Introduction to Image Super-resolution. Presenter: Kevin Su

Similar documents
Enhancing DubaiSat-1 Satellite Imagery Using a Single Image Super-Resolution

Super-Resolution. Many slides from Miki Elad Technion Yosi Rubner RTC and more

Adaptive Multiple-Frame Image Super- Resolution Based on U-Curve

Super-Resolution from Image Sequences A Review

IMAGE RECONSTRUCTION WITH SUPER RESOLUTION

A Survey On Super Resolution Image Reconstruction Techniques

Super-Resolution (SR) image re-construction is the process of combining the information from multiple

EFFICIENT PERCEPTUAL, SELECTIVE,

Super Resolution Using Graph-cut

Robust Video Super-Resolution with Registration Efficiency Adaptation

Super-Resolution. Deepesh Jain. EE 392J Digital Video Processing Stanford University Winter

Patch Based Blind Image Super Resolution

Belief propagation and MRF s

A Novel Multi-Frame Color Images Super-Resolution Framework based on Deep Convolutional Neural Network. Zhe Li, Shu Li, Jianmin Wang and Hongyang Wang

Super-Resolution on Moving Objects and Background

Novel Iterative Back Projection Approach

Multi-frame super-resolution with no explicit motion estimation

ZOOM-BASED SUPER-RESOLUTION IMAGE RECONSTRUCTION FROM IMAGES WITH DIFFERENT ORIENTATIONS. A Thesis by. Chandana K.K. Jayasooriya

Super-resolution Image Reconstuction Performance

Resolution. Super-Resolution Imaging. Problem

Super-Resolution Image with Estimated High Frequency Compensated Algorithm

INTERNATIONAL JOURNAL OF ELECTRONICS AND COMMUNICATION ENGINEERING & TECHNOLOGY (IJECET)

Predictive Interpolation for Registration

Super resolution: an overview

Influence of Training Set and Iterative Back Projection on Example-based Super-resolution

EECS 556 Image Processing W 09. Interpolation. Interpolation techniques B splines

Algorithms for Markov Random Fields in Computer Vision

Belief propagation and MRF s

Image Restoration. Diffusion Denoising Deconvolution Super-resolution Tomographic Reconstruction

A Fast Image Super-Resolution Algorithm Using an Adaptive Wiener Filter

Single Image Super-Resolution

AN ITERATIVE APPROACH TO IMAGE SUPER-RESOLUTION

Investigation of Superresolution using Phase based Image Matching with Function Fitting

Resolution Magnification Technique for Satellite Images Using DT- CWT and NLM

Face Hallucination Based on Eigentransformation Learning

Guided Image Super-Resolution: A New Technique for Photogeometric Super-Resolution in Hybrid 3-D Range Imaging

Comparative Analysis of Edge Based Single Image Superresolution

An improved non-blind image deblurring methods based on FoEs

Sally Wood Thomas J. Bannan Professor in Electrical Engineering, Santa Clara University. IEEE SCV Signal Processing Society Chapter 13 December 2016

Research Article Video Superresolution Reconstruction Using Iterative Back Projection with Critical-Point Filters Based Image Matching

Example-Based Super-Resolution

Performance study on point target detection using super-resolution reconstruction

Image Interpolation using Collaborative Filtering

Accurate Image Registration for MAP Image Super-Resolution

Image Processing. Filtering. Slide 1

Single-Image Super-Resolution Using Multihypothesis Prediction

Learning based face hallucination techniques: A survey

Locally Adaptive Learning for Translation-Variant MRF Image Priors

Learning Based Enhancement Model of Iris

SUPER-RESOLUTION RECONSTRUCTION OF CARDIAC MRI BY USING COUPLED DICTIONARY LEARNING

IMAGE RESTORATION VIA EFFICIENT GAUSSIAN MIXTURE MODEL LEARNING

A Novel Image Super-resolution Reconstruction Algorithm based on Modified Sparse Representation

Super-resolution on Text Image Sequences

Efficient Graphical Models for Processing Images

A Comparative Study & Analysis of Image Restoration by Non Blind Technique

Region Weighted Satellite Super-resolution Technology

Semantic Segmentation. Zhongang Qi

Edge-Preserving MRI Super Resolution Using a High Frequency Regularization Technique

Video Super-Resolution by Motion Compensated Iterative Back-Projection Approach *

Graphical Models, Bayesian Method, Sampling, and Variational Inference

Image Restoration using Markov Random Fields

Estimation of High Resolution Images and Registration Parameters from Low Resolution Observations

Regularized Energy Minimization Models in Image Processing. Tibor Lukić. Faculty of Technical Sciences, University of Novi Sad, Serbia

Steen Moeller Center for Magnetic Resonance research University of Minnesota

Problem Set 4. Assigned: March 23, 2006 Due: April 17, (6.882) Belief Propagation for Segmentation

BME I5000: Biomedical Imaging

NEW TECHNIQUES TO CONQUER THE IMAGE RESOLUTION ENHANCEMENT PROBLEM

CONTENT ADAPTIVE SCREEN IMAGE SCALING

Spatially Adaptive Block-Based Super-Resolution Heng Su, Liang Tang, Ying Wu, Senior Member, IEEE, Daniel Tretter, and Jie Zhou, Senior Member, IEEE

Linear models for multi-frame super-resolution restoration under non-affine registration and spatially varying PSF.

Dense Image-based Motion Estimation Algorithms & Optical Flow

IMAGE super-resolution is the process of reconstructing

Single and Multi-view Video Super-resolution

CoE4TN3 Medical Image Processing

Exploiting Self-Similarities for Single Frame Super-Resolution

f(x,y) is the original image H is the degradation process (or function) n(x,y) represents noise g(x,y) is the obtained degraded image p q

Imager Design using Object-Space Prior Knowledge

1 Lecture 10: Markov Random Fields (MRF s)

Single Image Super Resolution of Textures via CNNs. Andrew Palmer

Image Registration Lecture 4: First Examples

Edge-Directed Interpolation in a Bayesian Framework

A New Approach For Regularized Image Interpolation

IJESRT. Scientific Journal Impact Factor: (ISRA), Impact Factor: 2.114

Digital Image Processing Laboratory: MAP Image Restoration

x' = c 1 x + c 2 y + c 3 xy + c 4 y' = c 5 x + c 6 y + c 7 xy + c 8

15.10 Curve Interpolation using Uniform Cubic B-Spline Curves. CS Dept, UK

Generalizing the Non-Local-Means to Super-resolution Reconstruction

Bilevel Sparse Coding

Wavelet-Based Superresolution in Astronomy

Unrolling Inference: The Recurrent Inference Machine

Image Super-Resolution Reconstruction Based On L 1/2 Sparsity

Efficient Regression for Computational Imaging: from Color Management to Omnidirectional Superresolution

Wavelet-Based Superresolution in Astronomy

Robust Single Image Super-resolution based on Gradient Enhancement

Using Subspace Constraints to Improve Feature Tracking Presented by Bryan Poling. Based on work by Bryan Poling, Gilad Lerman, and Arthur Szlam

Babu Madhav Institute of Information Technology Years Integrated M.Sc.(IT)(Semester - 7)

Computer Vision I - Basics of Image Processing Part 1

A A A. Fig.1 image patch. Then the edge gradient magnitude is . (1)

Segmentation: Clustering, Graph Cut and EM

Multiple Model Estimation : The EM Algorithm & Applications

Transcription:

Introduction to Image Super-resolution Presenter: Kevin Su

References 1. S.C. Park, M.K. Park, and M.G. KANG, Super-Resolution Image Reconstruction: A Technical Overview, IEEE Signal Processing Magazine, Vol. 20, pp. 21-36, May 2003 2. W.T. Freeman, T.R. Jones, and E.C. Pasztor, Example-Based Super-Resolution, IEEE Computer Graphics and Applications, Vol. 22, pp. 56-65, 2002.

Overview Introduction Super-resolution Techniques Multi-frame Super-resolution Single-frame Super-resolution Conclusion

Terminology Low-Resolution (LR): Pixel density within an image is small, therefore offering less details. High-Resolution (HR): Pixel density within an image is larger, therefore offering more details. Superresolution (SR): Obtaining a HR image from one or multiple LR images.

Application Medical imaging (ie. CAT, MRI, etc). Satellite imaging Enlarging consumer photographs Video surveillance (ie. Car wash kidnapping). Converting NTSC video content to highdefinition television

Application raw After apply super-resolution technique

Application zoom apply super-resolution technique

Application Video with low resolution Video with high resolution

Application

How to increase resolution? Possible ways for increasing an image resolution: Reducing pixel size. Increase the chip-size. Super-resolution.

How to increase resolution? Reduce pixel size: Increase the number of pixels per unit area. Advantage: Increases spatial resolution. Disadvantage: Noise introduced. As the pixel size decreases, the amount of light decreases.

How to increase resolution? Increase the chip size (HW): Advantage: Enhances spatial resolution. Disadvantage: High cost for high precision optics.

How to increase resolution? Superresolution (SR): Process of combining multiple low resolution images to form a high resolution image. Advantages: Cost less than comparable approaches. LR imaging systems can still be utilized.

Overview Introduction Super-resolution Techniques Multi-frame Super-resolution Single-frame Super-resolution Conclusion

Multi-frame Super-resolution How can we obtain a HR image from multiple LR images? Basic premise is the availability of multiple LR image captured form the same scene. These multiple LR images provide different looks at the same scene. Each LR is naturally shifted with subpixel precision. If LR images are shifted by integer units, then each image contains the same information, SR is not possible. If LR images have different subpixel shifts, then SR is possible.

Basic premise for SR

Common image acquisition System

Observation Model First step to understanding SR is to formulate an Observation Model to relate the LR images to the desired HR image.

Desired HR image: Size: L 1N1 L2N 2 T Vector: where LR images: Observation Model x = x, x,..., ] [ 1 2 Size: N 1 N 2 K-th LR image: where =,, x N N = L N y k = [y ] k,1,yk,2,...,yk,m k 1 2..., p and M = N N 1 2 1 1 L2N 2 T

Observation Model Observation model can be represented as follows: y k = DB M x + n for 1 k M k is a warp matrix B k represents blur matrix D is a sub-sampling matrix represents noise matrix n k k Without loss of generality, it can also be represented as follows: y k = W x + n for 1 k k k k k p p

Nonuniform interpolation 3 stages: Registration Interpolation Deblurring approach

Nonuniform interpolation Registration: approach Need to estimate the scene motion for each image with reference to one particular image. The motion can be estimated as a 1-to-1 representation between the reference image and each of the images.

Registration: Nonuniform interpolation approach Estimating the completely arbitrary motion in real world image scenes is extremely difficult, with almost no guarantees of estimator performance. Incorrect estimates of motion have disastrous implications on overall SR performance.

Nonuniform interpolation Interpolation: approach Since the shifts between the LR images are arbitrary, the images will not always match up to a uniformly to the HR grid. Thus, nonuniform interpolation is necessary to obtain a uniformly spaced HR image from a nonuniformly spaced composite of LR images. Nonuniform interpolation between LR images are used to improve resolution.

Nonuniform interpolation approach Interpolation: This step requires interpolation when the estimated fractional unit of motion is not equal to the HR grid reference image.

Nonuniform interpolation approach Deblurring: In SR, blur is usually modeled as a spatial averaging operator as shown below.

Result

Regularized SR Reconstruction If there are enough LR images, we can solve y k = W x + n for 1 In reality, it is hard to find sufficient number of LR images. Use procedure (called regularization) to stabilize the inversion of illposed problem. Deterministic Approach (CLS) Stochastic Approach (MAP) k k k p

Deterministic Approach (CLS) CLS can be formulated by choosing x to minimize the Lagrangian p k = 1 y k W x k 2 + α Cx C is generally a high-pass filter α is regularization parameter The cost function above is convex and differentiable with the use of a quadratic regularization term. We can find a unique estimate image using iterative techniques xˆ p p T T Wk Wk + αc C xˆ = k = 1 k = 1 W T k y k

Stochastic Approach (MAP) Bayesian approach provides a flexible and convenient way to model a priori knowledge concerning solution x = arg max P( x y1, y2,..., y p ). x = arg max{ln P( y1, y2,..., y p x) + ln P( x)}. Using MRF Gibbs priori to define P(x) 1 1 P( X = x) = exp{ U ( x)} = exp( ϕc( x)) Z Z c S

Result

Other Approaches Frequency Domain Approach Projection onto Convex Sets Approach ML (maximum likelihood approach) ML-POCS hybrid approach Iterative back-projection approach Adaptive Filtering Approach Motionless SR Reconstruction Approach

Overview Introduction Super-resolution Techniques Multi-frame Super-resolution Single-frame Super-resolution Conclusion

Overview Introduction Super-resolution Techniques Multi-frame Super-resolution Single-frame Super-resolution Conclusion

Single-frame SR Traditional resolution enhancement: Smoothing (Gaussian, Wiener, and median filters) Interpolation (Nearest ngbr, bilinear, bicubic and cubic spline etc) Sharpening by amplifying existing image details (it is useful to do, provided noise isn t amplified) Single-frame SR: Estimate missing high-resolution detail that isn t present in the original image, and which we can t make visible by simple sharpening

Example-based SR Algorithm uses a training set to learn the fine details of an image at lowresolution. It then uses those learned relationships to predict fine details in other images. Markov network One pass algorithm

Training Set Generation Start with a collection of HR images. For each HR image, degrade it to get a LR image. Blur & subsample each to create LR image of ¼ total pixels. Apply analytical interpolation to the LR image. ie. Cubic spline. This will generate an image of desired # of pixels, but lacking the HR detail. Band pass filter and contrast normalize the interpolated image AND the original HR image.

Training Set Generation

Training Set Generation Divide images into small patches: 5x5 (HR), 7x7 (LR)

Markov network

Markov network Select the 16 or so closet examples to each input patch as the different states of the hidden nodes, x, that we seek to estimate. Maximize 1 P( x y) = ψ (, ) ij xi x j φk ( xk, yk ) Z where d ψ ( x ij i, x ( x, x j ) j ) ( ij) d exp ij i = 2 2σ ij i, the sum of squared differences between patch candidates x i and x j in their overlap regions at nodes i and j ( x, x j ) k

One pass algorithm

Results

Training Set

Results

Conclusions and future works Current SR approaches are effective to some extent SR considering registration error: Use total least squares method to minimize the error Use channel adaptive regularization: SR images with large registration error should be less contributed to the estimate of the HR. Blind SR Image Reconstruction: when blurring process is unknown. Need blur identification. Computationally efficient SR Algorithm