Illumination Estimation via Thin Plate Spline Weihua Xiong ( OmniVision Technology,USA ) Lilong Shi, Brian Funt ( Simon Fraser University, Canada) ( Simon.

Slides:



Advertisements
Similar presentations
Applications of one-class classification
Advertisements

A Robust Super Resolution Method for Images of 3D Scenes Pablo L. Sala Department of Computer Science University of Toronto.
Active Shape Models Suppose we have a statistical shape model –Trained from sets of examples How do we use it to interpret new images? Use an “Active Shape.
Edge Preserving Image Restoration using L1 norm
Medical Image Registration Kumar Rajamani. Registration Spatial transform that maps points from one image to corresponding points in another image.
Copyright © 2006 The McGraw-Hill Companies, Inc. Permission required for reproduction or display. 1 ~ Curve Fitting ~ Least Squares Regression Chapter.

Designing Facial Animation For Speaking Persian Language Hadi Rahimzadeh June 2005.
Light, Surface and Feature in Color Images Lilong Shi Postdoc at Caltech Computational Vision Lab, Simon Fraser University.
1 Chapter 4 Interpolation and Approximation Lagrange Interpolation The basic interpolation problem can be posed in one of two ways: The basic interpolation.
BMVC 2009 Specularity and Shadow Interpolation via Robust Polynomial Texture Maps Mark S. Drew 1, Nasim Hajari 1, Yacov Hel-Or 2 & Tom Malzbender 3 1 School.
x – independent variable (input)
Light Mixture Estimation for Spatially Varying White Balance
Offset of curves. Alina Shaikhet (CS, Technion)
Illumination Estimation via Non- Negative Matrix Factorization By Lilong Shi, Brian Funt, Weihua Xiong, ( Simon Fraser University, Canada) Sung-Su Kim,
Petter Mostad Linear regression Petter Mostad
6/23/2015CIC 10, Color constancy at a pixel [Finlayson et al. CIC8, 2000] Idea: plot log(R/G) vs. log(B/G): 14 daylights 24 patches.
Stereo Computation using Iterative Graph-Cuts
Hazırlayan NEURAL NETWORKS Radial Basis Function Networks I PROF. DR. YUSUF OYSAL.
Linear and generalised linear models
Camera parameters Extrinisic parameters define location and orientation of camera reference frame with respect to world frame Intrinsic parameters define.
Colour Image Compression by Grey to Colour Conversion Mark S. Drew 1, Graham D. Finlayson 2, and Abhilash Jindal 3 1 Simon Fraser University 2 University.
CSCI 347 / CS 4206: Data Mining Module 04: Algorithms Topic 06: Regression.
Radial-Basis Function Networks
Radial Basis Function Networks
Face Recognition Using Neural Networks Presented By: Hadis Mohseni Leila Taghavi Atefeh Mirsafian.
Machine Learning CUNY Graduate Center Lecture 3: Linear Regression.
Machine Learning1 Machine Learning: Summary Greg Grudic CSCI-4830.
Copyright © The McGraw-Hill Companies, Inc. Permission required for reproduction or display. 1 Part 4 Curve Fitting.
Geometric Operations and Morphing.
November 2012 The Role of Bright Pixels in Illumination Estimation Hamid Reza Vaezi Joze Mark S. Drew Graham D. Finlayson Petra Aurora Troncoso Rey School.
Regression analysis Control of built engineering objects, comparing to the plan Surveying observations – position of points Linear regression Regression.
Machine Learning Seminar: Support Vector Regression Presented by: Heng Ji 10/08/03.
1 SUPPORT VECTOR MACHINES İsmail GÜNEŞ. 2 What is SVM? A new generation learning system. A new generation learning system. Based on recent advances in.
Regression Approaches to Voice Quality Control Based on One-to-Many Eigenvoice Conversion Kumi Ohta, Yamato Ohtani, Tomoki Toda, Hiroshi Saruwatari, and.
1 RECENT DEVELOPMENTS IN MULTILAYER PERCEPTRON NEURAL NETWORKS Walter H. Delashmit Lockheed Martin Missiles and Fire Control Dallas, TX 75265
COMPARISON OF IMAGE ANALYSIS FOR THAI HANDWRITTEN CHARACTER RECOGNITION Olarik Surinta, chatklaw Jareanpon Department of Management Information System.
Jeff Howbert Introduction to Machine Learning Winter Regression Linear Regression.
Automatic Minirhizotron Root Image Analysis Using Two-Dimensional Matched Filtering and Local Entropy Thresholding Presented by Guang Zeng.
Feature based deformable registration of neuroimages using interest point and feature selection Leonid Teverovskiy Center for Automated Learning and Discovery.
Computer Vision Lecture #10 Hossam Abdelmunim 1 & Aly A. Farag 2 1 Computer & Systems Engineering Department, Ain Shams University, Cairo, Egypt 2 Electerical.
BCS547 Neural Decoding. Population Code Tuning CurvesPattern of activity (r) Direction (deg) Activity
Project 11: Determining the Intrinsic Dimensionality of a Distribution Okke Formsma, Nicolas Roussis and Per Løwenborg.
Lecture 6: Point Interpolation
Reservoir Uncertainty Assessment Using Machine Learning Techniques Authors: Jincong He Department of Energy Resources Engineering AbstractIntroduction.
Methods for 3D Shape Matching and Retrieval
Learning Photographic Global Tonal Adjustment with a Database of Input / Output Image Pairs.
A Hybrid Strategy For Illuminant Estimation Targeting Hard Images Roshanak Zakizadeh 1 Michael Brown 2 Graham Finlayson 1 1 University of East Anglia 2.
Giansalvo EXIN Cirrincione unit #4 Single-layer networks They directly compute linear discriminant functions using the TS without need of determining.
Global predictors of regression fidelity A single number to characterize the overall quality of the surrogate. Equivalence measures –Coefficient of multiple.
Neural Networks The Elements of Statistical Learning, Chapter 12 Presented by Nick Rizzolo.
Principal Warps: Thin-Plate Splines and the Decomposition of Deformations 김진욱 ( 이동통신망연구실 ; 박천현 (3D 모델링 및 처리연구실 ;
RiskTeam/ Zürich, 6 July 1998 Andreas S. Weigend, Data Mining Group, Information Systems Department, Stern School of Business, NYU 2: 1 Nonlinear Models.
MOTION Model. Road Map Motion Model Non Parametric Motion Field : Algorithms 1.Optical flow field estimation. 2.Block based motion estimation. 3.Pel –recursive.
A 2D/3D correspondence building method for reconstruction of a 3D bone surface model Longwei Fang
Deep Learning Overview Sources: workshop-tutorial-final.pdf
Active Flattening of Curved Document Images via Two Structured Beams
MAN-522 Computer Vision Spring
CS 9633 Machine Learning Support Vector Machines
Chapter 7. Classification and Prediction
Summary of “Efficient Deep Learning for Stereo Matching”
Final Year Project Presentation --- Magic Paint Face
CSE 554 Lecture 10: Extrinsic Deformations
Synthesis of Motion from Simple Animations
COLOR CONSTANCY IN THE COMPRESSED DOMAIN
Machine learning overview
Region-Based Segmentation
Specularity, the Zeta-image, and Information-Theoretic Illuminant
Shape from Shading and Texture
Calibration and homographies
Presentation transcript:

Illumination Estimation via Thin Plate Spline Weihua Xiong ( OmniVision Technology,USA ) Lilong Shi, Brian Funt ( Simon Fraser University, Canada) ( Simon Fraser University, Canada) Sung-Su Kim, Byoung-Ho Kang, Sung-Duk Lee, Sung-Su Kim, Byoung-Ho Kang, Sung-Duk Lee, and Chang-Yeong Kim and Chang-Yeong Kim (Samsung Advanced Institute of Technology, Korea) (Samsung Advanced Institute of Technology, Korea)

Automatic White Balancing Image Estimate the Illumination Original Surface Color

Illumination Estimation Methods Non-statistical SolutionNon-statistical Solution –Gray World (1980 Buchsbaum) –Max-RGB –Shades of Gray (2004 Finlayson) –Gray-Edge Hypothesis (Weijei & Gevers 2005) Statistics Based SolutionStatistics Based Solution –Color by Correlation (Finlayson at. el. 2001) –Neural Network (Funt. 2002) –Support Vector Regression (Xiong, 2004) –KL-Divergence (Rosenberg 2001)

Limitations of previous statistical solutions Color by Correlation Illuminations pre-fixed Neural Network Local Minima Support Vector Regression Many parameters to be determined by user

Thin Plate Spline (TPS) Interpolation Thin Plate Spline (TPS) interpolates between control pointsThin Plate Spline (TPS) interpolates between control points –Minimizes the bending energy function of a thin metal plate. –Originally designed for deformable matching between images AdvantageAdvantage –Output is always unique –Fits to all the training data smoothly –No extrapolation –Solution can never be singular Has been extended into 3D for mapping from RGB to XYZ (CIC 2005)Has been extended into 3D for mapping from RGB to XYZ (CIC 2005) Source Image Target Image

Thumbnail Input The method uses thumbnails as inputThe method uses thumbnails as input –8-by-8 input RGB images –Each of the 64 pixels is the average of pixels from original input image Original Image Change into chromaticity space [R/(R+G+B) G/(R+G+B)] So we extend TPS to 128 Dimensions here Thumbnail Image

TPS for AWB: Intuition Basic ideaBasic idea –Similar images require similar white balancing –Illumination rg-chromaticity interpolated Training set contains images and their respective white points (illumination color)Training set contains images and their respective white points (illumination color) For input imageFor input image –Interpolate white point based on the distance between the input and training images

Training set consists of N images Corresponding illumination chromaticity values (for case of 8x8x2=128 input image) {(I i,1,I i,2,…I i,128), (r i,g i )}. (i/o pair) TPS determines parameters w i and (a 0, a 1, a 2, …, a 128 ) Controls two non-rigid mapping functions f r, f g, such that (r i,g i ) = (f r (I i,1,I i,2,…I i,128 ), f g (I i,1,I i,2,…I i,128 )). TPS is defined by a non-linear function with an additional linear term. Without loss of generality, consider only f r definition in which w i and a i are coefficients to be determined: TPS Details

Weighted distance to every image in the training set X is either r or g chromaticity TPS Details (Continued) Linear Term Nonlinear Term

TPS Details (Continued) Smoothness constraint where is the total bending energy described in terms of the curvature of the energy is minimized when

Direct Solution (once per training set) N unknowns and N equations Define L: U ij = U(||(I i1,I i2,…I i128 )- (I j1,I j2,…I j128 )||, U(r) = r 2 *logr Additionally define W= (w 1, w 2,…, w N, a 0, a 1, a 2, …, a 128 ) T, and K = (r 1, r 2, r 3 … r N,0,0,0,….0) T. We have K =LW and solution W = L -1 K 0 is ZERO matrix with size of 129x129

Original Training Data Pairs Graphical Example of TPS Interpolation Nonlinear Term Linear Term Error

TPS Result Input Image (Bluish) TPS Output Ground Truth Image

TPS on Large Image Database Average of bright part on the grayball is assumed to the true illumination value

Performance Comparison Method Angular Distance (x10 2 ) MaxRMSMaxRMS SVR (3D) TPS SOG Gray World Max RGB The database is divided into two non-overlapped subsets Test set size Training data set size 3581

Algorithm Comparison Using Wilcoxon MethodTPSSVR(3D)SoGMAXGW TPS=+++ SVR(3D)=+++ SoG---- MAX---- GW---+ TPS is equal to SVR, but better than GW, SoG, and Max

Conclusion Thin Plate Interpolation is applied in illumination estimationThin Plate Interpolation is applied in illumination estimation Performs non-uniform interpolationPerforms non-uniform interpolation –Assumption that similar images require similar color correction Method is parameter independentMethod is parameter independent Both training and testing are fastBoth training and testing are fast The performance on natural images shows the accuracy of TPS illumination estimation to be goodThe performance on natural images shows the accuracy of TPS illumination estimation to be good

Funded by Samsung Advanced Technology Institute

Thanks & Questions