Image Pyramids and Blending

Slides:



Advertisements
Similar presentations
CSCE 643 Computer Vision: Template Matching, Image Pyramids and Denoising Jinxiang Chai.
Advertisements

Image Blending and Compositing : Computational Photography Alexei Efros, CMU, Fall 2010 © NASA.
Blending and Compositing Computational Photography Connelly Barnes Many slides from James Hays, Alexei Efros.
Multiscale Analysis of Images Gilad Lerman Math 5467 (stealing slides from Gonzalez & Woods, and Efros)
15-463: Computational Photography Alexei Efros, CMU, Spring 2010 Most slides from Steve Marschner Sampling and Reconstruction.
Ted Adelson’s checkerboard illusion. Motion illusion, rotating snakes.
Slides from Alexei Efros
CS 691 Computational Photography
Computational Photography: Sampling + Reconstruction Connelly Barnes Slides from Alexei Efros and Steve Marschner.
Recap from Monday Frequency domain analytical tool computational shortcut compression tool.
Computational Photography CSE 590 Tamara Berg Filtering & Pyramids.
Recap from Monday Fourier transform analytical tool computational shortcut.
Blending and Compositing Computational Photography Derek Hoiem, University of Illinois 09/23/14.
Blending and Compositing : Rendering and Image Processing Alexei Efros.
Image Filtering, Part 2: Resampling Today’s readings Forsyth & Ponce, chapters Forsyth & Ponce –
CSCE 641 Computer Graphics: Image Sampling and Reconstruction Jinxiang Chai.
Sampling and Pyramids : Rendering and Image Processing Alexei Efros …with lots of slides from Steve Seitz.
Edges and Scale Today’s reading Cipolla & Gee on edge detection (available online)Cipolla & Gee on edge detection Szeliski – From Sandlot ScienceSandlot.
CSCE 641 Computer Graphics: Image Sampling and Reconstruction Jinxiang Chai.
Image Sampling Moire patterns
Texture Reading: Chapter 9 (skip 9.4) Key issue: How do we represent texture? Topics: –Texture segmentation –Texture-based matching –Texture synthesis.
Image Pyramids Pre-filter images to collect information at different scalesPre-filter images to collect information at different scales More efficient.
2D Fourier Theory for Image Analysis Mani Thomas CISC 489/689.
Image Compositing and Blending : Computational Photography Alexei Efros, CMU, Fall 2007 © NASA.
Lecture 8: Image Alignment and RANSAC
More Mosaic Madness : Computational Photography Alexei Efros, CMU, Fall 2005 © Jeffrey Martin (jeffrey-martin.com) with a lot of slides stolen from.
The Frequency Domain : Computational Photography Alexei Efros, CMU, Fall 2008 Somewhere in Cinque Terre, May 2005 Many slides borrowed from Steve.
Image Pyramids and Blending : Computational Photography Alexei Efros, CMU, Fall 2005 © Kenneth Kwan.
4 – Image Pyramids. Admin stuff Change of office hours on Wed 4 th April – Mon 31 st March pm (right after class) Change of time/date of last.
Image Stitching II Ali Farhadi CSE 455
Slides from Alexei Efros, Steve Marschner Filters & fourier theory.
Image Sampling Moire patterns -
Image Pyramids and Blending
Recap from Friday Pinhole camera model Perspective projections Lenses and their flaws Focus Depth of field Focal length and field of view.
Image Representation Gaussian pyramids Laplacian Pyramids
Announcements Class web site – Handouts –class info –lab access/accounts –survey Readings.
Computer Vision Spring ,-685 Instructor: S. Narasimhan Wean 5409 T-R 10:30am – 11:50am.
The Frequency Domain Somewhere in Cinque Terre, May 2005 Many slides borrowed from Steve Seitz CS194: Image Manipulation & Computational Photography Alexei.
Medical Image Analysis Image Enhancement Figures come from the textbook: Medical Image Analysis, by Atam P. Dhawan, IEEE Press, 2003.
Image Processing Xuejin Chen Ref:
Lecture 4: Image Resampling and Reconstruction CS4670: Computer Vision Kavita Bala.
CS 4487/6587 Algorithms for Image Analysis
CS4670 / 5670: Computer Vision KavitaBala Lecture 17: Panoramas.
Computer Vision Spring ,-685 Instructor: S. Narasimhan Wean 5403 T-R 3:00pm – 4:20pm.
Templates, Image Pyramids, and Filter Banks
Computational Photography lecture 8 – segmentation CS (future 572) Spring 2016 Prof. Alex Berg (Credits to many other folks on individual slides)
Image Stitching II Linda Shapiro CSE 455. RANSAC for Homography Initial Matched Points.
Computer vision. Applications and Algorithms in CV Tutorial 3: Multi scale signal representation Pyramids DFT - Discrete Fourier transform.
Projects Project 1a due this Friday Project 1b will go out on Friday to be done in pairs start looking for a partner now.
Image Stitching Computer Vision CS 691E Some slides from Richard Szeliski.
Hebrew University Image Processing Exercise Class 8 Panoramas – Stitching and Blending Min-Cut Stitching Many slides from Alexei Efros.
Recall: Gaussian smoothing/sampling G 1/4 G 1/8 Gaussian 1/2 Solution: filter the image, then subsample Filter size should double for each ½ size reduction.
Medical Image Analysis
Image Stitching II Linda Shapiro EE/CSE 576.
Graphcut Textures:Image and Video Synthesis Using Graph Cuts
Image Blending : Computational Photography
CS 4501: Introduction to Computer Vision Sparse Feature Detectors: Harris Corner, Difference of Gaussian Connelly Barnes Slides from Jason Lawrence, Fei.
Image Blending and Compositing
Image Sampling Moire patterns
Image Sampling Moire patterns
Multiscale Analysis of Images
Image Stitching II Linda Shapiro EE/CSE 576.
Image Stitching II Linda Shapiro CSE 455.
Image Stitching Computer Vision CS 678
Filtering Part 2: Image Sampling
Image Sampling Moire patterns
Resampling.
Image Stitching II Linda Shapiro EE/CSE 576.
Photometric Processing
Presentation transcript:

Image Pyramids and Blending © Kenneth Kwan 15-463: Computational Photography Alexei Efros, CMU, Fall 2006

Gaussian pre-filtering Solution: filter the image, then subsample Filter size should double for each ½ size reduction. Why?

Subsampling with Gaussian pre-filtering Solution: filter the image, then subsample Filter size should double for each ½ size reduction. Why? How can we speed this up?

Image Pyramids Known as a Gaussian Pyramid [Burt and Adelson, 1983] In computer graphics, a mip map [Williams, 1983] A precursor to wavelet transform

A bar in the big images is a hair on the zebra’s nose; in smaller images, a stripe; in the smallest, the animal’s nose Figure from David Forsyth

What are they good for? Improve Search Precomputation Image Processing Search over translations Like homework Classic coarse-to-fine strategy Search over scale Template matching E.g. find a face at different scales Precomputation Need to access image at different blur levels Useful for texture mapping at different resolutions (called mip-mapping) Image Processing Editing frequency bands separately E.g. image blending…

Gaussian pyramid construction filter mask Repeat Filter Subsample Until minimum resolution reached can specify desired number of levels (e.g., 3-level pyramid) The whole pyramid is only 4/3 the size of the original image!

Image Blending

+ = Feathering Encoding transparency I(x,y) = (aR, aG, aB, a) 1 + = Encoding transparency I(x,y) = (aR, aG, aB, a) Iblend = Ileft + Iright

Affect of Window Size 1 left 1 right

Affect of Window Size 1 1

Good Window Size 1 “Optimal” Window: smooth but not ghosted

What is the Optimal Window? To avoid seams window >= size of largest prominent feature To avoid ghosting window <= 2*size of smallest prominent feature Natural to cast this in the Fourier domain largest frequency <= 2*size of smallest frequency image frequency content should occupy one “octave” (power of two) FFT

What if the Frequency Spread is Wide FFT Idea (Burt and Adelson) Compute Fleft = FFT(Ileft), Fright = FFT(Iright) Decompose Fourier image into octaves (bands) Fleft = Fleft1 + Fleft2 + … Feather corresponding octaves Flefti with Frighti Can compute inverse FFT and feather in spatial domain Sum feathered octave images in frequency domain Better implemented in spatial domain

What does blurring take away? original

What does blurring take away? smoothed (5x5 Gaussian)

High-Pass filter smoothed – original

Band-pass filtering Gaussian Pyramid (low-pass images) Laplacian Pyramid (subband images) Created from Gaussian pyramid by subtraction

Laplacian Pyramid Need this! Original image How can we reconstruct (collapse) this pyramid into the original image?

Pyramid Blending 1 1 1 Left pyramid blend Right pyramid

Pyramid Blending

laplacian level 4 laplacian level 2 laplacian level left pyramid right pyramid blended pyramid

Laplacian Pyramid: Blending General Approach: Build Laplacian pyramids LA and LB from images A and B Build a Gaussian pyramid GR from selected region R Form a combined pyramid LS from LA and LB using nodes of GR as weights: LS(i,j) = GR(I,j,)*LA(I,j) + (1-GR(I,j))*LB(I,j) Collapse the LS pyramid to get the final blended image

Blending Regions

Horror Photo © prof. dmartin

Season Blending (St. Petersburg)

Season Blending (St. Petersburg)

Simplification: Two-band Blending Brown & Lowe, 2003 Only use two bands: high freq. and low freq. Blends low freq. smoothly Blend high freq. with no smoothing: use binary mask

2-band Blending Low frequency (l > 2 pixels) High frequency (l < 2 pixels)

Linear Blending

2-band Blending

Gradient Domain In Pyramid Blending, we decomposed our image into 2nd derivatives (Laplacian) and a low-res image Let us now look at 1st derivatives (gradients): No need for low-res image captures everything (up to a constant) Idea: Differentiate Blend Reintegrate

Gradient Domain blending (1D) bright Two signals dark Regular blending Blending derivatives

Gradient Domain Blending (2D) Trickier in 2D: Take partial derivatives dx and dy (the gradient field) Fiddle around with them (smooth, blend, feather, etc) Reintegrate But now integral(dx) might not equal integral(dy) Find the most agreeable solution Equivalent to solving Poisson equation Can use FFT, deconvolution, multigrid solvers, etc.

Comparisons: Levin et al, 2004

Perez et al., 2003

Perez et al, 2003 Limitations: editing Can’t do contrast reversal (gray on black -> gray on white) Colored backgrounds “bleed through” Images need to be very well aligned

Don’t blend, CUT! Moving objects become ghosts So far we only tried to blend between two images. What about finding an optimal seam?

Davis, 1998 Segment the mosaic Single source image per segment Avoid artifacts along boundries Dijkstra’s algorithm

constrained by overlap Efros & Freeman, 2001 block Input texture B1 B2 Neighboring blocks constrained by overlap B1 B2 Minimal error boundary cut B1 B2 Random placement of blocks

Minimal error boundary overlapping blocks vertical boundary _ = 2 overlap error min. error boundary

Graphcuts What if we want similar “cut-where-things-agree” idea, but for closed regions? Dynamic programming can’t handle loops

Graph cuts (simple example à la Boykov&Jolly, ICCV’01) a cut n-links hard constraint Minimum cost cut can be computed in polynomial time (max-flow/min-cut algorithms)

Kwatra et al, 2003 Actually, for this example, DP will work just as well…

Lazy Snapping (Li el al., 2004) Interactive segmentation using graphcuts

Putting it all together Compositing images Have a clever blending function Feathering blend different frequencies differently Gradient based blending Choose the right pixels from each image Dynamic programming – optimal seams Graph-cuts Now, let’s put it all together: Interactive Digital Photomontage, 2004 (video)

+ = Back to Feathering Encoding transparency I(x,y) = (aR, aG, aB, a) 1 + = Encoding transparency I(x,y) = (aR, aG, aB, a) Iblend = Ileft + Iright

Setting alpha: simple averaging Alpha = .5 in overlap region

Image feathering Weight each image proportional to its distance from the edge (distance map [Danielsson, CVGIP 1980] 1. Generate weight map for each image 2. Sum up all of the weights and divide by sum: weights sum up to 1: wi’ = wi / ( ∑i wi)

Setting alpha: center weighting Distance transform Ghost! Alpha = dtrans1 / (dtrans1+dtrans2)

Setting alpha for Pyramid blending Distance transform Alpha = logical(dtrans1>dtrans2)