High-resolution Hyperspectral Imaging via Matrix Factorization Rei Kawakami 1 John Wright 2 Yu-Wing Tai 3 Yasuyuki Matsushita 2 Moshe Ben-Ezra 2 Katsushi.

Slides:



Advertisements
Similar presentations
Color Imaging Analysis of Spatio-chromatic Decorrelation for Colour Image Reconstruction Mark S. Drew and Steven Bergner
Advertisements

For Internal Use Only. © CT T IN EM. All rights reserved. 3D Reconstruction Using Aerial Images A Dense Structure from Motion pipeline Ramakrishna Vedantam.
Recognizing Surfaces using Three-Dimensional Textons Thomas Leung and Jitendra Malik Computer Science Division University of California at Berkeley.
A Graphical Operator Framework for Signature Detection in Hyperspectral Imagery David Messinger, Ph.D. Digital Imaging and Remote Sensing Laboratory Chester.
CS-MUVI Video compressive sensing for spatial multiplexing cameras Aswin Sankaranarayanan, Christoph Studer, Richard G. Baraniuk Rice University.
Image classification in natural scenes: Are a few selective spectral channels sufficient?
Hilal Tayara ADVANCED INTELLIGENT ROBOTICS 1 Depth Camera Based Indoor Mobile Robot Localization and Navigation.
Multi-Task Compressive Sensing with Dirichlet Process Priors Yuting Qi 1, Dehong Liu 1, David Dunson 2, and Lawrence Carin 1 1 Department of Electrical.
Patch-based Image Deconvolution via Joint Modeling of Sparse Priors Chao Jia and Brian L. Evans The University of Texas at Austin 12 Sep
VISUALIZATION OF HYPERSPECTRAL IMAGES ROBERTO BONCE & MINDY SCHOCKLING iMagine REU Montclair State University.
Robust Object Tracking via Sparsity-based Collaborative Model
Stereo.
Image classification by sparse coding.
Image Super-Resolution Using Sparse Representation By: Michael Elad Single Image Super-Resolution Using Sparse Representation Michael Elad The Computer.
Manifold Bootstrapping for SVBRDF Capture
Image Denoising via Learned Dictionaries and Sparse Representations
Illumination Estimation via Non- Negative Matrix Factorization By Lilong Shi, Brian Funt, Weihua Xiong, ( Simon Fraser University, Canada) Sung-Su Kim,
Multi-view stereo Many slides adapted from S. Seitz.
Motion Detail Preserving Optical Flow Estimation Li Xu 1, Jiaya Jia 1, Yasuyuki Matsushita 2 1 The Chinese University of Hong Kong 2 Microsoft Research.
VISUALIZATION OF HYPERSPECTRAL IMAGES ROBERTO BONCE & MINDY SCHOCKLING iMagine REU Montclair State University.
A Theory of Locally Low Dimensional Light Transport Dhruv Mahajan (Columbia University) Ira Kemelmacher-Shlizerman (Weizmann Institute) Ravi Ramamoorthi.
Matthew Brown University of British Columbia (prev.) Microsoft Research [ Collaborators: † Simon Winder, *Gang Hua, † Rick Szeliski † =MS Research, *=MS.
Seminar presented by: Tomer Faktor Advanced Topics in Computer Vision (048921) 12/01/2012 SINGLE IMAGE SUPER RESOLUTION.
Person-Specific Domain Adaptation with Applications to Heterogeneous Face Recognition (HFR) Presenter: Yao-Hung Tsai Dept. of Electrical Engineering, NTU.
Simple Calibration of Non-overlapping Cameras with a Mirror
Tracking by Sampling Trackers Junseok Kwon* and Kyoung Mu lee Computer Vision Lab. Dept. of EECS Seoul National University, Korea Homepage:
ARSF Data Processing Consequences of the Airborne Processing Library Mark Warren Plymouth Marine Laboratory, Plymouth, UK RSPSoc 2012 – Greenwich, London.
Recovering low rank and sparse matrices from compressive measurements Aswin C Sankaranarayanan Rice University Richard G. Baraniuk Andrew E. Waters.
Sparse Matrix Factorizations for Hyperspectral Unmixing John Wright Visual Computing Group Microsoft Research Asia Sept. 30, 2010 TexPoint fonts used in.
What Does Motion Reveal About Transparency ? Moshe Ben-Ezra and Shree K. Nayar Columbia University ICCV Conference October 2003, Nice, France This work.
Yu-Wing Tai, Hao Du, Michael S. Brown, Stephen Lin CVPR’08 (Longer Version in Revision at IEEE Trans PAMI) Google Search: Video Deblurring Spatially Varying.
HighlY Constrained Back PRojection (HYPR) Thank you to Oliver Wieben!!
Motion Deblurring Using Hybrid Imaging Moshe Ben-Ezra and Shree K. Nayar Columbia University IEEE CVPR Conference June 2003, Madison, USA.
Mitsubishi Electric Research Labs (MERL) Super-Res from Single Motion Blur PhotoAgrawal & Raskar Amit Agrawal and Ramesh Raskar Mitsubishi Electric Research.
The Quotient Image: Class-based Recognition and Synthesis Under Varying Illumination T. Riklin-Raviv and A. Shashua Institute of Computer Science Hebrew.
High-resolution Hyperspectral Imaging via Matrix Factorization
Computer Vision Stereo Vision. Bahadir K. Gunturk2 Pinhole Camera.
Optimal Component Analysis Optimal Linear Representations of Images for Object Recognition X. Liu, A. Srivastava, and Kyle Gallivan, “Optimal linear representations.
Paper presentation topics 2. More on feature detection and descriptors 3. Shape and Matching 4. Indexing and Retrieval 5. More on 3D reconstruction 1.
Polarization-based Shape Estimation of Transparent Objects by Using Raytracing and PLZT Camera Daisuke MiyazakiThe University of Tokyo Noriyuki TakashimaFuruuchi.
SuperResolution (SR): “Classical” SR (model-based) Linear interpolation (with post-processing) Edge-directed interpolation (simple idea) Example-based.
Convolutional Restricted Boltzmann Machines for Feature Learning Mohammad Norouzi Advisor: Dr. Greg Mori Simon Fraser University 27 Nov
Comparative Analysis of Spectral Unmixing Algorithms Lidan Miao Nov. 10, 2005.
Automatic 3D modelling of Architecture Anthony Dick 1 Phil Torr 2 Roberto Cipolla 1 1 Department of Engineering 2 Microsoft Research, University of Cambridge.
Jianchao Yang, John Wright, Thomas Huang, Yi Ma CVPR 2008 Image Super-Resolution as Sparse Representation of Raw Image Patches.
Che-An Wu Background substitution. Background Substitution AlphaMa p Trimap Depth Map Extract the foreground object and put into another background Objective.
Energy minimization Another global approach to improve quality of correspondences Assumption: disparities vary (mostly) smoothly Minimize energy function:
Sparse nonnegative matrix factorization for protein sequence motifs information discovery Presented by Wooyoung Kim Computer Science, Georgia State University.
Date of download: 6/20/2016 Copyright © 2016 SPIE. All rights reserved. Scheme depicting our high resolution hyperspectral camera principle of operation.
J. Appl. Remote Sens. 2014;8(1): doi: /1.JRS Figure Legend:
1 C.A.L. Bailer-Jones. Machine Learning. Data exploration and dimensionality reduction Machine learning, pattern recognition and statistical data modelling.
Jean Baptiste Joseph Fourier
Sparsity Based Poisson Denoising and Inpainting
Intrinsic images and shape refinement
Progress Report: Week 6 Alvaro Velasquez.
Motion Segmentation with Missing Data using PowerFactorization & GPCA
Hyperspectral Wind Retrievals Dave Santek Chris Velden CIMSS Madison, Wisconsin 5th Workshop on Hyperspectral Science 8 June 2005.
Single Image Haze Removal Using Dark Channel Prior
Rob Fergus Computer Vision
Towards Understanding the Invertibility of Convolutional Neural Networks Anna C. Gilbert1, Yi Zhang1, Kibok Lee1, Yuting Zhang1, Honglak Lee1,2 1University.
A Bayesian Estimation of Building Shape using MCMC
Domingo Mery Department of Computer Science
Daisuke Miyazaki Katsushi Ikeuchi The University of Tokyo
Daisuke Miyazaki Katsushi Ikeuchi The University of Tokyo
Nearly Analytical Pose Estimation
INFONET Seminar Application Group
FOCUS PRIOR ESTIMATION FOR SALIENT OBJECT DETECTION
Filtering Removing components from an image is know as “image filtering”. If we remove the high frequency components, we tend to remove the noise. This.
Progress Report Alvaro Velasquez.
Real-time Global Illumination with precomputed probe
Presentation transcript:

High-resolution Hyperspectral Imaging via Matrix Factorization Rei Kawakami 1 John Wright 2 Yu-Wing Tai 3 Yasuyuki Matsushita 2 Moshe Ben-Ezra 2 Katsushi Ikeuchi 3 1 University of Tokyo, 2 Microsoft Research Asia (MSRA), 3 Korea Advanced Institute of Science and Technology (KAIST) CVPR 11

Giga-pixel Camera M. Ezra et al. Giga-pixel Microsoft research Large-format lensCCD

Spectrum

RGB vs. Spectrum

Approach Low-res hyperspectral high-res RGB High-res hyperspectral image Combine

Problem formulation W (Image width) H (Image height) S Goal: Given:

Representation: Basis function W (Image width) H (Image height) S = … … 0 = + x 0x 1.0x 0 ++

Two-step approach 1.Estimate basis functions from hyperspectral image 2.For each pixel in high-res RGB image, estimate coefficients for the basis functions

1: Limited number of materials Sparse vector For all pixel (i,j) Sparse matrix W (Image width) H (Image height) S = … … 0.6

2: Sparsity in high-res image W H S Sparse coefficients Reconstruction

Simulation experiments

460 nm550 nm620 nm 460 nm550 nm620 nm

430 nm490 nm550 nm610 nm670 nm

Error images of Global PCA with back- projection Error images of local window with back-projection Error images of RGB clustering with back-projection

Estimated 430 nm

Ground truth

RGB image

Error image

HS camera Filter CMOSLens Aperture Focus Translational stage

Real data experiment Input RGBInput (550nm)Input (620nm)Estimated (550nm)Estimated (620nm)

Summary Method to reconstruct high-resolution hyperspectral image from ▫Low-res hyperspectral camera ▫High-res RGB camera Spatial sparsity of hyperspectral input ▫Search for a factorization of the input into  basis functions  set of maximally sparse coefficients