CSCI 599: Digital Geometry Processing Spring 2015 Hao Li - - PowerPoint PPT Presentation

▶
csci 599 digital geometry processing
SMART_READER_LITE
LIVE PREVIEW

CSCI 599: Digital Geometry Processing Spring 2015 Hao Li - - PowerPoint PPT Presentation

May 17, 2023 31 likes •876 views

CSCI 599: Digital Geometry Processing Spring 2015 Hao Li http://cs599.hao-li.com 1 USC Graphics http://gfx.usc.edu 2 Geometric Capture [Lab] http://www.hao-li.com 3 The Team Instructor ! Hao Li, hao.li@usc.edu Office: SAL 244

slide-1
SLIDE 1

CSCI 599: Digital Geometry Processing

Hao Li

http://cs599.hao-li.com

1

Spring 2015

slide-2
SLIDE 2

USC Graphics

2

http://gfx.usc.edu

slide-3
SLIDE 3

Geometric Capture [Lab]

http://www.hao-li.com

3

slide-4
SLIDE 4

The Team

Instructor!

  • Hao Li, hao.li@usc.edu
  • Office: SAL 244
  • Office hours: Tuesday 2-3PM

4

Assistants!

  • Kyle Olszewski, olszewsk@usc.edu
  • Pei-Lun Hsieh, peilun.hsieh@usc.edu
slide-5
SLIDE 5

About Me

slide-6
SLIDE 6

Industrial Light & Magic

slide-7
SLIDE 7

Science, Engineering, & Art

slide-8
SLIDE 8

High Tech & Capital of Entertainment

Disney

DreamWorks

Activision

Google

slide-9
SLIDE 9

Introduction

9

slide-10
SLIDE 10

Target Audience

10

!

  • PhD students, MSc students, Advanced undergraduates
  • Computer Science, Computer Engineering, Mathematics,

Physics, Game Program, Biomedicine, Bioengineering, etc.

  • Computer Graphics, Computer Vision, Robotics, Machine

Learning, Signal and Image Processing, Medical Imaging

!

slide-11
SLIDE 11

Prerequisites

11

!

  • C/C++ Programming
  • Linear Algebra
  • Numerical Optimization

!

  • CSCI 420 Recommended
slide-12
SLIDE 12

Administrative

12

When and where?!

  • Tuesday, Thursday, 11:00 am - 12:20 pm
  • KAP 158 (Kaprialian Hall)

Credits!

  • 3 Units

Website!

  • http://cs599.hao-li.com/
slide-13
SLIDE 13

Exercises

13

Programming assignments!

  • based on OpenMesh (tutorial will be given Thursday next week)
  • cover some core stages of the geometry processing pipeline
  • C/C++ framework including 3D UI will be provided

Integral part of the lecture!

  • important for achieving course objectives
slide-14
SLIDE 14

Grading

14

  • Best 5 out of 6 exercises contribute to 70% of the final grade
  • Each exercise counts 20 points
  • Late submissions: every 5 minute removes 1 point in each exercise
  • Scope 2 months/person, Groups up to 2
  • Implement a research paper around digital human capture but not

limited to it

  • Final presentation, code/documentation, contributes 30% of the final

grade

Exercises Project

slide-15
SLIDE 15

Academic Integrity

15

  • Do not copy any parts of the assignments

from anyone

  • Do not look at other student’s code
  • Collaboration only for the project
  • USC Office of Student Judicial Affairs and

Community Standards (Hell) will be notified

slide-16
SLIDE 16

Course Objectives

16

  • Define and relate the basic concept, tools, and

algorithms in geometric modeling and digital geometry processing

  • Critically analyze and assess current research on

surface representations and geometric modeling and apply the proposed methods in your own work

  • Design and implement individual components of

geometric modeling system

slide-17
SLIDE 17

Recommended Textbook

Botsch, Kobbelt, Pauly, Alliez, Levy: Polygon Mesh Processing, AK Peters, 2010

17

slide-18
SLIDE 18

Acknowledgement

18

Course material taught at:!

  • EPFL, Mark Pauly (My PhD Advisor)
  • Bielefeld University, Mario Botsch
  • INRIA, Pierre Alliez, Bruno Levy
  • RWTH Aarchen, Leif Kobbelt
slide-19
SLIDE 19

An Example

19

slide-20
SLIDE 20

Computer Graphics

slide-21
SLIDE 21

Performance Capture

slide-22
SLIDE 22

The Vision

slide-23
SLIDE 23

IMocap

slide-24
SLIDE 24

IMocap

slide-25
SLIDE 25

IMocap

slide-26
SLIDE 26

IMocap

slide-27
SLIDE 27

3 weeks for 10 seconds

Facial Perfomance Capture

slide-28
SLIDE 28

Geometry Capture

Motion can be Captured at the Same Resolution as the Geometry

slide-29
SLIDE 29

Realtime Facial Performance Capture

slide-30
SLIDE 30

Capturing Geometry

30

slide-31
SLIDE 31

Static 3D Capture

Stanford 2002

slide-32
SLIDE 32

Dynamic 3D Capture

Stanford 2002

slide-33
SLIDE 33

Commercial 3D Capture

Artec Group

slide-34
SLIDE 34

3D scanner 3D acquisition

Full Body Capture

slide-35
SLIDE 35

Lee Perry-Smith, Infinite Realities + Agisoft

Multi-View Stereo

slide-36
SLIDE 36

Capturing Cities

slide-37
SLIDE 37

Google Earth

slide-38
SLIDE 38

Geometry! γεωµετρία

38

geo = earth metria = measure

slide-39
SLIDE 39

Geometry! γεωµετρία

39

slide-40
SLIDE 40

Geometry! γεωµετρία

40

x-ray diffractometer microscope MRI scanner time-of-flight scanner stereo camera laser scanner radio telescope ultrasound
slide-41
SLIDE 41

Overview

Geometric Modeling!

  • Techniques and algorithms for representing and processing

geometric objects

We will focus on triangle meshes!

  • main questions:
  • why are triangles suitable representations for geometry

processing?

  • what are the central processing algorithms?
  • how can they implemented efficiently?
slide-42
SLIDE 42

Geometry Processing Pipeline

42

slide-43
SLIDE 43

Geometry Processing Pipeline

43

slide-44
SLIDE 44

Geometry Processing Pipeline

44

slide-45
SLIDE 45

Geometry Processing Pipeline

45

slide-46
SLIDE 46

Geometry Processing Pipeline

46

slide-47
SLIDE 47

Geometry Processing Pipeline

47

slide-48
SLIDE 48

Geometry Processing Pipeline

48

slide-49
SLIDE 49

Impacting Science

slide-50
SLIDE 50

Cardiology

slide-51
SLIDE 51

Evolutionary Biology

slide-52
SLIDE 52

Cancer Treatment

slide-53
SLIDE 53

Digitized Future

53

slide-54
SLIDE 54

For Everyone

slide-55
SLIDE 55

For Everyone

slide-56
SLIDE 56

For Everyone

slide-57
SLIDE 57

Scanning@Home

54°

slide-58
SLIDE 58

Living Room Entertainment

slide-59
SLIDE 59

In Tablet

slide-60
SLIDE 60

In Laptops

slide-61
SLIDE 61

In Laptops

slide-62
SLIDE 62

In Smartphones

slide-63
SLIDE 63

From Capture to Fabrication

63

3D printing

slide-64
SLIDE 64

Realtime Future

64

slide-65
SLIDE 65

VFX/Game Production Virtual Avatars Robotics AR/Virtual Mirror

Why Realtime?

slide-66
SLIDE 66

Realtime Game Engines

slide-67
SLIDE 67

Realtime Facial Animation

slide-68
SLIDE 68

Virtual Reality Reloaded

Oculus VR 2012 / Crytek 2014

slide-69
SLIDE 69

Personalized Future

69

slide-70
SLIDE 70

3D Self-Portraits

Omote3D Shashin Kan

slide-71
SLIDE 71

3D Self-Portraits

Omote3D Shashin Kan

slide-72
SLIDE 72

3D Self-Portraits

Omote3D Shashin Kan

slide-73
SLIDE 73

3D Self-Portraits

Omote3D Shashin Kan

slide-74
SLIDE 74

3D Selfies

slide-75
SLIDE 75

3D Selfies

slide-76
SLIDE 76

Personalized Games

USC/ICT

slide-77
SLIDE 77

Personalized Applications

digital garment entertainment fitness

MPI IS, Embodee

slide-78
SLIDE 78

Fashion Industry

slide-79
SLIDE 79

Summary

79

Reconstruction Geometry Processing Capture Design Analysis Manipulation Storage Rendering Simulation Reproduction

slide-80
SLIDE 80

Classic Graphics

80

Reconstruction Geometry Processing Capture Design Analysis Manipulation Storage Rendering Simulation Reproduction

slide-81
SLIDE 81

Modern Graphics/Vision

81

Reconstruction Geometry Processing Capture Design Analysis Manipulation Storage Rendering Simulation Reproduction

slide-82
SLIDE 82

The Future: Big Data / Robotics

82

Reconstruction Geometry Processing Capture Design Analysis Manipulation Storage Rendering Simulation Reproduction AI Feedback

slide-83
SLIDE 83

Next Time

83

  • Parametric Approximations
  • Polygon Meshes
  • Data Structures
slide-84
SLIDE 84

http://cs599.hao-li.com

Demos!

84