Patch-based Image Interpolation: Algorithms and Applications

Slides:



Advertisements
Similar presentations
Transform-based Non-local Methods for Image Restoration IT530, Lecture Notes.
Advertisements

Multiscale Analysis of Images Gilad Lerman Math 5467 (stealing slides from Gonzalez & Woods, and Efros)
Patch-based Image Deconvolution via Joint Modeling of Sparse Priors Chao Jia and Brian L. Evans The University of Texas at Austin 12 Sep
5. 1 Model of Image degradation and restoration
Image Denoising using Locally Learned Dictionaries Priyam Chatterjee Peyman Milanfar Dept. of Electrical Engineering University of California, Santa Cruz.
Hiroyuki Takeda, Hae Jong Seo, Peyman Milanfar EE Department University of California, Santa Cruz Jan 11, 2008 Statistical Image Quality Measures.
Error detection and concealment for Multimedia Communications Senior Design Fall 06 and Spring 07.
Belief Propagation on Markov Random Fields Aggeliki Tsoli.
Variational Bayesian Image Processing on Stochastic Factor Graphs Xin Li Lane Dept. of CSEE West Virginia University.
1 Outline  Introduction to JEPG2000  Why another image compression technique  Features  Discrete Wavelet Transform  Wavelet transform  Wavelet implementation.
Xin Li LDCSEE WVU Spring From Gene to Meme Example of Memes: -Cultural ideas, symbols -Religions -Languages -Mathematics (e.g., Gaussian.
School of Computing Science Simon Fraser University
1 Image Completion using Global Optimization Presented by Tingfan Wu.
Announcements Project 4 questions? Guest lectures Thursday: Richard Ladner “tactile graphics” Next Tuesday: Jenny Yuen and Jeff Bigham.
Image Denoising via Learned Dictionaries and Sparse Representations
1 On the Statistical Analysis of Dirty Pictures Julian Besag.
New Results in Image Processing based on Sparse and Redundant Representations Michael Elad The Computer Science Department The Technion – Israel Institute.
Primal Sketch Integrating Structure and Texture Ying Nian Wu UCLA Department of Statistics Keck Meeting April 28, 2006 Guo, Zhu, Wu (ICCV, 2003; GMBV,
Particle filters (continued…). Recall Particle filters –Track state sequence x i given the measurements ( y 0, y 1, …., y i ) –Non-linear dynamics –Non-linear.
* Joint work with Michal Aharon Guillermo Sapiro
Sparse and Redundant Representation Modeling for Image Processing Michael Elad The Computer Science Department The Technion – Israel Institute of technology.
(1) A probability model respecting those covariance observations: Gaussian Maximum entropy probability distribution for a given covariance observation.
Automatic Estimation and Removal of Noise from a Single Image
Applications of Image Filters Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem 02/04/10.
1 Patch Complexity, Finite Pixel Correlations and Optimal Denoising Anat Levin, Boaz Nadler, Fredo Durand and Bill Freeman Weizmann Institute, MIT CSAIL.
Computer Vision – Compression(2) Hanyang University Jong-Il Park.
Why do we Need Image Model in the first place?
SVCL Automatic detection of object based Region-of-Interest for image compression Sunhyoung Han.
DTU Medical Visionday May 27, 2009 Generative models for automated brain MRI segmentation Koen Van Leemput Athinoula A. Martinos Center for Biomedical.
Wavelets and Denoising Jun Ge and Gagan Mirchandani Electrical and Computer Engineering Department The University of Vermont October 10, 2003 Research.
INDEPENDENT COMPONENT ANALYSIS OF TEXTURES based on the article R.Manduchi, J. Portilla, ICA of Textures, The Proc. of the 7 th IEEE Int. Conf. On Comp.
Presented by Daniel Khashabi Joint work with Sebastian Nowozin, Jeremy Jancsary, Andrew W. Fitzgibbon and Bruce Lindbloom.
Texture Optimization for Example-based Synthesis Vivek Kwatra Irfan Essa Aaron Bobick Nipun Kwatra.
Sparsity-based Image Deblurring with Locally Adaptive and Nonlocally Robust Regularization Weisheng Dong a, Xin Li b, Lei Zhang c, Guangming Shi a a Xidian.
Forward-Scan Sonar Tomographic Reconstruction PHD Filter Multiple Target Tracking Bayesian Multiple Target Tracking in Forward Scan Sonar.
RIDA: A Robust Information-Driven Data Compression Architecture for Irregular Wireless Sensor Networks Nirupama Bulusu (joint work with Thanh Dang, Wu-chi.
Image Quilting for Texture Synthesis and Transfer Alexei A. Efros (UC Berkeley) William T. Freeman (MERL) Siggraph01 ’
Image Enhancement [DVT final project]
Real-Time Exemplar-Based Face Sketch Synthesis Pipeline illustration Note: containing animations Yibing Song 1 Linchao Bao 1 Qingxiong Yang 1 Ming-Hsuan.
EE565 Advanced Image Processing Copyright Xin Li Motivating Applications HDTV Internet video Artistic reproduction Widescreen movie.
Fields of Experts: A Framework for Learning Image Priors (Mon) Young Ki Baik, Computer Vision Lab.
Advances in digital image compression techniques Guojun Lu, Computer Communications, Vol. 16, No. 4, Apr, 1993, pp
EE565 Advanced Image Processing Copyright Xin Li Image Denoising Theory of linear estimation Spatial domain denoising techniques Conventional Wiener.
Nonparametric Modeling of Images
EE565 Advanced Image Processing Copyright Xin Li Why do we Need Image Model in the first place? Any image processing algorithm has to work on a collection.
1 Markov random field: A brief introduction (2) Tzu-Cheng Jen Institute of Electronics, NCTU
Patch-based Nonlocal Denoising for MRI and Ultrasound Images Xin Li Lane Dept. of CSEE West Virginia University.
2D Texture Synthesis Instructor: Yizhou Yu. Texture synthesis Goal: increase texture resolution yet keep local texture variation.
SuperResolution (SR): “Classical” SR (model-based) Linear interpolation (with post-processing) Edge-directed interpolation (simple idea) Example-based.
Nonparametric Modeling of Textures Outline Parametric vs. nonparametric Image patches and similarity distance Efros-Leung’s texture synthesis by non- parametric.
WCPM 1 Chang-Tsun Li Department of Computer Science University of Warwick UK Image Clustering Based on Camera Fingerprints.
EE565 Advanced Image Processing Copyright Xin Li Further Improvements Gaussian scalar mixture (GSM) based denoising* (Portilla et al.’ 2003) Instead.
Single Image Interpolation via Adaptive Non-Local Sparsity-Based Modeling The research leading to these results has received funding from the European.
EE5965 Advanced Image Processing Copyright Xin Li Post-processing: Fighting Against Coding Artifacts Deblocking of DCT coded images – Image.
EE565 Advanced Image Processing Copyright Xin Li Why do we Need Image Model in the first place? Any image processing algorithm has to work on a collection.
Introduction to Medical Imaging Week 5: Introduction to Medical Imaging Week 5: MRI (part II) and Denoising (part I) Guy Gilboa Course
Jianchao Yang, John Wright, Thomas Huang, Yi Ma CVPR 2008 Image Super-Resolution as Sparse Representation of Raw Image Patches.
Introduction to Medical Imaging Week 6: Introduction to Medical Imaging Week 6: Denoising (part II) – Variational Methods and Evolutions Guy Gilboa Course.
1 Nonlinear models for Natural Image Statistics Urs Köster & Aapo Hyvärinen University of Helsinki.
Sparsity Based Poisson Denoising and Inpainting
Fast edge-directed single-image super-resolution
WAVELET VIDEO PROCESSING TECHNOLOGY
Image Processing Digital image Fundamentals. Introduction to the course Grading – Project: 30% – Midterm Exam: 30% – Final Exam : 40% – Total: 100% –
The Chinese University of Hong Kong
School of Electronic Engineering, Xidian University, Xi’an, China
Outline S. C. Zhu, X. Liu, and Y. Wu, “Exploring Texture Ensembles by Efficient Markov Chain Monte Carlo”, IEEE Transactions On Pattern Analysis And Machine.
Compressive Sensing Imaging
Review and Importance CS 111.
Lecture 7 Patch based methods: nonlocal means, BM3D, K- SVD, data-driven (tight) frame.
Presentation transcript:

Patch-based Image Interpolation: Algorithms and Applications Xin Li Lane Dept. of CSEE West Virginia University

Where Does Patch Come from? Neuroscience: receptive fields of neighboring cells in human vision system have severe overlapping Engineering: patch has been under the disguise of many different names such as windows in digital filters, blocks in JPEG and the support of wavelet bases, Cited from D. Hubel, “Eye, Brain and Vision”, 1988

Patch-based Image Models Local models Markov Random Field (MRF) and higher-order extensions (e.g., Field-of-Expert) Transform-based: PCA, DCT, wavelets Nonlocal models Bilateral filtering (Tomasi et al. ICCV’1998) Texture synthesis via Nonparametric resampling (Efros&Leung ICCV’1999) Exemplar-based inpainting (Criminisi et al. TIP’2004) Nonlocal mean denoising (Buades et al.’ CVPR’2005) Total Least-Square denoising (Hirakawa&Parks TIP’2006) Block-matching 3D denoising (Dabov et al. TIP’2007)

A Bayesian Formulation of Image Interpolation Problem Likelihood (our focus here) Image prior (e.g., sparsity-based) Unobservable data Observable data Model class (e.g., local vs. nonlocal)

A Simple Extension of BM3D Hard thresholding 3D transform of similar patches Basic idea: combine BM3D with progressive thresholding (Guleryuz TIP’2006)

Interpolation of LR Images x y bicubic NEDI1 this work 31.76dB 32.36dB 32.63dB 34.71dB 34.45dB 37.35dB 28.70dB6 27.34dB 28.19dB 18.81dB 15.37dB 16.45dB 1X. Li and M. Orchard, “New edge directed interpolation”, IEEE TIP, 2001

Go Back to Biology rods cone Spatially random distribution of rod/cone cells keeps aliasing artifacts out of our vision

Interpolation of Nonuniformly-sampled Images x y DT KR this work 29.06dB 31.56dB 34.96dB DT- Delauney Triangle-based (griddata under MATLAB) KR- Kernal Regression-based (Takeda et al. IEEE TIP 2007) 28.46dB 31.16dB 36.51dB 26.04dB 24.63dB 29.91dB 17.90dB 18.49dB 29.25dB

Modeling Spatial Randomness Extensively studied in geostatistics and environmental statistics (e.g., spatial distribution of animals and plants) Mathematically modeled by homogeneous Poisson process (density parameterλ) Lack of positional differentiation Lack of scale differentiation Empirically there exist quadrant-based and distance-based randomness metrics

Monte-Carlo Based Optimization The lower energy the more random Iterative procedure: randomly pick two locations (one black and the other white), if swapping them decreases the energy, accept it; otherwise accept it with some probability

Importance of Locations after optimization In biological world: evolution + development before optimization Identical reconstruction algorithm; only differ on sampling locations

Application into Compressive Imaging Random Sampling Pattern S quantization channel interpolation sensor node How is it different from conventional image coding system? No bits are spent on coding the location information (random=no cost).

Coding Results R=0.21bpp original ours PSNR=27.85dB SSIM=0.8750 SPIHT

Error Resilience Results

Conclusions A good image prior is useful to many processing tasks involving incomplete or noisy observation As we move from local to nonlocal models, the location of sampling points becomes important – “location (address) and intensity (data) are the same thing” cited from T. Kohonen “Self-Organization and Associative Memory” Image processing is at the intersection of science and engineering- will BM3D lead to a new class of SOM?