Super-Resolution Barak Zackay Yaron Kassner. Outline Introduction to Super-Resolution Reconstruction Based Super Resolution –An Algorithm –Limits on Reconstruction.

Slides:



Advertisements
Similar presentations
A Two-Step Approach to Hallucinating Faces: Global Parametric Model and Local Nonparametric Model Ce Liu Heung-Yeung Shum Chang Shui Zhang CVPR 2001.
Advertisements

Andrew Cosand ECE CVRR CSE
Image Enhancement by Regularization Methods Andrey S. Krylov, Andrey V. Nasonov, Alexey S. Lukin Moscow State University Faculty of Computational Mathematics.
Optimizing and Learning for Super-resolution
The fundamental matrix F
QR Code Recognition Based On Image Processing
Principal Component Analysis Based on L1-Norm Maximization Nojun Kwak IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008.
Presented by Xinyu Chang
Support Vector Machines
Hongliang Li, Senior Member, IEEE, Linfeng Xu, Member, IEEE, and Guanghui Liu Face Hallucination via Similarity Constraints.
MASKS © 2004 Invitation to 3D vision Lecture 7 Step-by-Step Model Buidling.
A Sampled Texture Prior for Image Super-Resolution Lyndsey C. Pickup, Stephen J. Roberts and Andrew Zisserman, Robotics Research Group, University of Oxford.
IMAGE RESTORATION AND REALISM MILLIONS OF IMAGES SEMINAR YUVAL RADO.
Visual Recognition Tutorial
Computer Vision Optical Flow
X From Video - Seminar By Randa Khayr Eli Shechtman, Yaron Caspi & Michal Irani.
Image Super-Resolution Using Sparse Representation By: Michael Elad Single Image Super-Resolution Using Sparse Representation Michael Elad The Computer.
Coherency Sensitive Hashing (CSH) Simon Korman and Shai Avidan Dept. of Electrical Engineering Tel Aviv University ICCV2011 | 13th International Conference.
Bayesian Image Super-resolution, Continued Lyndsey C. Pickup, David P. Capel, Stephen J. Roberts and Andrew Zisserman, Robotics Research Group, University.
Surface Reconstruction from 3D Volume Data. Problem Definition Construct polyhedral surfaces from regularly-sampled 3D digital volumes.
Robust Super-Resolution Presented By: Sina Farsiu.
Image Denoising via Learned Dictionaries and Sparse Representations
Very Low Resolution Face Recognition Problem
Contents Description of the big picture Theoretical background on this work The Algorithm Examples.
Direct Methods for Visual Scene Reconstruction Paper by Richard Szeliski & Sing Bing Kang Presented by Kristin Branson November 7, 2002.
ON THE IMPROVEMENT OF IMAGE REGISTRATION FOR HIGH ACCURACY SUPER-RESOLUTION Michalis Vrigkas, Christophoros Nikou, Lisimachos P. Kondi University of Ioannina.
Computing motion between images
A Novel 2D To 3D Image Technique Based On Object- Oriented Conversion.
Pattern Recognition. Introduction. Definitions.. Recognition process. Recognition process relates input signal to the stored concepts about the object.
CSci 6971: Image Registration Lecture 16: View-Based Registration March 16, 2004 Prof. Chuck Stewart, RPI Dr. Luis Ibanez, Kitware Prof. Chuck Stewart,
lecture 2, linear imaging systems Linear Imaging Systems Example: The Pinhole camera Outline  General goals, definitions  Linear Imaging Systems.
Radial-Basis Function Networks
Face Recognition Using Neural Networks Presented By: Hadis Mohseni Leila Taghavi Atefeh Mirsafian.
Seminar presented by: Tomer Faktor Advanced Topics in Computer Vision (048921) 12/01/2012 SINGLE IMAGE SUPER RESOLUTION.
Super-Resolution of Remotely-Sensed Images Using a Learning-Based Approach Isabelle Bégin and Frank P. Ferrie Abstract Super-resolution addresses the problem.
3D-Assisted Facial Texture Super-Resolution Pouria Mortazavian, Josef Kittler, William Christmas 10 September 2009 Centre for Vision, Speech and Signal.
Super-Resolution Dr. Yossi Rubner
Advanced Image Processing Image Relaxation – Restoration and Feature Extraction 02/02/10.
Image Analogies Aaron Hertzmann (1,2) Charles E. Jacobs (2) Nuria Oliver (2) Brian Curless (3) David H. Salesin (2,3) 1 New York University 1 New York.
Yuping Lin and Gérard Medioni.  Introduction  Method  Register UAV streams to a global reference image ▪ Consecutive UAV image registration ▪ UAV to.
Face Alignment Using Cascaded Boosted Regression Active Shape Models
1 Patch Complexity, Finite Pixel Correlations and Optimal Denoising Anat Levin, Boaz Nadler, Fredo Durand and Bill Freeman Weizmann Institute, MIT CSAIL.
SVCL Automatic detection of object based Region-of-Interest for image compression Sunhyoung Han.
Jointly Optimized Regressors for Image Super-resolution Dengxin Dai, Radu Timofte, and Luc Van Gool Computer Vision Lab, ETH Zurich 1.
ECE 8443 – Pattern Recognition LECTURE 07: MAXIMUM LIKELIHOOD AND BAYESIAN ESTIMATION Objectives: Class-Conditional Density The Multivariate Case General.
Learning to perceive how hand-written digits were drawn Geoffrey Hinton Canadian Institute for Advanced Research and University of Toronto.
Mitsubishi Electric Research Labs (MERL) Super-Res from Single Motion Blur PhotoAgrawal & Raskar Amit Agrawal and Ramesh Raskar Mitsubishi Electric Research.
ECE 8443 – Pattern Recognition LECTURE 10: HETEROSCEDASTIC LINEAR DISCRIMINANT ANALYSIS AND INDEPENDENT COMPONENT ANALYSIS Objectives: Generalization of.
Esmaeil Faramarzi, Member, IEEE, Dinesh Rajan, Senior Member, IEEE, and Marc P. Christensen, Senior Member, IEEE Unified Blind Method for Multi-Image Super-Resolution.
Motion Estimation Today’s Readings Trucco & Verri, 8.3 – 8.4 (skip 8.3.3, read only top half of p. 199) Newton's method Wikpedia page
ECE 8443 – Pattern Recognition ECE 8527 – Introduction to Machine Learning and Pattern Recognition LECTURE 12: Advanced Discriminant Analysis Objectives:
Motion Estimation Today’s Readings Trucco & Verri, 8.3 – 8.4 (skip 8.3.3, read only top half of p. 199) Newton's method Wikpedia page
Machine Vision Edge Detection Techniques ENT 273 Lecture 6 Hema C.R.
Instructor: Mircea Nicolescu Lecture 5 CS 485 / 685 Computer Vision.
Jianchao Yang, John Wright, Thomas Huang, Yi Ma CVPR 2008 Image Super-Resolution as Sparse Representation of Raw Image Patches.
CSCI 631 – Foundations of Computer Vision March 15, 2016 Ashwini Imran Image Stitching.
RECONSTRUCTION OF MULTI- SPECTRAL IMAGES USING MAP Gaurav.
SIFT.
CSCI 631 – Foundations of Computer Vision March 15, 2016 Ashwini Imran Image Stitching Link: singhashwini.mesinghashwini.me.
SIFT Scale-Invariant Feature Transform David Lowe
Compressive Coded Aperture Video Reconstruction
LECTURE 11: Advanced Discriminant Analysis
Scale Invariant Feature Transform (SIFT)
Super-resolution Image Reconstruction
A guide to SR different approaches
Inferring Edges by Using Belief Propagation
Announcements more panorama slots available now
SIFT.
Image Segmentation.
Announcements more panorama slots available now
Presentation transcript:

Super-Resolution Barak Zackay Yaron Kassner

Outline Introduction to Super-Resolution Reconstruction Based Super Resolution –An Algorithm –Limits on Reconstruction Based Super Resolution Example Based Super Resolution –Halucination –Example Based –Single Image Super Resolution Summary

Introduction to Super Resolution

Definition of the Problem Super-resolution is the process of combining multiple low resolution images to form a higher resolution one. No cheating! –Resulting image should represent reality better than all the input images.

The Imaging Process

Physical Properties Each camera suffers from some inherent optical issues: –Finite size of the aperture - generates blur, modeled by the Point-Spread-Function (PSF). –Noise

Mathematical Model Each pixel in the resulting image is given by: Lo i (m) – the i-th LR image in pixel m. E i (x) – total photon count from the direction x PSF i – Point Spread Function

Deresolution Given HR image Project to LR image Each LR pixel is a linear combination of HR pixels HR LR

Reconstruction-based Super Resolution Reconstruct hidden HR pixels out of known linear combinations. HR LR

Example-Based Super Resolution Use prior knowledge to reconstruct a HR image. Prior Knowledge of faces

Reconstruction Based Super Resolution from Improving Resolution by Image Registration Michal Irani and Shmuel Peleg

Basic Idea The HR image should create the LR images when deresoluted.

Notation : The k th observed LR image. : The approximation to the HR image after n iterations. : The LR image obtained by applying the simulated imaging process to. : The point spread function of the imaging blur. : a HR pixel : a LR pixel influenced by x : The center of the receptive field of y.

Problem Formulation Find a HR image, that gives. –

Algorithm Overview Register the LR images. Guess the HR image. Iteration n: –Simulate the imaging process to create from. –Compare and. –Correct in the direction of the error. output

Registration HR LR

Iteration Take the current guess. Decrease its resolution to get Update each HR pixel x according to the error in all LR pixels (y) it influences.c is a constant normalizing factor. –c is a constant normalizing factor. –Yk,x is the group of all pixels y that are influenced by x. – is a back-projection kernel applied on that represents the way the HR pixel x should be updated from y.

Wasach One of three input images Initial guess (average of input images) Output

Debluring Original ImageBlurred ImageRestored Image

Wasach Initial GuessBlurred ImageRestored Image

Wasach 1 of 10 LR imagesInitial guessReconstructed Image

Limits on Reconstruction Based Methods from Limits on Super-Resolution and How to Break Them Simon Baker and Takeo Kanade

Large Magnification Factor is Problematic Large magnification factor causes: –Overly smooth HR image –Fine details are not recovered An explanation is needed.

Evil Example Suppose we want to increase the resolution by exactly M=2. Lets look on a checkboard like scene, where each pixel is either white or black. HR LR

Information is Inherently Missing The resulting image would be grey independently from the offset of the LR image! Conclusion: some information is inherently missing on our LR images!

When M is not an Integer HR LR

Limits of Super-Resolution Size of LR images: N pixels. Size of HR image: NM 2 pixels. Each HR pixel can be added noise of amplitude smaller than M 2 which wont change the LR image! Volume of possible HR solutions: O(M 2N ) 1 It can be shown that under practical considerations the effective magnification factor ( M ) is bounded by 1.6, no matter how many LR images are taken 2. 1 Limits on Super-Resolution and How to Break Them, Simon Baker and Takeo Kanade 2 Fundamental Limits of Reconstruction-Based Superresolution Algorithms under Local Translation, Zhouchen Lin, and Heung-Yeung Shum

Break Introduction to Super-Resolution Reconstruction Based Super Resolution –An Algorithm –Limits on Reconstruction Based Super Resolution Example Based Super Resolution –Halucination –Example Based –Single Image Super Resolution Summary

Example Based Super Resolution

Introduction to Example-Based Super Resolution Reconstruction constraints are not enough. One has to use prior knowledge of the image to break the reconstruction limits. The following algorithms will use priors learned from databases of example images.

Recogstruction or Hallucination from Limits on Super-Resolution and How to Break Them Simon Baker and Takeo Kanade

General Idea Find a HR image Su that satisfies two kinds of constraints: –Reconstruction constraints: When projected to the LR dimensions, the image is similar to the observed input images. –Recognition constraints: The pixels of Su should resemble pixels from images in the DB that where found to have similar features to the observed LR images’ features.

MAP formulation To solve the problem, given the LR images, we need to find the HR image that maximizes - Su : the HR image - Lo : the LR images Reconstruction Constraints Recognition Constraints

Reconstruction Constraints The probability of the LR images given the HR image can be computed from the distance between the deresoluted HR image and the LR images. – : the noise variance –PSF : Point Spread Function – : The pixel in Lo that corresponds to pixel z in Su. –m : a LR pixel index

Recognition: LR features We use “Parent Structures” to describe LR features.

Recognition: Choosing the Pixels from the DB PS = Parent Structure F = Features – like First deriviative, or Laplacian

Formulation of Recognition Constraints Instead of estimating the probability of the HR image, Su, we estimate its probability given each pixel’s “recognition”. H 0 – Horizontal derivative V 0 – Vertical derivative. - Variance of the recognition errors. T - the training images. BI – best images for the pixels of the LR images. BP – best pixel indices in the best images for the pixels of the LR images. C i,BP,BI – Class of all images that would have the Best corresponding Images BI, and the Best corresponding Pixels BP in the db. - The function that fits a LR pixel index to the corresponding HR pixel index. 2 k – the ratio between the HR image scale and the LR image scale.

Maximization Note that the function we need to maximize is quadratic with the HR image’s pixels. Do gradient descent.

Algorithm Summary Preliminary work: –Take a training set of images. –Build a DB that matches parent structures to HR pixels. Compute the reconstruction constraints. For each LR image: –For each HR pixel index: Search for the corresponding parent structure in the DB. Find the HR image that fits best both the reconstruction constraints and the HR pixels extracted from the database.

Comparison

Best and Worst Image

Noise Effect

Image Size

Hallucination

Results on Text

Example Based Super Resolution William T. Freeman, Thouis R. Jones and Egon C. Pasztor

Algorithm Overview Construct a DB of matching LR-HR patches Algorithmically find the most coherent patch assignment to generate a good image

Constructing the DB Given a DB of images Make a table from LR patches to HR patches. Each image in the DB is treated as follows: –Take each 7x7 patch from the image and deresolute into a 5x5 patch –Normalize the 5x5 patches to have the same mean and relative contrast. –Arrange the DB by the low frequencies of the LR patches

Local Patch Matching Match a LR patch to a HR patch from the DB, using low frequencies. Get an estimation to the unknown (high) frequencies, based on the match. Remaining problem: match between neighboring overlapping patches.

Global Patch Matching Run over patches from left to right and from top to bottom Match each patch its nearest neighbor in the DB using the predetermined patches as additional constraints.

Algorithm

Wasach

Cubic-spline Super-resolutionTrue high-resolution image

Wasach

Complete Failure

Priors are definitely used!

Super Resolution From a Single Image Daniel Glaser, Shai Bagon and Michal Irani

Patch Redundancy in a Single Image

Employing in-scale Patch Redundancy

Employing Cross-scale Patch Redundancy Build a cascade of decreasing resolution images from the LR image. For each patch in the LR image, search for its Nearest Neighbour in the even lower resolution image. Take the found neighbour’s parent in the original LR image and copy it to be the HR image.

Combining the Methods

Wasach Bicubic interpolation Unified single-image SR (x3)Ground truth image

Wasach Unified single-image SR (x3) Bicubic interpolation

Wasach

Summary We have presented two basic approaches for super resolution: –Reconstruction-based – which simply tries to reverse the imaging process –Example-based – which uses example images to reconstruct the original image. We have shown that there are limits to reconstruction based methods, which are independent of the number of LR images we use. We have presented an algorithm that combines both approaches to achieve SR from a single image.

Questions?