Colorization using Optimization Anat Levin Dani Lischinski Yair - - PowerPoint PPT Presentation

colorization using optimization
SMART_READER_LITE
LIVE PREVIEW

Colorization using Optimization Anat Levin Dani Lischinski Yair - - PowerPoint PPT Presentation

Colorization using Optimization Anat Levin Dani Lischinski Yair Weiss Colorization Colorization : a computer-assisted process of adding color to a monochrome image or ) movie. (Invented by Wilson Markle, 1970 Motivation Colorizing black


slide-1
SLIDE 1

Colorization using Optimization

Anat Levin Dani Lischinski Yair Weiss

slide-2
SLIDE 2

Colorization: a computer-assisted process of adding color to a monochrome image or

  • movie. (Invented by Wilson Markle, 1970

)

Colorization

slide-3
SLIDE 3
  • Colorizing black and white movies / TV

shows

  • Recoloring color images for special effects

Motivation

slide-4
SLIDE 4

Color 101

  • Typically represented by points in a three

dimensional color space:

  • (Red, Green, Blue)
  • Another option: [Y, U, V]
  • Y - intensity
  • U, V - chromatic channels
  • A simple transformation exists:

[R, G, B] ⇔ [Y, U, V]

slide-5
SLIDE 5

Typical Colorization Process

Images from: “Yet Another Colorization Tutorial” http://www.worth1000.com/tutorial.asp?sid= 161018

slide-6
SLIDE 6

Images from: “Yet Another Colorization Tutorial” http://www.worth1000.com/tutorial.asp?sid= 161018

Typical Colorization Process

  • Delineate region boundary
slide-7
SLIDE 7

Images from: “Yet Another Colorization Tutorial” http://www.worth1000.com/tutorial.asp?sid= 161018

Typical Colorization Process

  • Delineate region boundary
  • Choose region color from palette
slide-8
SLIDE 8

Images from: “Yet Another Colorization Tutorial” http://www.worth1000.com/tutorial.asp?sid= 161018

Typical Colorization Process

  • Delineate region boundary
  • Choose region color from palette
slide-9
SLIDE 9

Images from: “Yet Another Colorization Tutorial” http://www.worth1000.com/tutorial.asp?sid= 161018

Typical Colorization Process

  • Delineate region boundary
  • Choose region color from palette
slide-10
SLIDE 10

Process Limitations

  • Requires expertise and time consuming
  • Selecting detailed or fuzzy boundaries is

difficult

  • Tracking regions is difficult (for video)
slide-11
SLIDE 11

Let the user focus on the creative goals, without having to worry about selection!

Our Approach

slide-12
SLIDE 12

Our Approach

Colors are propagated to every pixel in the image.

Grayscale channel Chroma channels

slide-13
SLIDE 13

Pixel Affinity

Assumption: Neighboring pixels with similar intensities should have similar colors.

slide-14
SLIDE 14

Pixel Affinity

Minimize:

r s wrs

slide-15
SLIDE 15

Optimization

  • Find a function U that minimizes:

(subject to the user’s color scribbles)

  • Boils down to solving a system of linear

equations.

  • Do the same for V.
slide-16
SLIDE 16

Colorizing Stills

slide-17
SLIDE 17
slide-18
SLIDE 18

Original Colorized

Colorizing Stills

slide-19
SLIDE 19

Colorizing Stills

slide-20
SLIDE 20

13

  • ut of 92 frames

Colorizing Video