+ All Categories
Home > Documents > Image-Based Visual Hulls

Image-Based Visual Hulls

Date post: 21-Mar-2016
Category:
Upload: tadhg
View: 41 times
Download: 0 times
Share this document with a friend
Description:
Paper by Wojciech Matusik, Chris Buehler, Ramesh Raskar, Steven J. Gortler and Leonard McMillan [http:// graphics.lcs.mit.edu/~wojciech/vh/] Vortrag von Simon Dellenbach GDV Fachseminar 2001. Image-Based Visual Hulls. Overview (1). Motivation Basics Viewpoint Model Visual Hull - PowerPoint PPT Presentation
26
1 Image-Based Visual Hulls Paper by Wojciech Matusik, Chris Buehler, Ramesh Raskar, Steven J. Gortler and Leonard McMillan [http://graphics.lcs.mit.edu/~wojciech/vh/] Vortrag von Simon Dellenbach GDV Fachseminar 2001
Transcript
Page 1: Image-Based Visual Hulls

1

Image-Based Visual Hulls

Paper by Wojciech Matusik, Chris Buehler, Ramesh Raskar,

Steven J. Gortler and Leonard McMillan[http://graphics.lcs.mit.edu/~wojciech/vh/]

Vortrag von Simon DellenbachGDV Fachseminar 2001

Page 2: Image-Based Visual Hulls

2

Overview (1)

• Motivation• Basics

– Viewpoint Model– Visual Hull– Epipolar Geometry

• Creating Image-Based Visual Hulls

Page 3: Image-Based Visual Hulls

3

Overview (2)

• Rendering IBVH• System Implementation• Summary & Results• Future Work• Personal Opinion

Page 4: Image-Based Visual Hulls

4

Motivation (1)

• Traditional computer graphics, rendering..– static synthetic scenes (CG Images)– dynamic synthetic scenes (CG Animations)– static acquired scenes (Image-Based Rendering)

• Acquire and render dynamic scenes in real-time:– appropriate representation– rendering system

Page 5: Image-Based Visual Hulls

5

Motivation (2)

Page 6: Image-Based Visual Hulls

6

Viewpoint Model - Basics (1)

Page 7: Image-Based Visual Hulls

7

Visual Hull - Basics (2)

• Geometric shape obtained using silhouettes of object seen from number of views:– extruded silhouette = cone-like volume limiting

the extent of object– intersection of volumes results in a visual hull– more views better approximation of object– limitation: concavities can’t be captured

(e.g. an open box looks like a solid cube)

Page 8: Image-Based Visual Hulls

8

Visual Hull - Basics (3)

Page 9: Image-Based Visual Hulls

9

Epipolar Geometry - Basics (4)

• The tree points [COP1,COP2,P] form an epipolar plane

• Intersection of this plane with image planes results in epipolar lines

• The line connecting the two centers of projection [COP1,COP2] intersects the image planes at the conjugate points e1 and e2 which are called epipoles

Page 10: Image-Based Visual Hulls

10

Epipolar Geometry - Basics (5)

Page 11: Image-Based Visual Hulls

11

Creating Image-Based Visual Hulls (1)

• Algorithm input:– set of k silhouettes (binary images) with

associated viewpoints– desired viewpoint (in this case, constructed

visual hull is viewpoint-dependent)• Algorithm output:

– sampled image of the visual hull, each pixel containing a list of occupied intervals of space

Page 12: Image-Based Visual Hulls

12

Creating Image-Based Visual Hulls (2)

• The Basic Algorithm:– cast ray into space for each pixel in the

desired view of the visual hull– intersect ray with the k silhouette cones

k lists of intervals; intersect together single list of intersections of the viewing ray with the visual hull

Page 13: Image-Based Visual Hulls

13

Creating Image-Based Visual Hulls (3)

Page 14: Image-Based Visual Hulls

14

Creating Image-Based Visual Hulls (4)

• Trick: due to Epipolar Geometry interval calculation can be done in image space of reference images:– 3D: intersecting silhouette cone with viewing

ray– 2D: intersecting projected viewing ray with

silhouette

Page 15: Image-Based Visual Hulls

15

Creating Image-Based Visual Hulls (5)

Page 16: Image-Based Visual Hulls

16

Rendering IBVH (1)

• Reference images are used as textures• For each pixel:

– rank reference-image texture from “best” to “worst” according to angle, take reference with lowest

– avoid texturing surface points with an image whose line-of-sight is blocked by some other point of the visual hull

– consider visibility during shading based on visual hull (not actual geometry)

Page 17: Image-Based Visual Hulls

17

Rendering IBVH (2)

Page 18: Image-Based Visual Hulls

18

Rendering IBVH (3)

Page 19: Image-Based Visual Hulls

19

System Implementation (1)

• Four calibrated and triggered digital cameras

• One desktop PC per camera for capturing and pre-processing video frames (image segmentation)

• Silhouette and texture information sent to central server for IBVH processing

Page 20: Image-Based Visual Hulls

20

System Implementation (2)

• Server runs IBVH intersection and shading algorithms

• IBVH objects can be combined with OpenGL background

• System runs in ‘real time’ with heavy optimization (like caching strategies for silhouette intersection)

Page 21: Image-Based Visual Hulls

21

System Implementation (3)

Page 22: Image-Based Visual Hulls

22

Summary & Results

• Use visual hull as object shape approximation• Using silhouette information from reference

views to generate view dependent visual hull• Reference images are used as ‘textures’

• Results:Videoclips

Page 23: Image-Based Visual Hulls

23

Future Work

• Find Techniques for blending between textures to produce smoother transitions

• Scale up system by using larger number of cameras

• Split workload on multiple servers, as algorithm parallelizes fairly much

• Speed up viewing ray silhouette intersections (most expensive part of the computation)

Page 24: Image-Based Visual Hulls

24

Personal Opinion (1)

• Pros:– simple technique / low-cost hardware– image-based representation partially

compensates simplification problems– epipolar geometry reduces 3D-intersection

problems to 2D-intersections

Page 25: Image-Based Visual Hulls

25

Personal Opinion (2)

• Cons:– texture flipping during viewpoint transitions

produces ugly results– shadows are considered as part of the object– preprocessing is really expensive

(85 ms for image foreground segmentation)

Page 26: Image-Based Visual Hulls

26

The End

“If there are no questions,there won’t be any answers.”

? ? ?

???


Recommended