Intro to Image Based Rendering Intro to Image Based Rendering - - PDF document

▶
intro to image based rendering intro to image based
SMART_READER_LITE
LIVE PREVIEW

Intro to Image Based Rendering Intro to Image Based Rendering - - PDF document

Feb 25, 2024 200 likes •400 views

Intro to Image Based Rendering Intro to Image Based Rendering Working with images Working with images realistic appearance textures inflexible? 1 References References Two classic papers (available through the ACM web site:

slide-1
SLIDE 1

1

Intro to Image Based Rendering Intro to Image Based Rendering Working with images Working with images

  • realistic appearance

– textures

  • inflexible?
slide-2
SLIDE 2

2

References References

Two classic papers (available through the ACM web site: www.acm.org/dl) Thaddeus Beier and Shawn Neely, “Feature- Based Image Metamorphosis”, SIGGRAPH ‘92 Shenchang Eric Chen and Lance Williams, “View Interpolation for Image Synthesis,” SIGGRAPH ’93.

Feature Based Morphing Feature Based Morphing

  • Goal: create an animated morph from person A

to person B (while they are singing!)

slide-3
SLIDE 3

3

Main Idea Main Idea

Warp to destination shape Warp to source shape Intermediate image is a partial warp of both source and destination images, followed by a blend source image destination image

Controlling the Warp Controlling the Warp

  • Idea: Feature lines establish correspondence
slide-4
SLIDE 4

4

Feature Lines Feature Lines

  • A feature line defines a coordinate system

Feature Lines Feature Lines

  • Changing

the feature line changes how the image is drawn

slide-5
SLIDE 5

5

Filling in Pixels Filling in Pixels Multiple Feature Lines Multiple Feature Lines

  • Weighted average of displacement vectors

(destination to source pixel)

slide-6
SLIDE 6

6

Multiple Feature Lines Example Multiple Feature Lines Example Problems with the technique Problems with the technique

slide-7
SLIDE 7

7

slide-8
SLIDE 8

8

slide-9
SLIDE 9

9

slide-10
SLIDE 10

10

Video Video View Interpolation View Interpolation

  • Goal: Given photographs, generate new views
slide-11
SLIDE 11

11

Main Idea Main Idea

Warp to desired viewpoint Warp to desired viewpoint Blend / composite the two warped images image A image B

Controlling the Warp Controlling the Warp

  • Key: we know the depth of every pixel
  • Result is dense correspondence between

images

  • Forward mapping is used to create warped

image

– why?

  • (Example on the board)
slide-12
SLIDE 12

12

Boring pixel displacement fields Boring pixel displacement fields

More general displacement field More general displacement field

slide-13
SLIDE 13

13

Issues: Overlaps Issues: Overlaps

  • Many pixels map to one

– large area becomes smaller blend – multiple layers map to single point z-buffer

Issues: Holes Issues: Holes

  • No pixels map to a pixel in the new image
slide-14
SLIDE 14

14

Holes Holes

slide-15
SLIDE 15

15

Application: Motion Blur w/out Rerendering Application: Motion Blur w/out Rerendering Application: Soft shadows w/out rerendering Application: Soft shadows w/out rerendering

slide-16
SLIDE 16

16

Primary Limitation Primary Limitation

  • depth is required for every pixel!
slide-17
SLIDE 17

17

Some more recent work: Some more recent work:

  • get the user involved in specifying depth

– Debevec, SIGGRAPH ’96 – http://athens.ict.usc.edu/Research

  • use color and many cameras to get a good

guess at depth .. use texture synthesis to refine that guess

– Fitzgibbon et al., ICCV ’03 – http://www.robots.ox.ac.uk/~awf/ibr/

Some more recent work: Some more recent work:

  • Fitzgibbon et al., ICCV ‘03

Input images Results Results 2

slide-18
SLIDE 18

18

Announcements Announcements

  • Homework due Thursday just before class
  • Project 4 goes out Thursday

– Texture synthesis! – James Hays will give the lecture on Thursday