86
Poisson Image Editing SIGGRAPH 2003 Patric Perez Michel Gangnet Andrew Black

Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

  • Upload
    others

  • View
    4

  • Download
    0

Embed Size (px)

Citation preview

Page 1: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Poisson Image Editing

SIGGRAPH 2003Patric Perez Michel GangnetAndrew Black

Page 2: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM
Page 3: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Most Frequently Used PDE

Wave Equation

Heat Equation

Page 4: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Most Frequently Used PDE

Poisson Equation, Steady State of Wave Equation and Heat Equation

Laplace’s Equation

Page 5: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Boundary Conditions

Dirichlet Boundary ConditionsSpecify the value of the function on a surface

Neumann Boundary ConditionSpecify the normal derivative of the function on a surface

Page 6: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Guided Interpolation

f: to be solved, f*: known regionv: guided field, g: v is prob. gradient of g

Page 7: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Simple Interpolation

Maximize the Smoothness

Solution: Laplace Equation with DirichletBoundary Conditions

Page 8: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM
Page 9: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Guided Interpolation

Interpolation-> minimization

Solution: Poisson Equation with DirichletBoundary Conditions

Relationship with Laplace case?

Page 10: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Or from vector field decomposition

Helmholtz-Hodge decomp.

Page 11: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Discrete Poisson SolverDiscretize the Minimization Directly

Partial Derivative

Partial Derivative for Interior Points

Page 12: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Discrete Poisson Solver

Linear System of EquationsGauss-Seidel Method with Successive OverrelaxationV-cycle MultigridDiscretize Laplacian with Discrete Laplacian of Gaussianhttp://www.tau.ac.il/~stoledo/taucs/ Taucs

Page 13: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Seamless Cloning :Importing Gradients

Importing Gradients from a Source Image

Discretize

Page 14: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Seamless Cloning Results

Page 15: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Seamless Cloning Results

Texture

Alignment

Page 16: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Transfer intensity only

Page 17: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM
Page 18: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Seamless Cloning: Mixing Gradients

Two ProposalsDefine v as Linear Combination of Source and Destination GradientsSelect Stronger one from Source and Destination Gradients (not conservative!)

Discretization

Page 19: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Mixing Gradients Results

Page 20: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Mixing Gradients Results

Page 21: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Mixing Gradients Results

Just reduce terrible things ! Another solution

Page 22: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Texture Flattening

Remain Only Salient Gradients

Discretization

Page 23: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Texture Flattening

Edge mask

Page 24: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Local Illumination Changes

Fattal Transformation

Page 25: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM
Page 26: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Local Color Changes

Mix two different colored version of original image

One provide f* outsideOne provide g inside

Page 27: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Local Color Changes

Monochrome of backgroundWhite in flower

Page 28: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Seamless Tiling

Select original image as gBoundary condition:

f*north=f*

south=0.5(gnorth+gsouth)Similarly for the east and west

Page 29: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Seamless Tiling

Page 30: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Discussion

Page 31: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Discussion

Page 32: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Discussion

Page 33: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Discussion

Page 34: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Drag-and-Drop Pasting

Leo Jiaya Jia Leo Jiaya Jia Jian Sun Jian Sun ChiChi--Keung TangKeung TangHeungHeung--Yeung ShumYeung Shum

The Chinese University of Hong KongMicrosoft Research AsiaThe H.K. University of Sci. & Tech.Microsoft Research Asia

SIGGRAPH 2006

Slides by the authors

Page 35: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Introduction to our method

Our method improves the Poisson image editing with

a new boundary optimization algorithm,an easier user interface,and an integration of alpha values.

Page 36: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Poisson equations in images

A case study

+

sftf

Page 37: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Poisson equations in imagesA case study

+

sftf

Page 38: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Poisson equations in imagesThe optimization problem in image blending [Perez et al. 2003]

Taking , we have

What does it imply?

0 00

2

pmin | | with | |f s tf f dp f f∂Ω ∂Ω∈Ω

∇ −∇ =∫ 0 00

2

pmin | | with | |tsf dp ff ff ∂Ω ∂Ω∈Ω

=∇ −∇∫ 0 00

2

pmin | | with | | f s tf f fdp f∂Ω Ω ∂Ω∈

∇ −∇ =∫sf∇

tf'

sf f f= −

0 00

2' p

min | ' | with ' | |f t sf dp f f f∂Ω ∂Ω∈Ω∇ = −∫ 0

t sf f−

Page 39: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Poisson equations in images

The minimization problem equals to solving the Laplace equation:

Image blending should take both the source and the target images into consideration.Property of solving the Laplace equation:

The variational energy will approach zero if and only if all boundary pixels satisfy , where k is a constant value.

0 0' 0 with ' | |t sf f f f∂Ω ∂ΩΔ = = −

0

2| ' |fΩ

∇∫0

( ) |t sf f k∂Ω− =

Page 40: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Poisson equations in images

Where is the optimal boundary ?Inside the user drawn regionOutside the object of interest

How is the object extracted?Lazy snapping or Grabcut [Rother et al. 2004] (September 23)

How to optimize it?Minimum color variance

∂Ω

2min (( ( ) ( )) ) , s.t. bluet sp

f p f p k∈∂Ω

− − ∂Ω∈∑

Page 41: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Boundary optimization

∂Ω and k are all unknownsAn iterative optimization

Initialize ∂Ω as the user drawn boundary.Given new ∂Ω, the optimal k is computed:

Given new k, optimize the boundary ∂Ω.Repeat the previous two steps until convergence.

2( , ) (( ( ) ( )) ) , s.t. bluet sp

E k f p f p k∈∂Ω

∂Ω = − − ∂Ω∈∑

( , ) 0E kk

∂ ∂Ω=

∂Shortest path problem

Page 42: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Boundary optimizationIn 2D graph, computing the shortest path between any two points: Dynamic ProgrammingOur problem is to compute a closed path

Page 43: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Boundary optimizationA shortest closed-path algorithm

Breaking closed boundary

Page 44: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Boundary optimizationA shortest closed-path algorithm

Page 45: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Boundary optimizationA shortest closed-path algorithm

Computation complexity O(N)

Page 46: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Boundary optimizationA shortest closed-path algorithm

Total computation complexity O(NM)

Page 47: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Boundary optimization discussion

OptimalityAvoiding that the path twists around the cut by selecting the initial cut position.

How to select the initial cut?Making it short to reduce O(MN)Passing smooth region

Page 48: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

One example

Page 49: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Integrating fractional boundary

Fractional boundary is important in image composting: (transparency)

Page 50: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

MattingComposition Image I is generated by foreground and background with alpha matteI = alpha*F + (1-alpha)*BMatting is a problem to get alpha,F,B from a given image I.User have to devide the image into three region: Foreground, Background and Unknown area. In foreground area, F = I, alpha = 1, B = 0; In background area, F = 0, alpha = 0, B = I. Our task is to get F,B,alphain unknown area.

Page 51: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Integrating fractional boundary

Where to use the fractional values?only the pixels where the optimized boundary is near the blue ribbon

∂Ω

Page 52: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Integrating fractional boundary

Where to use the fractional values?only the pixels where the optimized boundary is near the blue ribbon

fractional integration: the green region

otherwise: the yellow region

Page 53: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

'

( , ) ( , ), ( 1, )( , ) ( (1 ) ) ( , ), ( 1, )

0 otherwise

x s

x x s t

f x y x y x y yellowv x y f f x y x y greenα α

∇ + ∈⎧⎪= ∇ + − + ∈⎨⎪⎩

Integrating fractional boundary

How to integrate the fractional values in Poisson blending?

A blended guidance field

'

( , ) ( , ), ( 1, )( , ) ( (1 ) ) ( , ), ( 1, )

0 otherwise

s

s

x

x x t

f x y x y x y yellowv x y f f x y x y greenα α

∇ + ∈⎧⎪= ∇ + − + ∈⎨⎪⎩

'

( , ) ( , ), (( , ) ( (1 ) ) ( , ), ( 1, )

0 otherwi

1, )

sex x s

x s

tv x y f f x y x y greef x y x y x y

nyellow

α α⎧⎪= ∇ + −

∇ ∈+ ∈⎨

+

⎪⎩

( , ) ( 1, ) ( , )x f x y f x y f x y∇ = + −

Page 54: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

' ( (1 ) ) ( , ), ( 1, )( , ) ( , ), ( 1, )

( , )0 otherwise

x s t

x s

x

f x y x yf f x y x y gr

x y yellowv y nx eeα α

∇ +∇ + − +

∈= ∈⎧⎪⎨⎪⎩

Integrating fractional boundaryHow to integrate the fractional values in Poisson blending?

A blended guidance field

Page 55: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

'

0 o

( , ) ( , ), (

therw

1, )( , ) ( (1 ) ) ( , ), ( 1,

s)i e

x s

x x s t

f x y x y x y yellowv x y f f x y x y greenα α

∇ + ∈⎧⎪= ∇ + − + ∈⎨⎪⎩

Integrating fractional boundaryHow to integrate the fractional values in Poisson blending?

A blended guidance field

Page 56: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Integrating fractional boundary

Final minimization:

New boundary: Solving the corresponding Poisson equation.

2* *p *

min | ' | with | |f tf v dp f f∂Ω ∂Ω∈Ω∇ − =∫

Page 57: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Results and comparison

Alpha blending

Page 58: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Results and comparison

Poisson blendingOur method

Page 59: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Results and comparison

Alpha blendingOur method

Page 60: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Results and comparison

Poisson blendingOur method

Page 61: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Poisson Image Editing Extended

SIGGRAPH 2006 sketch

Daniel Leventhal Brown Univ.Bernard Gordon Brown Univ.Peter G. Sibley Brown Univ.

Page 62: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Problem caused by texture

Page 63: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Alpha control

Alpha in [0, 1], background 0, and foreground 1.Obtain unselected area’s Alpha by blurring.

Implemented in YUV rather than RGB

Page 64: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Result

Luminance rescaling

Page 65: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Far from solved…

Only pure texture, how about mixture of texture and non-textureFar from perfect…

Page 66: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Parallel Method on Mesh

Poisson based mesh editingOptical Boundaries for mesh mergingExtend from image space to mesh manifold

Page 67: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Mesh Editing with Poisson-Based Gradient Field Manipulation

SIGGRAPH 2004Yizhou Yu UIUCKun Zhou MSRADong Xu Zhejiang Univ, MSRAXiaohan Shi Zhejiang Univ, MSRAHujun Bao Zhejiang Univ.Baining Guo MSRAHeung-Yueng Shum MSRA

Page 68: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Mesh merging

Page 69: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Deformation

Page 70: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Basic idea

Quite similar to the case of imageVector field decomposition can be extended to manifold

Page 71: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Discretization

NOT real gradient and divergence, but it works

Sparse linear system

Page 72: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Mesh Merging

Some ‘ugly’ detailsBoundary interactionBoundary correspondenceRe-parameterization

Page 73: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM
Page 74: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM
Page 75: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM
Page 76: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Mesh deformation

Interactively change guided vector fieldChange normal on a curvePropagate to other areas

Smooth normal field – smooth

Page 77: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM
Page 78: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM
Page 79: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Optimal Boundaries for Poisson Mesh Merging

SPM 2007Xiaohuang Huang Zhejiang Univ. & HUSTHongbu Fu HUSTOscar Kin-Chung Au HUSTChiew-Lan Tai HUST

Page 80: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Basic idea

Best boundary for Poisson MergingSimilar to ‘Drag-and-Drop Pasting’.

Page 81: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Optimal boundary

2( , ) (( ( ) ( )) ) , s.t. bluet sp

E k f p f p k∈∂Ω

∂Ω = − − ∂Ω∈∑

Page 82: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Mesh ‘ugly’ limitation

Correspondence between source and target images are trivialMeaningful correspondence between source and target meshes are VERY difficult.

Page 83: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Results

Page 84: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM
Page 85: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM
Page 86: Poisson Image Editing - Computer Sciencelazebnik/research/fall08/jia_pan.pdfMicrosoft PowerPoint - Poisson Image Editing.ppt Author: Jia Pan Created Date: 9/18/2008 3:25:34 PM

Failure?