Efficient reconstruction of nonrigid shape and motion from real-time 3D scanner data
Abstract
We present a new technique for reconstructing a single shape and its nonrigid motion from 3D scanning data. Our algorithm takes a set of time-varying unstructured sample points that capture partial views of a deforming object as input and reconstructs a single shape and a deformation field that fit the data. This representation yields dense correspondences for the whole sequence, as well as a completed 3D shape in every frame. In addition, the algorithm automatically removes spatial and temporal noise artifacts and outliers from the raw input data. Unlike previous methods, the algorithm does not require any shape template but computes a fitting shape automatically from the input data. Our reconstruction framework is based upon a novel topology-aware adaptive subspace deformation technique that allows handling long sequences with complex geometry efficiently. The algorithm accesses data in multiple sequential passes, so that long sequences can be streamed from hard disk, not being limited by main memory. We apply the technique to several benchmark datasets, significantly increasing the complexity of the data that can be handled efficiently in comparison to previous work.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Apr 01, 2009
- Source ID
- 10.1145/1516522.1516526
Entities
People
- Alexander Berner
- Andreas Schilling
- Bart Adams
- Hans-peter Seidel
- Leonidas J. Guibas
- Maksim Ovsjanikov
- Martin Bokeloh
- Michael Wand
- Philipp Jenke
Organizations
- Defense Advanced Research Projects Agency
- Max Planck Society
- National Institutes of Health
- National Science Foundation
- Saarland University
- Stanford University
- University of Tübingen