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.

Slides:



Advertisements
Similar presentations
Ter Haar Romeny, FEV Geometry-driven diffusion: nonlinear scale-space – adaptive scale-space.
Advertisements

Group Meeting Presented by Wyman 10/14/2006
Optimizing and Learning for Super-resolution
Ter Haar Romeny, Computer Vision 2014 Geometry-driven diffusion: nonlinear scale-space – adaptive scale-space.
Hongliang Li, Senior Member, IEEE, Linfeng Xu, Member, IEEE, and Guanghui Liu Face Hallucination via Similarity Constraints.
Accelerating Spatially Varying Gaussian Filters Jongmin Baek and David E. Jacobs Stanford University.
Patch-based Image Deconvolution via Joint Modeling of Sparse Priors Chao Jia and Brian L. Evans The University of Texas at Austin 12 Sep
A Sampled Texture Prior for Image Super-Resolution Lyndsey C. Pickup, Stephen J. Roberts and Andrew Zisserman, Robotics Research Group, University of Oxford.
H. R. Sheikh, A. C. Bovik, “Image Information and Visual Quality,” IEEE Trans. Image Process., vol. 15, no. 2, pp , Feb Lab for Image and.
Image Denoising using Locally Learned Dictionaries Priyam Chatterjee Peyman Milanfar Dept. of Electrical Engineering University of California, Santa Cruz.
Guillaume Lavoué Mohamed Chaker Larabi Libor Vasa Université de Lyon
Image Super-Resolution Using Sparse Representation By: Michael Elad Single Image Super-Resolution Using Sparse Representation Michael Elad The Computer.
Bayesian Image Super-resolution, Continued Lyndsey C. Pickup, David P. Capel, Stephen J. Roberts and Andrew Zisserman, Robotics Research Group, University.
DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML Fast super-resolution of video sequences using sparse directional transforms* Sandeep Kanumuri.
ON THE IMPROVEMENT OF IMAGE REGISTRATION FOR HIGH ACCURACY SUPER-RESOLUTION Michalis Vrigkas, Christophoros Nikou, Lisimachos P. Kondi University of Ioannina.
Mean Squared Error : Love It or Leave It ?. Why do we love the MSE ? It is simple. It has a clear physical meaning. The MSE is an excellent metric in.
Texture Reading: Chapter 9 (skip 9.4) Key issue: How do we represent texture? Topics: –Texture segmentation –Texture-based matching –Texture synthesis.
Dorin Comaniciu Visvanathan Ramesh (Imaging & Visualization Dept., Siemens Corp. Res. Inc.) Peter Meer (Rutgers University) Real-Time Tracking of Non-Rigid.
J OURNAL C LUB : Yang and Ni, Xidian University, China “Multimodality medical image fusion based on multiscale geometric analysis of contourlet transform.”
Linear Filtering About modifying pixels based on neighborhood. Local methods simplest. Linear means linear combination of neighbors. Linear methods simplest.
Automatic Estimation and Removal of Noise from a Single Image
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.
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.
1 Patch Complexity, Finite Pixel Correlations and Optimal Denoising Anat Levin, Boaz Nadler, Fredo Durand and Bill Freeman Weizmann Institute, MIT CSAIL.
Prakash Chockalingam Clemson University Non-Rigid Multi-Modal Object Tracking Using Gaussian Mixture Models Committee Members Dr Stan Birchfield (chair)
Estimation-Quantization Geometry Coding using Normal Meshes
CAP5415: Computer Vision Lecture 4: Image Pyramids, Image Statistics, Denoising Fall 2006.
Participation in the NIPS 2003 Challenge Theodor Mader ETH Zurich, Five Datasets were provided for experiments: ARCENE: cancer diagnosis.
بسمه تعالی IQA Image Quality Assessment. Introduction Goal : develop quantitative measures that can automatically predict perceived image quality. 1-can.
What is Image Quality Assessment?
Jointly Optimized Regressors for Image Super-resolution Dengxin Dai, Radu Timofte, and Luc Van Gool Computer Vision Lab, ETH Zurich 1.
R. Ray and K. Chen, department of Computer Science engineering  Abstract The proposed approach is a distortion-specific blind image quality assessment.
MDDSP Literature Survey Presentation Eric Heinen
Object Detection with Discriminatively Trained Part Based Models
Edge-Directed Image Interpolation Nickolaus Mueller, Yue Lu, and Minh N. Do “In theory, there is no difference between theory and practice; In practice,
Supervised Learning of Edges and Object Boundaries Piotr Dollár Zhuowen Tu Serge Belongie.
Fast Direct Super-Resolution by Simple Functions
Structured Face Hallucination Chih-Yuan Yang Sifei Liu Ming-Hsuan Yang Electrical Engineering and Computer Science 1.
Why is computer vision difficult?
Images Similarity by Relative Dynamic Programming M. Sc. thesis by Ady Ecker Supervisor: prof. Shimon Ullman.
Just Noticeable Difference Estimation For Images with Structural Uncertainty WU Jinjian Xidian University.
Segmentation of Vehicles in Traffic Video Tun-Yu Chiang Wilson Lau.
Non-Ideal Iris Segmentation Using Graph Cuts
Filtering Objective –improve SNR and CNR Challenges – blurs object boundaries and smears out important structures.
Demosaicking for Multispectral Filter Array (MSFA)
Learning Photographic Global Tonal Adjustment with a Database of Input / Output Image Pairs.
1 Marco Carli VPQM /01/2007 ON BETWEEN-COEFFICIENT CONTRAST MASKING OF DCT BASIS FUNCTIONS Nikolay Ponomarenko (*), Flavia Silvestri(**), Karen.
Speaker Min-Koo Kang March 26, 2013 Depth Enhancement Technique by Sensor Fusion: MRF-based approach.
Scale-Space and Edge Detection Using Anisotropic Diffusion Presented By:Deepika Madupu Reference: Pietro Perona & Jitendra Malik.
Jianchao Yang, John Wright, Thomas Huang, Yi Ma CVPR 2008 Image Super-Resolution as Sparse Representation of Raw Image Patches.
SUPER RESOLUTION USING NEURAL NETS Hila Levi & Eran Amar Weizmann Ins
Deeply-Recursive Convolutional Network for Image Super-Resolution
Fast edge-directed single-image super-resolution
Learning Mid-Level Features For Recognition
Nikolay Ponomarenkoa, Vladimir Lukina, Oleg I. Ieremeieva,
Machine Learning Basics
Super-resolution Image Reconstruction
Presenter: Hajar Emami
Machine Learning Feature Creation and Selection
Enhanced-alignment Measure for Binary Foreground Map Evaluation
A Comparative Study for Single Image Blind Deblurring
Pei Qi ECE at UW-Madison
Research Topic Error Concealment Techniques in H.264/AVC for Wireless Video Transmission Vineeth Shetty Kolkeri EE Graduate,UTA.
Historic Document Image De-Noising using Principal Component Analysis (PCA) and Local Pixel Grouping (LPG) Han-Yang Tang1, Azah Kamilah Muda1, Yun-Huoy.
Computational Imaging and Display Project Title
Review and Importance CS 111.
Single image super-resolution with limited number of filters
Lecture 7 Patch based methods: nonlocal means, BM3D, K- SVD, data-driven (tight) frame.
Presentation transcript:

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

Motivation We would like to figure out some questions. Which is the best super-resolution algorithm? What is the influence of blur kernel width? What metric should be used?

Approach (step 1) We collect 11 state-of-the-art super-resolution algorithms 1.Bicubic interpolation 2.Back projection (Irani 93 : IP) 3.Fast image/video (Shan 07 : SLJT) 4.Gradient profile (Sun 08 : SSXS) 5.Self example (Glasner 09 : GBI) 6.Sparse regression (Kim 10 : KK) 7.Sparse representation (Yang 10 : YWHM) 8.Local self example (Freedman 11 : FF) 9.Adaptive regularization (Dong 11 : DZSW) 10.Simple function (Yang 13 : YY) 11.Anchored neighborhood regression (Timofte 13 : TSG)

Approach (step 2) We set 2 parameters Scaling factors as 6 values Blurring kernel width as 9 values to generate super-resolution images from 2 datasets Berkeley segmentation dataset (200 images) LIVE dataset (29 images)

Approach (step 3) We conduct a human subject study to collect perceptual scores and compute the ranked correlation coefficient between the perceptual scores and 8 metric indices 1.PSNR 2.Weighted PSNR 3.SSIM 4.Multi-scale SSIM 5.VIF (visual information fidelity) 6.UIQI (universal image quality index) 7.IFC (information fidelity criterion) 8.NQM (noise quality measure)

Flow chart (1) (2) (3) (4) (5) Prepare ground truth images

Flow chart (1) (2) (3) (4) (5) Generate low-resolution images

Flow chart (1) (2) (3) (4) (5) Generate super-resolution images

Flow chart (1) (2) (3) (4) (5) Compute metric indices

Flow chart (1) (2) (3) (4) (5) Compute correlation coefficients

Averaged Metric Indices BSD dataset (200 images) LIVE dataset (29 images) s=2 s=3 s=4 s=5 s=6 s=8

We find BSD dataset (200 images) s=2 s=3 s=4 the SLJT, FF, DZSW methods generate misaligned super-resolution results and low metric indices

We find BSD dataset (200 images) s=2 s=3 s=4 the best Gaussian kernel width is proportional to the scaling factor

Reason Information remained in a low-resolution image is determined by 2 factors 1.blurring 2.subsampling When a subsampling ratio is larger, a larger kernel maximizes the remained information in low- resolution images.

We find index / PSNR all algorithms work well for smooth images but poorly for highly textured images. Easiest Most challenging

Reason All test algorithms use appearance features and statistical approaches. Thus they effectively handle smooth regions but difficultly reconstruct textures.

Perceptual correlations Best: IFC Worst: VIF PSNR SSIM

Reason IFC is a metric modelled by natural image priors based on high-frequency features Our test images are all natural images The perceptual scores are determined by the reconstructed high-frequency details

Conclusions IFC metric shows higher correlation with perceptual scores than PSNR and SSIM Existing algorithms have difficulty to reconstruct high-frequency textures A scaling factor of 4 is already challenging

Future Work How to overcome the limitation of visual features and statistical approaches? How to evaluate super-resolution results without a ground truth image?

Code and datasets available 11 algorithms on MATLAB 4 of our implementation (IP, SSXS, GBI, FF) 7 of original release 400 Perceptual scores 130,000 super-resolution images 1M evaluation values