Removing Partial Blur in a Single Image Shengyang Dai and Ying Wu EECS Department, Northwestern University, Evanston, IL 60208, USA 2009CVPR.

Slides:



Advertisements
Similar presentations
Practical Camera Auto-Calibration Based on Object Appearance and Motion for Traffic Scene Visual Surveillance Zhaoxiang Zhang, Min Li, Kaiqi Huang and.
Advertisements

Reconstructing Non-stationary Articulated Objects in Monocular Video using Silhouette Information Saad M. Khan and Mubarak Shah University of Central Florida,
Blind motion deblurring from a single image using sparse approximation
Recovery of relative depth from a single observation using an uncalibrated (real-aperture) camera Vinay P. Namboodiri Subhasis Chaudhuri Department of.
S INGLE -I MAGE R EFOCUSING AND D EFOCUSING Wei Zhang, Nember, IEEE, and Wai-Kuen Cham, Senior Member, IEEE.
GrabCut Interactive Image (and Stereo) Segmentation Carsten Rother Vladimir Kolmogorov Andrew Blake Antonio Criminisi Geoffrey Cross [based on Siggraph.
EVENTS: INRIA Work Review Nov 18 th, Madrid.
Robust Object Tracking via Sparsity-based Collaborative Model
Automatic Identification of Bacterial Types using Statistical Image Modeling Sigal Trattner, Dr. Hayit Greenspan, Prof. Shimon Abboud Department of Biomedical.
Adviser : Ming-Yuan Shieh Student ID : M Student : Chung-Chieh Lien VIDEO OBJECT SEGMENTATION AND ITS SALIENT MOTION DETECTION USING ADAPTIVE BACKGROUND.
Unnatural L 0 Representation for Natural Image Deblurring Speaker: Wei-Sheng Lai Date: 2013/04/26.
Optimization & Learning for Registration of Moving Dynamic Textures Junzhou Huang 1, Xiaolei Huang 2, Dimitris Metaxas 1 Rutgers University 1, Lehigh University.
Andrea Colombari and Andrea Fusiello, Member, IEEE.
Video Coding with Spatio-temporal Texture Synthesis and Edge-based inpainting Chunbo Zhu, Xiaoyan Sun, Feng Wu, and Houqiang Li ICME 2008.
Boundary matting for view synthesis Samuel W. Hasinoff Sing Bing Kang Richard Szeliski Computer Vision and Image Understanding 103 (2006) 22–32.
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.
Efficient Moving Object Segmentation Algorithm Using Background Registration Technique Shao-Yi Chien, Shyh-Yih Ma, and Liang-Gee Chen, Fellow, IEEE Hsin-Hua.
1 Static Sprite Generation Prof ︰ David, Lin Student ︰ Jang-Ta, Jiang
Robust Object Segmentation Using Adaptive Thresholding Xiaxi Huang and Nikolaos V. Boulgouris International Conference on Image Processing 2007.
Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.
A Closed Form Solution to Natural Image Matting
CVPR 2006 New York City Granularity and Elasticity Adaptation in Visual Tracking Ming Yang, Ying Wu NEC Laboratories America Cupertino, CA 95014
CCU VISION LABORATORY Object Speed Measurements Using Motion Blurred Images 林惠勇 中正大學電機系
Interactive Matting Christoph Rhemann Supervised by: Margrit Gelautz and Carsten Rother.
An Iterative Optimization Approach for Unified Image Segmentation and Matting Hello everyone, my name is Jue Wang, I’m glad to be here to present our paper.
Our output Blur kernel. Close-up of child Our output Original photograph.
Dorin Comaniciu Visvanathan Ramesh (Imaging & Visualization Dept., Siemens Corp. Res. Inc.) Peter Meer (Rutgers University) Real-Time Tracking of Non-Rigid.
A REAL-TIME VIDEO OBJECT SEGMENTATION ALGORITHM BASED ON CHANGE DETECTION AND BACKGROUND UPDATING 楊靜杰 95/5/18.
Image Subtraction for Real Time Moving Object Extraction Shahbe Mat Desa, Qussay A. Salih, CGIV’04.
Despeckle Filtering in Medical Ultrasound Imaging
EE392J Final Project, March 20, Multiple Camera Object Tracking Helmy Eltoukhy and Khaled Salama.
Speaker: Chi-Yu Hsu Advisor: Prof. Jian-Jung Ding Leveraging Stereopsis for Saliency Analysis, CVPR 2012.
HMM-BASED PSEUDO-CLEAN SPEECH SYNTHESIS FOR SPLICE ALGORITHM Jun Du, Yu Hu, Li-Rong Dai, Ren-Hua Wang Wen-Yi Chu Department of Computer Science & Information.
1. Introduction Motion Segmentation The Affine Motion Model Contour Extraction & Shape Estimation Recursive Shape Estimation & Motion Estimation Occlusion.
Introduction to Visible Watermarking IPR Course: TA Lecture 2002/12/18 NTU CSIE R105.
Object Stereo- Joint Stereo Matching and Object Segmentation Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on Michael Bleyer Vienna.
Johann Knechtel, Igor L. Markov and Jens Lienig University of Michigan, EECS Department, Ann Arbor USA Dresden University of Technology, EE Department,
An Interactive Background Blurring Mechanism and Its Applications NTU CSIE 1 互動式背景模糊.
Person detection, tracking and human body analysis in multi-camera scenarios Montse Pardàs (UPC) ACV, Bilkent University, MTA-SZTAKI, Technion-ML, University.
#MOTION ESTIMATION AND OCCLUSION DETECTION #BLURRED VIDEO WITH LAYERS
Motion Deblurring Using Hybrid Imaging Moshe Ben-Ezra and Shree K. Nayar Columbia University IEEE CVPR Conference June 2003, Madison, USA.
Image Restoration Chapter 5.
Image Segmentation in Color Space By Anisa Chaudhary.
Su-ting, Chuang 1. Outline Introduction Related work Hardware configuration Detection system Optimal parameter estimation framework Conclusion 2.
Stas Goferman Lihi Zelnik-Manor Ayellet Tal Technion.
Object Recognition as Ranking Holistic Figure-Ground Hypotheses Fuxin Li and Joao Carreira and Cristian Sminchisescu 1.
An Interactive Background Blurring Mechanism and Its Applications NTU CSIE Yan Chih-Yu Advisor: Wu Ja-Ling, Ph.D. 1.
Removing motion blur from a single image
Improving Image Matting using Comprehensive Sampling Sets CVPR2013 Oral.
Face Detection and Head Tracking Ying Wu Electrical Engineering & Computer Science Northwestern University, Evanston, IL
Su-ting, Chuang 1. Outline Introduction Related work Hardware configuration Finger Detection system Optimal parameter estimation framework Conclusion.
Markov Networks: Theory and Applications Ying Wu Electrical Engineering and Computer Science Northwestern University Evanston, IL 60208
ICCV 2007 Optimization & Learning for Registration of Moving Dynamic Textures Junzhou Huang 1, Xiaolei Huang 2, Dimitris Metaxas 1 Rutgers University 1,
An H.264-based Scheme for 2D to 3D Video Conversion Mahsa T. Pourazad Panos Nasiopoulos Rabab K. Ward IEEE Transactions on Consumer Electronics 2009.
Motion Estimation of Moving Foreground Objects Pierre Ponce ee392j Winter March 10, 2004.
Video object segmentation and its salient motion detection using adaptive background generation Kim, T.K.; Im, J.H.; Paik, J.K.;  Electronics Letters 
Image Deblurring and noise reduction in python
References & Acknowledgements
DIGITAL SIGNAL PROCESSING
IMAGE RESTORATION.
PHOTO – Day 2 depth of field.
Image Deblurring Using Dark Channel Prior
Vehicle Segmentation and Tracking in the Presence of Occlusions
PRAKASH CHOCKALINGAM, NALIN PRADEEP, AND STAN BIRCHFIELD
Vincent DeVito Computer Systems Lab
Reversible data hiding in encrypted images based on absolute mean difference of multiple neighboring pixels Source: Journal of Visual Communication and.
The Image The pixels in the image The mask The resulting image 255 X
CS654: Digital Image Analysis
Deblurring Shaken and Partially Saturated Images
Lecture 7 Patch based methods: nonlocal means, BM3D, K- SVD, data-driven (tight) frame.
Presentation transcript:

Removing Partial Blur in a Single Image Shengyang Dai and Ying Wu EECS Department, Northwestern University, Evanston, IL 60208, USA 2009CVPR

Outline Introduction Generation model of partial blur ◦ The two-layer model for a clear image ◦ Motion blur ◦ Out-of-focus blur ◦ Unified formulation of partial blurs Image recovery from partial degradation ◦ The objective function ◦ Initialization ◦ Recovering (F, B, α) Experiments Conclusion

Introduction Two key issues ◦ Partial blur estimation ◦ Partial deblurring

Generation model of partial blur(1/3) The two-layer model for a clear image ◦ I = F α + B(1 − α) Degraded image is the average over time F α : clear foreground component B(1 − α) : clear background component α : clear soft occlusion mask,α(x) ∈ [0, 1] for each pixel x

Generation model of partial blur(2/3) Motion blur ◦ Case 1:  foreground object is moving  static background, we have = 0, q = δ. ◦ Case 2:  background is moving  static foreground, we have = 0, p = δ. Out-of-focus blur ◦ Case 1:  background layer is in focus  foreground layer is out- of-focus ◦ Case 2:  foreground layer is in focus  background layer is out- of-focus

Generation model of partial blur(3/3) Unified formulation of partial blurs Either the foreground or background layer is not degraded ◦ p or q is the δ function

Image recovery from partial degradation(1/2) The objective function

Image recovery from partial degradation(1/2) Initialization ◦ extract the degraded occlusion mask by using a matting technique ◦ the degradation kernels p and q are estimated by analyzing both and ◦ iterate between F, B and α to obtain the final recovery

Experiments

Conclusion Removing partial blur from a single image input A two-layer image model ◦ foreground and background layers Enables high quality recovery and synthesis for real images