removing blur due to camera shake from images

Removing blur due to camera shake from images.

William T. Freeman

Joint work with Rob Fergus, Anat Levin, Yair Weiss, Fredo Durand, Aaron Hertzman, Sam Roweis, Barun Singh

Massachusetts Institute of Technology

Overview

Original Our algorithm

Close-up

Original Naïve Sharpening Our algorithm

Let’s take a photo

Blurry result

Slow-motion replay

Slow-motion replay

Motion of camera

Image formation process

= ⊗

Blurry image Sharp image

Blur kernel

Input to algorithm Desired output

ConvolutionoperatorModel is approximation

Why is this hard?

Simple analogy:11 is the product of two numbers.What are they?

No unique solution: 11 = 1 x 1111 = 2 x 5.511 = 3 x 3.667 etc…..

Need more information !!!!

Multiple possible solutions

= ⊗

Blurry image

Sharp image Blur kernel

= ⊗

= ⊗

Is each of the images that follow sharp or blurred?

Another blurry one

Natural image statistics

Histogram of image gradients

Characteristic distribution with heavy tails

Blury images have different statistics

Histogram of image gradients

Parametric distribution

Histogram of image gradients

Use parametric model of sharp image statistics

Uses of natural image statistics

• Denoising [Roth and Black 2005]

• Superresolution [Tappen et al. 2005]

• Intrinsic images [Weiss 2001]

• Inpainting [Levin et al. 2003]

• Reflections [Levin and Weiss 2004]

• Video matting [Apostoloff & Fitzgibbon 2005]

Corruption process assumed known

Existing work on image deblurring

Software algorithms:– Extensive literature in signal processing

community– Mainly Fourier and/or Wavelet based– Strong assumptions about blur

not true for camera shake

– Image constraints are frequency-domain power-laws

Assumed forms of blur kernels

A focus on image constraints, not image priors

Some image constraints/priors

Toy example: observed “image”:

1.0

0.0

1.0

0.0

Toy example: observed “image”:

Toy example: observed “image”:

1.0

0.0

Three sources of information

1. Reconstruction constraint:

=⊗

Input blurry imageEstimated sharp imageEstimatedblur kernel

3. Blur prior:

Positive&

Sparse

2. Image prior:

Distribution of gradients

Prior on image gradients (mixture of Gaussians giving a

Laplacian-like distribution)

Distribution of gradients (log-scale)Green curve is our mixture of gaussians fit.

Prior on blur kernel pixels (mixture of exponentials)

b

P(b)

How do we use this information?

Obvious thing to do:– Combine 3 terms into an objective function

– Run conjugate gradient descent

– This is Maximum a-Posteriori (MAP)

Maximum A-Posterioriy – observed blurry imagex – unobserved sharp imageb – blur kernel

i – image patch indexf – derivative filter

Likelihood Latent image prior Blur prior

Assumption: all pixels independent of one another

Sparse and

Results from MAP estimation

Maximum a-Posteriori (MAP)Our method: Variational Bayes

Input blurry image

Variational Bayes

http://citeseer.ist.psu.edu/cache/papers/cs/16537/http:zSzzSzwol.ra.phy.cam.ac.ukzSzjwm1003zSzspringer_chapter8.pdf/miskin00ensemble.pdf

Miskin and Mackay, 2000

Setup of variational approachNeed likelihood and prior in same space, so use gradients:

Likelihood

Prior on latent image gradients – mixture of Gaussians

Prior on blur elements – mixture of Exponentialsi – image pixelj – blur pixel

We use C=4, D=4

Also have Gamma hyperpriors on

Variational inference• Approximate posterior with

• Cost function

• Assume

• Use gradient descent, alternating between updating while marginalizing out over and vice versa

• Adapted code from Miskin & Mackay 2000

is Gaussian on each pixel

is rectified Gaussian on each pixel

Variational Bayesian method

Based on work of Miskin & Mackay 2000

Keeps track of uncertainty in estimates of image and blur by using a distribution instead of a single estimate

Helps avoid local maxima and over-fitting

Variational Bayes

Variational Bayesian method

Maximum a-Posteriori (MAP)

Pixel intensity

Score

Objective function for a single variable

MAP vs Variational

MAP

Variational

MAP using variational initialization

Blurry synthetic image

Inference – initial scale

Inference – scale 2

Inference – scale 3

Inference – scale 4

Inference – scale 5

Inference – scale 6

Inference – final scale

Our output

Ground truth

Matlab’s deconvblind

True kernel Estimated kernel

Tried the same algorithm on an image of real camera blur, with very similar blur kernel

Failure!

Whiteboard scene:

Does camera shake give a stationary blur kernel?

8 different people, handholding camera, using 1 second exposure

View of the dots at each corner in photos taken by 4 people

Topleft

Bot.left

Topright

Bot.right

Person 1

Person 3 Person 4

Person 2

Tonescale: output from camera

Linear response to light intensities looks like this

Overview of algorithm

Input image

1. Pre-processing

2. Kernel estimation- Multi-scale approach

3. Image reconstruction- Standard non-blind deconvolution

routine

Preprocessing

Convert tograyscale

Input image

Remove gammacorrection

User selects patch from image

Bayesian inference too slow to run on whole image

Infer kernel from this patch

InitializationInput image

Initialize 3x3 blur kernel

Initial blur kernelBlurry patch Initial image estimate

Convert tograyscale

Remove gammacorrection

User selects patch from image