamic scanning turn the cross-parametrization of non-rigid animatable surface into a vision-oriented ill-posed problem. In contrast with [Li et al. 2012], we propose a novel detail-preserving registration approach with resolution-independent control. Furthermore, our skin-detached surface registration avoids patch-based segmentation or affine fitting to maintain the local plasticity, as required in [Budd and Hilton 2010]. In particular, we leverage the problem of highly non-rigid spacetime registration by employing an elasto-plastic coarse cage. Thus, we perform scalable handle-aware harmonic shape registration, relying on the high-level of shape abstraction offered by the space-based paradigm. To the best of our knowledge, our technique is the first to investigate handle-aware elastic overlapping-rigidities for registering life-like dynamic shapes in full-body clothing.