Image-Guided Weathering: A New Approach Applied to Flow Phenomena

1
(No Transcript)
2
Image-Guided WeatheringA New Approach Applied
to Flow Phenomena
C. Bosch1, P. Y. Laffont, H. Rushmeier, J.
Dorsey, G. Drettakis Yale University
REVES/INRIA Sophia Antipolis 1 Currently at
ViRVIG, University of Girona
3
Aging and Weathering

• Essential for modeling urban environments
• Governed by physical, chemical and biological
  processes

4
Flow effects

• Particularly complex
• Flow over the scene (global effect)
• Material properties (local effect)

5
Aging and Weathering in CG

• Physically-based simulation
• Difficult to get the desired effect
• Texture synthesis
• Restricted by input information
• Global effects particularly hard

6
Motivation

• Physically-based simulation
• More flexible, allows global effects
• Two main difficulties
• Choosing appropriate parameters to achieve a
  given effect
• Obtaining realistic visual detail

7
Image-Guided Weathering

• Use images to guide simulation
• Flow stains as a representative case

Exemplar
New simulation
8
Overview (I)

• Extract data from exemplars
• Color information
• Simulation parameters
• High frequency details

Si 1.301 rt 0.252 kS 0.0201 at
0.404 kD 0.0807 T 803 ka,t 0.021
Exemplar
Data
9
Overview (II)

• Simulate new effects on scenes

Si 1.301 rt 0.252 kS 0.0201 at
0.404 kD 0.0807 T 803 ka,t 0.021
Data
10
Related Work

• Simulation
• Phenomenon-specific Merillou08
• Flow stains Dorsey96 Chen05 Endo10
• Capture-and-transfer (synthesis)
• Single image Wang06 Xue08
• Acquisition systems Gu06 Mertens06 Sun07
  Lu07
• Inverse procedural textures Bourque04
  Lefebvre00

11
Flow model

• Particle-based simulation Dorsey96
• Absorption, solubility and deposition
• Stain concentration maps
• Parameters
• Particles mass (m), Si
• Stain material kS, kD
• Target materials a, ka, roughness (r)
• Simulation time (t), particle rate (N)

12
Extracting Stains

• Based on Appearance Manifolds Wang06

Exemplar
13
Parameter Fitting

• Degree map Stain concentration map

Proxy geometry
(Levenberg-Marquardt) Lourakis04
14
Improving Fitting

• Stain distribution along the source
• Accumulate degree from bottom to top

15
Improving Fitting (II)

• Flow deflection along the target
• Compute local degree distribution (vector field)

16
Parameter Fitting (II)
17
Fitting Results (w/o vector field)
Using source distribution
Exemplar
Degree Map
Simulation
18
Fitting Results (w/o vector field)
Exemplar
Degree Map
Simulation
19
Fitting Results (w/ vector field)
Exemplar
w/o vfield
Degree Map
Simulation
20
Fitting Results (w/ vector field)
Exemplar
Degree Map
Simulation
21
Fitting Results (w/ vector field)
Exemplar
Degree Map
Simulation
22
Fitting Results (Complex Targets)
Exemplar
Degree Map
Simulation
23
Stain Detail

• Simulation lacks spatial variations
  (high-frequency detail)

Degree Map
Simulation
Exemplar
24
Detail Maps

• Extract detail by image difference
• Use guided texture synthesis Lefebvre05
• Detail maps will modify stain adhesion

Detail Map
Degree Map
Simulation
Difference
25
Simulating New Stains

• Link data to stain sources and targets
• Parameters, detail maps, color
• Use 1D texture synthesis for distributions
• Run flow simulation
• Flow deflected by target geometry ( disp. map)

26
Color Transfer

• Transfer stain color from input image
• Background mixed with stain everywhere
• Non-linear relationship between color and degree
• Use per-pixel warping

27
Results
28
Results (II)
29
Results (III)
30
Results (IV)
31
Performance

• Preprocessing
• Degree map 1-3 minutes
• Fitting 30-60 minutes (500 iter., 256x512)
• Detail synthesis 1-2 minutes (1024x1024)
• Final simulation
• Stain simulation 2-5 minutes/stain
• Color warping 5-8 seconds/stain (1024x1024)

32
Limitations

• Good extraction from background
• Fitting Not true physical estimations
• Detail maps Depend on appropriate fit
• Computation time

33
Conclusions

• New approach to acquire simulation data from
  photographs
• Solves parameter estimation from images
• Combines simulation with data-driven methods
• Appearance manifold, texture synthesis,
• Fills the gap between data-driven and simulation
• ? Easy to use
• ? Natural variations (including global effects)

34
Future work

• Extend to other weathering phenomena
• Deal with large scale scenes
• Fast simulation, global effects,

35
Acknowledgements

• Visiting grant U.Girona
• ANR project (ANR-06-MDCA-004-01)
• ERCIM Alain Bensoussan Fellowship
• Autodesk (Maya/MentalRay)
• Coding help Li-Ying, Su Xue
• Scene treatment S. Close and F. Andrade-Cabral

36

• Thank you