Dynamic Geometry Processing EG 2012 Tutorial Will Chang, Hao Li, - - PowerPoint PPT Presentation

dynamic geometry processing
SMART_READER_LITE
LIVE PREVIEW

Dynamic Geometry Processing EG 2012 Tutorial Will Chang, Hao Li, - - PowerPoint PPT Presentation

Dynamic Geometry Processing EG 2012 Tutorial Will Chang, Hao Li, Niloy Mitra, Mark Pauly, Michael Wand Tutorial: Dynamic Geometry Processing 1 Eurographics 2012, Cagliari, Italy Overview Speakers & Topics Eurographics 2012,


slide-1
SLIDE 1

Dynamic Geometry Processing

EG 2012 Tutorial

Will Chang, Hao Li, Niloy Mitra, Mark Pauly, Michael Wand

Tutorial: Dynamic Geometry Processing 1

slide-2
SLIDE 2

Eurographics 2012, Cagliari, Italy

Overview

Speakers & Topics

slide-3
SLIDE 3

Eurographics 2012, Cagliari, Italy

Presenters

Will Chang

University of California at San Diego, USA

Hao Li

Columbia University, USA

Niloy Mitra

University Colledge London, UK

Mark Pauly

EPFL Lausanne Switzerland

mark.pauly@epfl.ch wychang@cs.ucsd.edu hao@inf.ethz.ch n.mitra@cs.ucl.ac.uk

Michael Wand

Saarland University, MPI Informatik, Germany

mwand@mpi-inf.mpg.de

slide-4
SLIDE 4

Eurographics 2012, Cagliari, Italy

Course Webpage

Course Webpage

  • Updated slides
  • Literature & references
  • Additional material / data sets

Linked from:

  • http://www.mpi-inf.mpg.de/~mwand/
  • Available next week
slide-5
SLIDE 5

Eurographics 2012, Cagliari, Italy

What we cover

Basics

  • Motivation, data sources, problems
  • Basic correspondence estimation techniques

Dynamic Geometry Registration

  • Kinematic surfaces and geometric optical flow
  • Incremental deformable matching
  • Deformation graphs

Bringing it all together: State-of-the-art systems

  • Example 1: offline tracking system for articulated models
  • Example 2: real-time face tracking (“faceshift”)
slide-6
SLIDE 6

Eurographics 2012, Cagliari, Italy

Data Sources

Where does all the data come from?

slide-7
SLIDE 7

Eurographics 2012, Cagliari, Italy

Deformable Shape Matching

New technology

  • 3D animation scanners
  • Record 3D video
  • Active research area

Ultimate goal

  • 3D movie making
  • New creative perspectives

[P. Jenke, WSI/GRIS Tübingen]

slide-8
SLIDE 8

Eurographics 2012, Cagliari, Italy

Time-of-Flight / PMD Devices

8

PMD Time-of-flight camera

Minolta Laser Scanner (static)

slide-9
SLIDE 9

Eurographics 2012, Cagliari, Italy

Structured / Unstructured Light Scanners

space-time stereo courtesy of James Davis, UC Santa Cruz color-coded structured light courtesy of Phil Fong, Stanford University motion compensated structured light courtesy of Sören König, TU Dresden

slide-10
SLIDE 10

Eurographics 2012, Cagliari, Italy

Going Mainstream

[Microsoft 2010]

slide-11
SLIDE 11

Eurographics 2012, Cagliari, Italy

Kinect Example Data

Tutorial: Dynamic Geometry Processing 11

slide-12
SLIDE 12

Eurographics 2012, Cagliari, Italy

High-End Acquisition Setup: Lightstage

[Vlasic et al., Siggraph Asia 2009]

slide-13
SLIDE 13

Eurographics 2012, Cagliari, Italy

Lightstage Example Sequence

[Vlasic et al., Siggraph Asia 2009]

slide-14
SLIDE 14

Eurographics 2012, Cagliari, Italy

Problems & Topics

slide-15
SLIDE 15

Eurographics 2012, Cagliari, Italy

Problems

  • Noise, outliers
  • Missing data
  • No correspondences
  • No semantics (joints, bones, expressions)

We discuss

  • Establishing correspondences
  • Reconstruction
  • Noise removal
  • Hole filling
  • Data-driven priors
  • Semantic rigging

Processing Dynamic Geometry

Tutorial: Dynamic Geometry Processing 15 noise holes missing correspondences missing semantics