Title: Two-scale Tone Management for Photographic Look
1Two-scale Tone Management for Photographic Look
Soonmin Bae, Sylvain Paris, and Frédo Durand MIT
CSAIL
2Ansel Adams
Ansel Adams, Clearing Winter Storm
3An Amateur Photographer
4A Variety of Looks
5Goals
- Control over photographic look
- Transfer look from a model photo
For example, we want
with the look of
6Aspects of Photographic Look
- Subject choice
- Framing and composition
- ? Specified by input photos
- Tone distribution and contrast
- ?Modified based on model photos
Input
Model
7Tonal Aspects of Look
Ansel Adams
Kenro Izu
8Tonal aspects of Look- Global Contrast
Ansel Adams
Kenro Izu
High Global Contrast
Low Global Contrast
9Tonal aspects of Look - Local Contrast
Ansel Adams
Kenro Izu
Variable amount of texture
Texture everywhere
10Related Work Scale/Frequency Manipulation
- Used for audio visual equalizer
- controls sound ambiance
- Not really used yet for images
- Exception Kais Power Tools
11Related Work - Example-based style transfer
- Non-photorealistic styles
- Hertzmann 01 Efros 01 Drori 03 Rosales 03
- mimics brush strokes or textures
- but does not target photorealistic style
Hertzmann 01
12Related Work - Tone Mapping
- Reduce global contrast
- Pattanaik 98Tumblin 99Ashikhmin 02Durand
02Fattal 02Reinhard 02Li 05 - Seeks neutral reproduction
- Little control over look
-
- In contrast, we want to achieve particular looks
Durand 02
13Related Work Professional tools
- Image editing software
- e.g. Adobe Photoshop
- need skills
- tedious
- Photo management tools
- e.g. Adobe Lightroom, Apple Aperture
- optimizes user efficiency (workflow)
- but has limited control
Adobe Photoshop
Adobe Lightroom
14Our work
Model
Input Image
Result
- Transfer look between photographs
- Tonal aspects
15Our work
Global contrast
InputImage
Result
Local contrast
- Separate global and local contrast
16Overview
Global contrast
Carefulcombination
Split
Post-process
InputImage
Local contrast
Result
17Overview
Global contrast
Carefulcombination
Split
Post-process
InputImage
Local contrast
Result
18Split Global vs. Local Contrast
- Naïve decomposition low vs. high frequency
- Problem introduce blur halos
Halo
Blur
Low frequency
High frequency
Global contrast
Local contrast
19Bilateral Filter
- Edge-preserving smoothing Tomasi 98
- We build upon tone mapping Durand 02
After bilateral filtering
Residual after filtering
Global contrast
Local contrast
20Bilateral Filter
- Edge-preserving smoothing Tomasi 98
- We build upon tone mapping Durand 02
BASE layer
DETAIL layer
After bilateral filtering
Residual after filtering
Global contrast
Local contrast
21Global contrast
BilateralFilter
Carefulcombination
Post-process
InputImage
Local contrast
Result
22Global contrast
BilateralFilter
Carefulcombination
Post-process
InputImage
Local contrast
Result
23Global Contrast
- Intensity remapping of base layer
Remapped intensity
Input intensity
Input base
After remapping
24Global Contrast (Model Transfer)
- Histogram matching
- Remapping function given input and model histogram
Modelbase
Inputbase
25Global contrast
Intensitymatching
BilateralFilter
Carefulcombination
Post-process
InputImage
Local contrast
Result
26Global contrast
Intensitymatching
BilateralFilter
Carefulcombination
Post-process
InputImage
Local contrast
Result
27Local Contrast Detail Layer
- Uniform control
- Multiply all values in the detail layer
Input
Base 3 ? Detail
28The amount of local contrast is not uniform
Smooth region
Textured region
29Local Contrast Variation
- We define textureness amount of local contrast
- at each pixel based on surrounding region
Smooth region? Low textureness
Textured region? High textureness
30Textureness 1D Example
Input signal
31Textureness
Textureness
Input
32Textureness Transfer
Model textureness
Step 1 Histogram transfer
Input textureness
Desired textureness
Hist. transfer
x 0.5
Step 2 Scaling detail layer (per pixel) to
match desired textureness
x 2.7
x 4.3
Input detail
Output detail
33Global contrast
Intensitymatching
BilateralFilter
Carefulcombination
Post-process
InputImage
Texturenessmatching
Local contrast
Result
34Global contrast
Intensitymatching
BilateralFilter
Carefulcombination
Post-process
InputImage
Texturenessmatching
Local contrast
Result
35A Non Perfect Result
- Decoupled and large modifications (up to 6x)
- Limited defects may appear
result after global and local adjustments
input (HDR)
36Intensity Remapping
- Some intensities may be outside displayable
range. - Compress histogram to fit visible range.
correctedresult
remappedintensities
initialresult
37Preserving Details
- In the gradient domain
- Compare gradient amplitudes of input and current
- Prevent extreme reduction extreme increase
- Solve the Poisson equation.
correctedresult
remappedintensities
initialresult
38Effect of Detail Preservation
uncorrected result
corrected result
39Global contrast
Intensitymatching
BilateralFilter
ConstrainedPoisson
Post-process
InputImage
Texturenessmatching
Local contrast
Result
40Global contrast
Intensitymatching
BilateralFilter
ConstrainedPoisson
Post-process
InputImage
Texturenessmatching
Local contrast
Result
41Additional Effects
model
- Soft focus (high frequency manipulation)
- Film grain (texture synthesis Heeger 95)
- Color toning (chrominance f (luminance) )
aftereffects
beforeeffects
42Global contrast
Intensitymatching
BilateralFilter
ConstrainedPoisson
Soft focus Toning Grain
InputImage
Texturenessmatching
Local contrast
Result
43Recap
Global contrast
Intensitymatching
BilateralFilter
ConstrainedPoisson
Soft focus Toning Grain
InputImage
Texturenessmatching
Local contrast
Result
44Results
- User provides input and model photographs.
- Our system automatically produces the result.
- Running times
- 6 seconds for 1 MPixel or less
- 23 seconds for 4 MPixels
- multi-grid Poisson solver and fast bilateral
filter Paris 06
45Input
Model
Result
46Result
Input
47Model
Input
Result
48Comparison with Naïve Histogram Matching
Model Snapshot, Alfred Stieglitz
Input
Naïve Histogram Matching
Our result
Local contrast, sharpness unfaithful
49Comparison with Naïve Histogram Matching
Model Clearing Winter Storm, Ansel Adams
Input
Our Result
Histogram Matching
Local contrast too low
50Color Images
- Lab color space modify only luminance
Input
Output
51Limitations
- Noise and JPEG artifacts
- amplified defects
- Can lead to unexpected results if the image
content is too different from the model - Portraits, in particular, can suffer
52Conclusions
- Transfer look from a model photo
- Two-scale tone management
- Global and local contrast
- New edge-preserving textureness
- Constrained Poisson reconstruction
- Additional effects