DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML Fast super-resolution of video sequences using sparse directional transforms* Sandeep Kanumuri.

Slides:



Advertisements
Similar presentations
Image Enhancement by Regularization Methods Andrey S. Krylov, Andrey V. Nasonov, Alexey S. Lukin Moscow State University Faculty of Computational Mathematics.
Advertisements

11/11/02 IDR Workshop Dealing With Location Uncertainty in Images Hasan F. Ates Princeton University 11/11/02.
Pixel Recovery via Minimization in the Wavelet Domain Ivan W. Selesnick, Richard Van Slyke, and Onur G. Guleryuz *: Polytechnic University, Brooklyn, NY.
INTERNATIONAL CONFERENCE ON TELECOMMUNICATIONS, ICT '09. TAREK OUNI WALID AYEDI MOHAMED ABID NATIONAL ENGINEERING SCHOOL OF SFAX New Low Complexity.
2004 COMP.DSP CONFERENCE Survey of Noise Reduction Techniques Maurice Givens.
Patch-based Image Deconvolution via Joint Modeling of Sparse Priors Chao Jia and Brian L. Evans The University of Texas at Austin 12 Sep
SWE 423: Multimedia Systems
H.264/AVC Baseline Profile Decoder Complexity Analysis Michael Horowitz, Anthony Joch, Faouzi Kossentini, and Antti Hallapuro IEEE TRANSACTIONS ON CIRCUITS.
1 Audio Compression Techniques MUMT 611, January 2005 Assignment 2 Paul Kolesnik.
1 Robust Video Stabilization Based on Particle Filter Tracking of Projected Camera Motion (IEEE 2009) Junlan Yang University of Illinois,Chicago.
Image Denoising via Learned Dictionaries and Sparse Representations
Probabilistic video stabilization using Kalman filtering and mosaicking.
Direct Methods for Visual Scene Reconstruction Paper by Richard Szeliski & Sing Bing Kang Presented by Kristin Branson November 7, 2002.
Prague Institute of Chemical Technology - Department of Computing and Control Engineering Digital Signal & Image Processing Research Group Brunel University,
Image Denoising with K-SVD Priyam Chatterjee EE 264 – Image Processing & Reconstruction Instructor : Prof. Peyman Milanfar Spring 2007.
MPEG Audio Compression by V. Loumos. Introduction Motion Picture Experts Group (MPEG) International Standards Organization (ISO) First High Fidelity Audio.
SUSAN: structure-preserving noise reduction EE264: Image Processing Final Presentation by Luke Johnson 6/7/2007.
Scalable Wavelet Video Coding Using Aliasing- Reduced Hierarchical Motion Compensation Xuguang Yang, Member, IEEE, and Kannan Ramchandran, Member, IEEE.
2D Fourier Theory for Image Analysis Mani Thomas CISC 489/689.
Introduction to Wavelets
EE565 Advanced Image Processing Copyright Xin Li Different Frameworks for Image Processing Statistical/Stochastic Models: Wiener’s MMSE estimation.
Xinqiao LiuRate constrained conditional replenishment1 Rate-Constrained Conditional Replenishment with Adaptive Change Detection Xinqiao Liu December 8,
A Nonlinear Loop Filter for Quantization Noise Removal in Hybrid Video Compression Onur G. Guleryuz DoCoMo USA Labs
Despeckle Filtering in Medical Ultrasound Imaging
ENG4BF3 Medical Image Processing
Unitary Extension Principle: Ten Years After Zuowei Shen Department of Mathematics National University of Singapore.
Predicting Wavelet Coefficients Over Edges Using Estimates Based on Nonlinear Approximants Onur G. Guleryuz Epson Palo Alto Laboratory.
WEIGHTED OVERCOMPLETE DENOISING Onur G. Guleryuz Epson Palo Alto Laboratory Palo Alto, CA (Please view in full screen mode to see.
Audio Compression Usha Sree CMSC 691M 10/12/04. Motivation Efficient Storage Streaming Interactive Multimedia Applications.
Windows Media Video 9 Tarun Bhatia Multimedia Processing Lab University Of Texas at Arlington 11/05/04.
Iterated Denoising for Image Recovery Onur G. Guleryuz To see the animations and movies please use full-screen mode. Clicking on.
Ping Zhang, Zhen Li,Jianmin Zhou, Quan Chen, Bangsen Tian
Seeram Chapter 7: Image Reconstruction
Image Compression Supervised By: Mr.Nael Alian Student: Anwaar Ahmed Abu-AlQomboz ID: IT College “Multimedia”
BARCODE IDENTIFICATION BY USING WAVELET BASED ENERGY Soundararajan Ezekiel, Gary Greenwood, David Pazzaglia Computer Science Department Indiana University.
Image Denoising Using Wavelets
Wavelets and Multiresolution Processing (Wavelet Transforms)
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.
Advances in digital image compression techniques Guojun Lu, Computer Communications, Vol. 16, No. 4, Apr, 1993, pp
Digital Image Processing Lecture 21: Lossy Compression Prof. Charlene Tsai.
Spatial Sparsity Induced Temporal Prediction for Hybrid Video Compression Gang Hua and Onur G. Guleryuz Rice University, Houston, TX DoCoMo.
Image Decomposition, Inpainting, and Impulse Noise Removal by Sparse & Redundant Representations Michael Elad The Computer Science Department The Technion.
Nonlinear Approximation Based Image Recovery Using Adaptive Sparse Reconstructions Onur G. Guleryuz Epson Palo Alto Laboratory.
SuperResolution (SR): “Classical” SR (model-based) Linear interpolation (with post-processing) Edge-directed interpolation (simple idea) Example-based.
Single Image Interpolation via Adaptive Non-Local Sparsity-Based Modeling The research leading to these results has received funding from the European.
SIMD Implementation of Discrete Wavelet Transform Jake Adriaens Diana Palsetia.
Compressive Sensing Techniques for Video Acquisition EE5359 Multimedia Processing December 8,2009 Madhu P. Krishnan.
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.
Iterative Techniques for Image Interpolation
Motion tracking TEAM D, Project 11: Laura Gui - Timisoara Calin Garboni - Timisoara Peter Horvath - Szeged Peter Kovacs - Debrecen.
Image Processing Architecture, © Oleh TretiakPage 1Lecture 5 ECEC 453 Image Processing Architecture Lecture 5, 1/22/2004 Rate-Distortion Theory,
Date of download: 6/29/2016 Copyright © 2016 SPIE. All rights reserved. Potential imaging modes. (a) Each detector in a focal plane array measures the.
Computational Controlled Mode Selection for H.264/AVC June Computational Controlled Mode Selection for H.264/AVC Ariel Kit & Amir Nusboim Supervised.
Wavelet Transform Advanced Digital Signal Processing Lecture 12
Compressive Coded Aperture Video Reconstruction
Quality Evaluation and Comparison of SVC Encoders
Computing and Compressive Sensing in Wireless Sensor Networks
Digital Image Processing Lecture 21: Lossy Compression
Last update on June 15, 2010 Doug Young Suh
T. Chernyakova, A. Aberdam, E. Bar-Ilan, Y. C. Eldar
Yinsheng Liu, Beijing Jiaotong University, China
Research Topic Error Concealment Techniques in H.264/AVC for Wireless Video Transmission Vineeth Shetty Kolkeri EE Graduate,UTA.
Digital Image Processing
Reduction of blocking artifacts in DCT-coded images
Govt. Polytechnic Dhangar(Fatehabad)
Research Institute for Future Media Computing
Scalable light field coding using weighted binary images
Lecture 7 Patch based methods: nonlocal means, BM3D, K- SVD, data-driven (tight) frame.
Presentation transcript:

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML Fast super-resolution of video sequences using sparse directional transforms* Sandeep Kanumuri Onur G. Guleryuz DoCoMo USA Labs *Presented at 2008 SIAM Conference on Imaging Science on 07/09/2008 (Animated slides, please use slide show mode)

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML 2 Outline System Model Motivation Prior Work Our Solution: SWAT (Sparse Warped transform and Adaptive Thresholding) –Algorithm Flowchart –Over-complete Transform –Warped (Directional) Transform –Over-complete Inverse Transform –Adaptive Thresholding Performance Comparison Conclusion

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML 3 System Model Design goals 1.High Quality Rendering 2.Fast Algorithm (Lower Complexity) – Single Frame, Simple Transform

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML Motivation

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML 5 Broadcast Video – TV application Docking station Low-resolution video signal for mobile phones Low-resolution video is sent to the docking station Docking station uses the SWAT algorithm to convert low-resolution video to high-resolution video High-resolution video is sent to a TV or a large display BENEFIT: Broadcast programming aimed at mobile phones can also be used in stationary environments A.1 A.2 B Low-resolution video is converted to high- resolution video by the cell phone itself using the SWAT algorithm and high- resolution video is transmitted to the TV using local wireless technologies Only one path (Path A or Path B) is used

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML 6 Broadcast Video – VGA phones Low-resolution video signal for mobile phones BENEFIT: SWAT capability allows this cell phone to convert low-resolution video to high-resolution video VGA phone with SWAT capability VGA phone without SWAT capability

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML 7 More Applications… Video Quality Enhancement Service –SWAT algorithm can be deployed as a service to enhance the resolution and quality of videos Video Conferencing –A SWAT equipped terminal can show video at a higher zoom level and with improved quality High-quality Image Zooming –SWAT algorithm enables the mobile phone to convert the low quality, low resolution image into a high quality, high resolution image

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML 8 Prior Work Linear solutions –Filter design Non-linear solutions –Regularization (Projection onto the model space) Signal Sparsity –Iterated Denoising / Shrinkage –Lp-Norm Minimization Optical Flow Adaptive filtering Example-based approaches –Data Consistency (Projection onto the input space)

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML 9 SWAT Algorithm Flowchart Output Image/Video Input Image/Video Linear Interpolation Filter Directional Over-complete Transform Adaptive Thresholding Directional Over-complete Inverse Transform Enforce Data Consistency More iterations? Low-resolution, low quality High-resolution, low quality High-resolution, high quality yesno Regularization

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML 10 Linear Interpolation Filter A linear interpolation filter is used to form an initial estimate of the high-resolution image/video –However, the quality of interpolation is relatively low Popular filter choice –Low pass filter of Daubechies 7/9 Inverse Wavelet –H.264 Interpolation Filter A customized linear interpolation filter can be used, if any of the following is known. –Downsampling filter (if the input was obtained by downsampling a higher resolution original) –Filtering caused by the camera acquisition process

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML 11 0N-1 k (Sparse Decomposition Domain)(Signal Domain) S(k) +T -T 0N-1 n s(n) 0N-1 k C(k) ^ (Denoised) Core idea – Exploit Signal Sparsity S(k) 0N-1 k + W(k) C(k) = “noise”

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML 12 Transform size: 4x4 (used for description), 3x3 Transform used: DCT, Hadamard For an Over-complete Transform –all possible 4x4 blocks in the image/frame are selected using a non- directional mask –Each 4x4 block undergoes a transform to produce a set of transformed coefficients –Each pixel is involved in multiple transforms (16, on the average) –Total number of transformed coefficients ~ 16 x number of pixels Directional Over-complete Transform –Here, each of the 4x4 blocks is formed by applying a directional mask followed by a warping process (see next slide) Block (1,1) Block (2,1) Block (H-3,1)Block (H-3,2)Block (H-3,W-3) Block (1,2)Block (1,W-3) Block (2,2)Block (2,W-3) … … … … … … Blocks of an Over-complete Transform H = Height of image; W = Width of image Non-directional mask used to select a 4x4 block Over-complete Transform

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML 13 but violated on directional edges Signal sparsity in DCT domain holds for horizontal and veritcal edges Non-directional mask Directional masks Transform domain: 4x4 DCT Transform support is warped Animated Slide, Please use slide show mode Let us consider 4 blocks along the edge - First, using Non-directional masks - Now, using Directional masks - Directional masks lead to sparse representation For Directional Over-complete Transform, Directional masks replace the Non-directional mask Warped (Directional) Transform

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML 14 Decision made for a block (4x4) of pixels –At each pixel, a vote is cast for the mask that minimizes the signal variance along the mask direction. –The mask with the most votes is chosen Reduces inconsistency in directions How to choose a mask? Example masks

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML 15 Over-complete Inverse Transform For an Over-complete Inverse Transform –Each set of transformed coefficients is converted back to pixel domain –Each pixel has multiple estimates from different blocks and a weighted combination is used to arrive at its final estimate W1W2W3 and so on with all the blocks….

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML 16 Adaptive Thresholding Transform coefficients are thresholded for denoising A master threshold ( ) is used for an initial pass A local threshold ( ) is calculated and finally used –E lost : Energy lost due to thresholding when is used as threshold. Parameters f 1 to f n and E 1 to E n are tuned to achieved a local optimum 1 f1f1 f2f2 fnfn (0,0)E2E2 E1E1 EnEn E lost f()

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML 17 Enforcing Data Consistency Role of data consistency module –Ensure that the high-resolution estimate, when downsampled, can produce the low-resolution input. Data Consistency module Downsampling Filter Linear Interpolation Filter High-resolution Input Low-resolution Input High-resolution Output + + _ +

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML 18 Performance Comparison Super-resolution of QCIF to CIF sequences –Low pass filter from Daubechies 7/9 wavelet filter bank –Compression is done using H.264/AVC codec (JM12.0) SWAT run with 2 iterations Compared with –Bilinear interpolation –H.264 interpolation –Simple Inverse –Iterated Denoising / Shrinkage (ID) 2 iterations (similar complexity compared to SWAT) 10 iterations

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML 19 PSNR comparison (uncompressed)

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML 20 PSNR comparison (uncompressed)

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML 21 PSNR comparison (uncompressed)

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML 22 H264 ID (2 iterations)SWAT Visual Comparison (uncompressed)

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML 23 H264 ID (2 iterations)SWAT Visual Comparison (uncompressed)

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML 24 PSNR comparison (compression at QP=20)

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML 25 PSNR comparison (compression at QP=25)

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML 26 H264 SWAT Visual Comparison (compression at QP=25)

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML 27 Visual Comparison (compression at QP=25) H264 SWAT

DoCoMo USA Labs All Rights Reserved Sandeep Kanumuri, NML 28 Conclusion SWAT algorithm renders high quality output and yet remains fast –Quality comparable to ID (10 iterations) –Complexity comparable to ID (2 iterations) Enabling Features –Over-complete transform representation –Simple basic transform (Hadamard, Integer DCT) –Sparse warped transform –Adaptive thresholding –Weighted inverse transform Reference –S. Kanumuri, O. G. Guleryuz and M. R. Civanlar, "Fast super-resolution reconstructions of mobile video using warped transforms and adaptive thresholding", SPIE Applications of Digital Image Processing XXX, August 2007 Flicker Reduction Application –To appear in SPIE 2008 (Applications of Digital Image Processing XXXI) –Sandeep Kanumuri –Onur G. Guleryuz