Fast edge-directed single-image super-resolution

Slides:



Advertisements
Similar presentations
Bayesian Belief Propagation
Advertisements

Image Enhancement by Regularization Methods Andrey S. Krylov, Andrey V. Nasonov, Alexey S. Lukin Moscow State University Faculty of Computational Mathematics.
A Robust Super Resolution Method for Images of 3D Scenes Pablo L. Sala Department of Computer Science University of Toronto.
Image Super-resolution via Sparse Representation
Optimizing and Learning for Super-resolution
QR Code Recognition Based On Image Processing
Improving resolution and depth of astronomical observations (via modern mathematical methods for image analysis) M. Castellano, D. Ottaviani, A. Fontana,
Various Regularization Methods in Computer Vision Min-Gyu Park Computer Vision Lab. School of Information and Communications GIST.
L1 sparse reconstruction of sharp point set surfaces
Boundary Detection - Edges Boundaries of objects –Usually different materials/orientations, intensity changes.
Lecture 23 Exemplary Inverse Problems including Earthquake Location.
Hongliang Li, Senior Member, IEEE, Linfeng Xu, Member, IEEE, and Guanghui Liu Face Hallucination via Similarity Constraints.
Patch-based Image Deconvolution via Joint Modeling of Sparse Priors Chao Jia and Brian L. Evans The University of Texas at Austin 12 Sep
Shape From Light Field meets Robust PCA
IMAGE UPSAMPLING VIA IMPOSED EDGE STATISTICS Raanan Fattal. ACM Siggraph 2007 Presenter: 이성호.
1 Removing Camera Shake from a Single Photograph Rob Fergus, Barun Singh, Aaron Hertzmann, Sam T. Roweis and William T. Freeman ACM SIGGRAPH 2006, Boston,
Patch Based Synthesis for Single Depth Image Super-Resolution (ECCV 2012) Oisin Mac Aodha, Neill Campbell, Arun Nair and Gabriel J. Brostow Presented By:
Sampling, Aliasing, & Mipmaps
Soft Edge Smoothness Prior for Alpha Channel Super Resolution Shengyang Dai 1, Mei Han 2, Wei Xu 2, Ying Wu 1, Yihong Gong 2 1.EECS Department, Northwestern.
1 Image filtering Hybrid Images, Oliva et al.,
Motion Analysis (contd.) Slides are from RPI Registration Class.
ON THE IMPROVEMENT OF IMAGE REGISTRATION FOR HIGH ACCURACY SUPER-RESOLUTION Michalis Vrigkas, Christophoros Nikou, Lisimachos P. Kondi University of Ioannina.
Optical flow and Tracking CISC 649/849 Spring 2009 University of Delaware.
2D Fourier Theory for Image Analysis Mani Thomas CISC 489/689.
Optical Flow Estimation
EE565 Advanced Image Processing Copyright Xin Li Different Frameworks for Image Processing Statistical/Stochastic Models: Wiener’s MMSE estimation.
CSCE 641 Computer Graphics: Image Registration Jinxiang Chai.
Advanced Computer Vision Chapter 3 Image Processing (2) Presented by: 傅楸善 & 張乃婷
Session: Image Processing Seung-Tak Noh 五十嵐研究室 M2.
Dual Evolution for Geometric Reconstruction Huaiping Yang (FSP Project S09202) Johannes Kepler University of Linz 1 st FSP-Meeting in Graz, Nov ,
Frequency-domain Bayer demosaicking
Jointly Optimized Regressors for Image Super-resolution Dengxin Dai, Radu Timofte, and Luc Van Gool Computer Vision Lab, ETH Zurich 1.
Image Processing Edge detection Filtering: Noise suppresion.
Edge-Directed Image Interpolation Nickolaus Mueller, Yue Lu, and Minh N. Do “In theory, there is no difference between theory and practice; In practice,
Fast Direct Super-Resolution by Simple Functions
Qiaochu Li, Qikun Guo, Saboya Yang and Jiaying Liu* Institute of Computer Science and Technology Peking University Scale-Compensated Nonlocal Mean Super.
Structured Face Hallucination Chih-Yuan Yang Sifei Liu Ming-Hsuan Yang Electrical Engineering and Computer Science 1.
Effective Optical Flow Estimation
Single Image Super-Resolution: A Benchmark Chih-Yuan Yang 1, Chao Ma 2, Ming-Hsuan Yang 1 UC Merced 1, Shanghai Jiao Tong University 2.
The 18th Meeting on Image Recognition and Understanding 2015/7/29 Depth Image Enhancement Using Local Tangent Plane Approximations Kiyoshi MatsuoYoshimitsu.
Advanced Computer Vision Chapter 3 Image Processing (2) Presented by: 林政安
1 Markov random field: A brief introduction (2) Tzu-Cheng Jen Institute of Electronics, NCTU
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
SuperResolution (SR): “Classical” SR (model-based) Linear interpolation (with post-processing) Edge-directed interpolation (simple idea) Example-based.
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 7
Projects Project 1a due this Friday Project 1b will go out on Friday to be done in pairs start looking for a partner now.
Using Neumann Series to Solve Inverse Problems in Imaging Christopher Kumar Anand.
Jianchao Yang, John Wright, Thomas Huang, Yi Ma CVPR 2008 Image Super-Resolution as Sparse Representation of Raw Image Patches.
RECONSTRUCTION OF MULTI- SPECTRAL IMAGES USING MAP Gaurav.
Deeply-Recursive Convolutional Network for Image Super-Resolution
Image Resampling & Interpolation
Summary of “Efficient Deep Learning for Stereo Matching”
Khallefi Leïla © esa Supervisors: J. L. Vazquez M. Küppers
Depth Map Upsampling by Self-Guided Residual Interpolation
Synthesis of X-ray Projections via Deep Learning
Super-resolution Image Reconstruction
Presenter: Hajar Emami
School of Electronic Engineering, Xidian University, Xi’an, China
CSCE 643 Computer Vision: Thinking in Frequency
Inferring Edges by Using Belief Propagation
Announcements more panorama slots available now
Image Resampling & Interpolation
MCMC Inference over Latent Diffeomorphisms
Announcements more panorama slots available now
Unfolding with system identification
Advanced deconvolution techniques and medical radiography
Single image super-resolution with limited number of filters
Recent Developments on Super-Resolution
Presentation transcript:

Fast edge-directed single-image super-resolution Mushfiqur Rouf1 Dikpal Reddy2 Kari Pulli2 Rabab K Ward1 1University of British Columbia 2Light co an improved EDI Design an image prior Develop a PD algorithm for SISR (Describe the terms)

Single image super-resolution 2x2 SISR as we know…

Fast edge-directed SISR Combines Sparse gradient “Smooth contour” Small overhead Prior more general purpose than SISR SISR methods Filtering / forward methods Bilinear, bicubic, … Anisotropic methods Deep learning methods Inverse / reconstruction methods Total variation (TV) optimization Markov random fields Bilateral filtering + optimization Can’t begin to cover all the techniques… Forward and inverse Inverse problems use a global optimization; slower but are expected to distribute error

= Image formation model Priors Sparse gradient Smooth contour [http://www.imaging-resource.com/PRODS/pentax-k3/pentax-k3SELECTIVE_LPF.HTM] Observed image Anti-aliasing filter Latent image = Priors Sparse gradient Smooth contour Convolution Downsampling First formalize how LR is produced Assuming Gaussian noise… Forward model

Inverse problem formulation At what cost? Observed image Is it worth the cost? Complementary Anti-aliasing filter Is the method useful? Latent image Priors Sparse gradient Smooth contour Convolution Downsampling Only sharpens image across edges. Edges could be jaggy. Also smooths edge structure along the edge contours. No jaggy edge. …The corresponding inverse problem becomes L2 minimization Underdetermined Need priors Two priors… Questions we ask Complementary is the key Data fitting

Inverse problem formulation Observed image Anti-aliasing filter TV-only SR Latent image Smooth contour Convolution Downsampling Gradient Why not bilateral filter here? Total variation With TV this is the standard TV-only SR As the second prior why not bilateral? Data fitting Sparse gradient

Inverse problem formulation Observed image Anti-aliasing filter TV-only SR Latent image Proposed Convolution Downsampling Gradient Downsampling anisotropic interpolation Total variation Smooth contour “anisotropic interpolatedness” needs to be faaast Combats jagginess  improved reconst That’s all in theory… Data fitting Sparse gradient Little computation overhead Improved reconstruction

Smooth contour prior – at what cost? Our improvement Smooth contour …let’s see what happens in practice. … And here’s some intuition as to why that happens… Edge directed interpolation [Li and Orchard 2001] Sparse gradient prior only (TV optimization) Little computation overhead Little computation overhead Improved reconstruction Improved reconstruction

Ours (sparse gradient and smooth contour) Smooth contour prior Ground truth Bicubic TV optimization Star chart Ours (sparse gradient and smooth contour) LR input EDI

Inverse problem formulation Observed image Anti-aliasing filter anisotropic interpolation Latent image Convolution Downsampling Gradient Downsampling Total variation Smooth contour Back to the formulation Data fitting Sparse gradient Little computation overhead Improved reconstruction

Choice of anisotropic interpolation Goals: Local calculations Direct estimation of interpolation weights Fast implementation We choose: [Li and Orchard 2001] Newer versions of the method overkill

Intro to EDI [Li and Orchard 2001] Edge directed interpolation Detects local “edge orientation” Sliding-window linear least-squares regressions Interpolates along the edge [Li and Orchard 2001]

Intro to EDI [Li and Orchard 2001] Two step process for upsampling

Intro to EDI [Li and Orchard 2001] Sliding window process ?

Intro to EDI [Li and Orchard 2001] Downsides Edge misestimation artifacts Fixed 2x2 upsampling Upsampled image not sharp Performs very well where the edge estimates are accurate 4x4 [http://chiranjivi.tripod.com/EDITut.html]

Our improvements to EDI Wrapped up in a prior and used a data fitting term and a complementary prior Removes misestimation artifacts Regularized regression Speedup  iterative application possible

EDI Speedup Original EDI too slow to use iteratively We propose a speedup: Dynamic programming: Remove costly overlapping recalculations

Inverse problem formulation Observed image Anti-aliasing filter Edge directed upsampling Latent image Convolution Downsampling Gradient Downsampling Total variation Smooth contour Little computation overhead Data fitting Sparse gradient Improved reconstruction

Primal dual optimization Convex Mixture of L1 and L2 priors --> Primal dual method

Primal dual optimization

Primal dual optimization Primal dual form

Primal dual optimization Standard TV optimization Our prior [Chambolle and Pock 2010]

Results - dyadic 2x2 Ground truth

Results - dyadic 2x2 PSNR: 32.25 SSIM: 0.9858 [He-Siu 2011]

Results - dyadic 2x2 PSNR: 34.97 SSIM: 0.9961 [Kwon et al. 2014]

Results - dyadic 2x2 PSNR: 35.13 SSIM: 0.9928 Our method

Results - nondyadic 3x3 Ground truth

Results - nondyadic 3x3 PSNR: 23.28 SSIM: 0.9041 [Yang 2010]

Results - nondyadic 3x3 PSNR: 24.17 SSIM: 0.9218 [Kwon et al. 2014]

Results - nondyadic 3x3 PSNR: 23.93 SSIM: 0.9122 Our method

Comparisons with deep learning 4x4 Ground truth

Comparisons with deep learning 4x4 PSNR: 32.95 SSIM: 0.9442 Our method

Comparisons with deep learning 4x4 PSNR: 33.12 SSIM: 0.9504 [Dong et al. 2014]

Comparisons with deep learning 4x4 PSNR: 33.28 SSIM: 0.9513 [Timofte et al. 2014]

Conclusions Proposed a novel natural image prior Application in Fast. Complementary to sparse gradient prior Any anisotropic upsampling method can be used Potentially deep learning methods? (Future work!) Application in SISR Similar image reconstruction problems (future work)

Fast edge-directed single-image super-resolution Thanks! Fast edge-directed single-image super-resolution Mushfiqur Rouf1 Dikpal Reddy2 Kari Pulli2 Rabab K Ward1 1University of British Columbia 2Light co