Y. Moses 11 Combining Photometric and Geometric Constraints Yael Moses IDC, Herzliya Joint work with Ilan Shimshoni and Michael Lindenbaum, the Technion.

Slides:



Advertisements
Similar presentations
1 Photometric Stereo Reconstruction Dr. Maria E. Angelopoulou.
Advertisements

3D reconstruction.
Announcements Project 2 due today Project 3 out today –demo session at the end of class.
Lecture 35: Photometric stereo CS4670 / 5670 : Computer Vision Noah Snavely.
3D Modeling from a photograph
Machine Vision Laboratory The University of the West of England Bristol, UK 2 nd September 2010 ICEBT Photometric Stereo in 3D Biometrics Gary A. Atkinson.
Stereo Vision Reading: Chapter 11
Shape-from-X Class 11 Some slides from Shree Nayar. others.
Camera calibration and epipolar geometry
Lecture 23: Photometric Stereo CS4670/5760: Computer Vision Kavita Bala Scott Wehrwein.
Last Time Pinhole camera model, projection
Epipolar geometry. (i)Correspondence geometry: Given an image point x in the first view, how does this constrain the position of the corresponding point.
Visibility Subspaces: Uncalibrated Photometric Stereo with Shadows Kalyan Sunkavalli, Harvard University Joint work with Todd Zickler and Hanspeter Pfister.
Multiple-view Reconstruction from Points and Lines
Multiple View Geometry Marc Pollefeys University of North Carolina at Chapel Hill Modified by Philippos Mordohai.
The plan for today Camera matrix
Lecture 32: Photometric stereo, Part 2 CS4670: Computer Vision Noah Snavely.
Previously Two view geometry: epipolar geometry Stereo vision: 3D reconstruction epipolar lines Baseline O O’ epipolar plane.
May 2004Stereo1 Introduction to Computer Vision CS / ECE 181B Tuesday, May 11, 2004  Multiple view geometry and stereo  Handout #6 available (check with.
CSE473/573 – Stereo Correspondence
Photometric Stereo Merle Norman Cosmetics, Los Angeles Readings R. Woodham, Photometric Method for Determining Surface Orientation from Multiple Images.
Photometric Stereo & Shape from Shading
Structure Computation. How to compute the position of a point in 3- space given its image in two views and the camera matrices of those two views Use.
Lecture 11 Stereo Reconstruction I Lecture 11 Stereo Reconstruction I Mata kuliah: T Computer Vision Tahun: 2010.
Structure from images. Calibration Review: Pinhole Camera.
Final Exam Review CS485/685 Computer Vision Prof. Bebis.
1/20 Obtaining Shape from Scanning Electron Microscope Using Hopfield Neural Network Yuji Iwahori 1, Haruki Kawanaka 1, Shinji Fukui 2 and Kenji Funahashi.
Lecture 12 Stereo Reconstruction II Lecture 12 Stereo Reconstruction II Mata kuliah: T Computer Vision Tahun: 2010.
Computer Vision - A Modern Approach Set: Sources, shadows and shading Slides by D.A. Forsyth Sources and shading How bright (or what colour) are objects?
Analysis of Lighting Effects Outline: The problem Lighting models Shape from shading Photometric stereo Harmonic analysis of lighting.
Shape from Shading and Texture. Lambertian Reflectance Model Diffuse surfaces appear equally bright from all directionsDiffuse surfaces appear equally.
Stereo Vision Reading: Chapter 11 Stereo matching computes depth from two or more images Subproblems: –Calibrating camera positions. –Finding all corresponding.
3D Sensing and Reconstruction Readings: Ch 12: , Ch 13: , Perspective Geometry Camera Model Stereo Triangulation 3D Reconstruction by.
CS654: Digital Image Analysis Lecture 8: Stereo Imaging.
Sources, Shadows, and Shading
Robot Vision SS 2007 Matthias Rüther 1 ROBOT VISION Lesson 6a: Shape from Stereo, short summary Matthias Rüther Slides partial courtesy of Marc Pollefeys.
Lec 22: Stereo CS4670 / 5670: Computer Vision Kavita Bala.
Course 10 Shading. 1. Basic Concepts: Light Source: Radiance: the light energy radiated from a unit area of light source (or surface) in a unit solid.
Single-view geometry Odilon Redon, Cyclops, 1914.
CSE 185 Introduction to Computer Vision Stereo. Taken at the same time or sequential in time stereo vision structure from motion optical flow Multiple.
Raquel A. Romano 1 Scientific Computing Seminar May 12, 2004 Projective Geometry for Computer Vision Projective Geometry for Computer Vision Raquel A.
Shape from Shading Course web page: vision.cis.udel.edu/cv February 26, 2003  Lecture 6.
Multiple Light Source Optical Flow Multiple Light Source Optical Flow Robert J. Woodham ICCV’90.
Announcements Final Exam Friday, May 16 th 8am Review Session here, Thursday 11am.
55:148 Digital Image Processing Chapter 11 3D Vision, Geometry Topics: Basics of projective geometry Points and hyperplanes in projective space Homography.
Large-Scale Matrix Factorization with Missing Data under Additional Constraints Kaushik Mitra University of Maryland, College Park, MD Sameer Sheoreyy.
Lecture 9 Feature Extraction and Motion Estimation Slides by: Michael Black Clark F. Olson Jean Ponce.
1Ellen L. Walker 3D Vision Why? The world is 3D Not all useful information is readily available in 2D Why so hard? “Inverse problem”: one image = many.
3D Reconstruction Using Image Sequence
Reflectance Function Estimation and Shape Recovery from Image Sequence of a Rotating object Jiping Lu, Jim Little UBC Computer Science ICCV ’ 95.
Tal Amir Advanced Topics in Computer Vision May 29 th, 2015 COUPLED MOTION- LIGHTING ANALYSIS.
Geometry Reconstruction March 22, Fundamental Matrix An important problem: Determine the epipolar geometry. That is, the correspondence between.
EECS 274 Computer Vision Sources, Shadows, and Shading.
Announcements Project 3a due today Project 3b due next Friday.
1 Resolving the Generalized Bas-Relief Ambiguity by Entropy Minimization Neil G. Alldrin Satya P. Mallick David J. Kriegman University of California, San.
MAN-522 Computer Vision Spring
CS4670 / 5670: Computer Vision Kavita Bala Lec 27: Stereo.
Merle Norman Cosmetics, Los Angeles
Epipolar geometry.
3D Photography: Epipolar geometry
Structure from motion Input: Output: (Tomasi and Kanade)
Announcements Project 3b due Friday.
Reconstruction.
Depthmap Reconstruction Based on Monocular cues
Announcements Today: evals Monday: project presentations (8 min talks)
Lecture 28: Photometric Stereo
Announcements Project 3 out today demo session at the end of class.
Chapter 11: Stereopsis Stereopsis: Fusing the pictures taken by two cameras and exploiting the difference (or disparity) between them to obtain the depth.
Shape from Shading and Texture
Structure from motion Input: Output: (Tomasi and Kanade)
Presentation transcript:

Y. Moses 11 Combining Photometric and Geometric Constraints Yael Moses IDC, Herzliya Joint work with Ilan Shimshoni and Michael Lindenbaum, the Technion

Y. Moses 22 Recover the 3D shape of a general smooth surface from a set of calibrated images Problem 1:

Y. Moses 33 Problem 2: Recover the 3D shape of a smooth bilaterally symmetric object from a single image.

Y. Moses 44 Shape Recovery  Geometry: Stereo  Photometry:  Shape from shading  Photometric stereo Main problems: Calibrations and Correspondence

Y. Moses 55 3D Shape Recovery Photometry:  Shape from shading  Photometric stereo Geometry:  Stereo  Structure from motion

Y. Moses 66 Geometric Stereo  2 different images  Known camera parameters  Known correspondence + +

Y. Moses 77 Photometric Stereo  3D shape recovery: surface normals from two or more images taken from the same viewpoint

Y. Moses 88 Photometric Stereo Solution: Three images Matrix notation

Y. Moses 99 Photometric Stereo  3D shape recovery (surface normals) Two or more images taken from the same viewpoint Main Limitation: Correspondence is obtained by a fixed viewpoint

Y. Moses  10 Overview  Combining photometric and geometric stereo:  Symmetric surface, single image  Non symmetric: 3 images  Mono-Geometric stereo  Mono-Photometric stereo  Experimental results.

Y. Moses  11 The input  Smooth featureless surface  Taken under different viewpoints  Illuminated by different light sources The Problem: Recover the 3D shape from a set of calibrated images

Y. Moses  12 Assumptions  Given correspondence the normals can be computed (e.g., Lambertian, distant point light source …) * *  n n  Three or more images  Perspective projection

Y. Moses  13 Our method Combines photometric and geometric stereo We make use of:  Given Correspondence:  Can compute a normal  Can compute the 3D point

Y. Moses  14 Basic Method Given Correspondence

Y. Moses  15 First Order Surface Approximation

Y. Moses  16 First Order Surface Approximation

Y. Moses  17 First Order Surface Approximation P(  ) = (1 -  )O 1 +  P , N (P(  ) - P) = 0

Y. Moses  18 First Order Surface Approximation

Y. Moses  19 New Correspondence

Y. Moses  20 New Surface Approximation

Y. Moses  21 Dense Correspondence

Y. Moses  22 Basic Propagation

Y. Moses  23 Basic Propagation

Y. Moses  24 Basic method: First Order  Given correspondence p i and L  P and n  Given P and n  T  Given P, T and M i  a new correspondence q i

Y. Moses  25 Extensions  Using more than three images  Propagation:  Using multi-neighbours  Smart propagation  Second error approximation  Error correction:  Based on local continuity  Other assumptions on the surface

Y. Moses  26 Multi-neighbors Propagation

Y. Moses  27 Smart Propagation

Y. Moses  28 Second Order: a Sphere P()P() N+N  N NN P (P-P(  ))(N+N  )=0

Y. Moses  29 Second Order Approximation

Y. Moses  30 Second Order Approximation

Y. Moses  31 Using more than three images  Reduce noise of the photometric stereo  Avoid shadowed pixels  Detect “bad pixels”  Noise  Shadows  Violation of assumptions on the surface

Y. Moses  32 Smart Propagation

Y. Moses  33 Error correction The compatibility of the local 3D shape can be used to correct errors of:  Correspondence  Camera parameters  Illumination parameters

Y. Moses  34 Score  Continuity:  Shape  Normals  Albedo  The consistency of 3D points locations and the computed normals:  General case: full triangulation  Local constraints

Y. Moses  35 Extensions  Using more than three images  Propagation:  Using multi-neighbours  Smart propagation  Second error approximation  Error correction:  Based on local continuity  Other assumptions on the surface

Y. Moses  36 Real Images  Camera calibration  Light calibration  Direction  Intensity  Ambient

Y. Moses  37 Error correction + multi-neighbor 5 Images

Y. Moses  38 5pp 3pp 3nn 5nn 5pn

Y. Moses  39

Y. Moses  40

Y. Moses  41

Y. Moses  42

Y. Moses  43

Y. Moses  44 Detected Correspondence

Y. Moses  45 Error correction + multi-neighbord Multi-neighbors Basic scheme (3 images) Error correction no multi-neighbors

Y. Moses  46 New Images Synthetic Images

Y. Moses  47 Sec a Ground truth Basic scheme Multi-neighbors Error correction

Y. Moses  48 Sec b Ground truth Basic scheme Multi-neighbors Error correction

Y. Moses  49 Sec c Ground truth Basic scheme Multi-neighbors Error correction

Y. Moses  50 Ground truth Basic scheme Multi-neighbors approx. Error correction Sec d Ground truth Basic scheme Multi-neighbors Error correction

Y. Moses  51 Combining Photometry and Geometry Yields a dense correspondence and dense shape recovery of the object in a single path

Y. Moses  52 Assumptions  Bilaterally Symmetric object  Lambertian surface with constant albedo  Orthographic projection  Neither occlusions nor shadows  Known “epipolar geometry”

Y. Moses  53 Geometric Stereo  2 different images  Known camera parameters  Known viewpoints  Known correspondence 3D shape recovery

Y. Moses  54 Computing the Depth from Disparity plpl prpr P qlql qrqr Z Z Orthographic Projection

Y. Moses  55 Symmetry and Geometric Stereo Non frontal view of a symmetric object Two different images of the same object

Y. Moses  56 Symmetry and Geometric Stereo Non frontal view of a symmetric object Two different images of the same object

Y. Moses  57 Geometry  Weak perspective projection: Around X Around Z Around Y

Y. Moses  58 Geometry  Projection of R y : Around Y  is the only pose parameter Image point Object point

Y. Moses  59 object x z image Correspondence Assume YxZ is the symmetry plane.

Y. Moses  60 Mono-Geometric Stereo  3D reconstruction: given correspondence and , unknown known z image x object

Y. Moses  61 Viewpoint Invariant  Given the correspondence and unknown  Invariant

Y. Moses  62 Photometric Stereo  2 images  Lambertian reflectance  Known illuminations  Known correspondence (same viewpoint) 3D shape recovery

Y. Moses  63 Symmetry and Photometric Stereo Non-frontal illumination of a symmetric object Two different images of the same object

Y. Moses  64 Notation: Photometry  Corresponding object points:  Illumination:

Y. Moses  65 Mono-Photometric Stereo  3D reconstruction given correspondence and E (up to a twofold ambiguity): unknown known

Y. Moses  66 Invariance to Illumination  Given correspondence and E unknown  Invariant:

Y. Moses  67 Mono-Photometric Stereo  3D reconstruction E unknown but correspondence is given  Frontal viewpoint with non-frontal illumination.  Use image first derivatives.

Y. Moses  68 Mono-Photometric Stereo Using image derivatives  3 global unknowns: E  For each pair:  5 unknowns z x z y z xx z xy z yy  6 equations  3 pairs are sufficient

Y. Moses  69 Mono-Photometric Stereo Unknown Illumination

Y. Moses  70 Correspondence  No correspondence => no stereo.  Hard to define correspondence in images of smooth surfaces.  Almost any correspondence is legal when:  Only geometric constraints are considered.  Only photometric constraints are considered.

Y. Moses  71 Combining Photometry and Geometry  Yields a dense correspondence (dense shape recovery of the object).  Enables recovering of the global parameters.

Y. Moses  72 Self-Correspondence  A self-correspondence function:

Y. Moses  73 Dense Correspondence using Propagation Assume correspondence between a pair of points, p 0 l and p 0 r.

Y. Moses  74 Dense Correspondence using Propagation

Y. Moses  75 x z image object

Y. Moses  76 First derivatives of the Correspondence  Assume known   Assume known E

Y. Moses  77 Computing and  Object coordinates: Given computing and is trivial  Moving from object to image coordinates depends on the viewing parameter 

Y. Moses  78  Derivatives with respect to the object coordinates:  Derivatives with respect to the image coordinates:

Y. Moses  79 x z image object E

Y. Moses  80  Given a corresponding pair and E  n=(z x,z y,-1) T  Given  and n  c x and c y  Given c x and c y  a new corresponding pair General Idea    

Y. Moses  81 Results on Real Images: Given global parameters

Y. Moses  82 Finding Global Parameters  Assume E and  are unknown.  Assume a pair of corresponding points is given.  Two possibilities:  Search for E and  directly.  Compute E and  from the image second derivatives.

Y. Moses  83  All roads lead to Rome …  Find and verify correct correspondence  Recover global parameters, E and  Integration Constraint: Circular Tour

Y. Moses  84 Finding Global Parameters Consider image second derivatives  Due to foreshortening effect: and  We can relate image and object derivatives by

Y. Moses  85 For each corresponding pair: and Plus 4 linear equations in 3 unknown. Where Testing E and  : Image second derivatives

Y. Moses  86 Counting  5 unknowns for each pair: z x z y,z xx z xy z yy  4 global unknowns: E,   For each pair: 6 equations.  For n pairs: 5n+4 unknowns 6n equations. 4 pairs are sufficient

Y. Moses  87 Results on Simulated Data Ground Truth Recovered Shape

Y. Moses  88 Recovering the Global Parameters

Y. Moses  89 Degenerate Case  Close to frontal view: problems with geometric-stereo. reconstruction problem  Close to frontal illumination: problems with photometric-stereo. correspondence problem

Y. Moses  90 Future work  Perspective photometric stereo  Use as a first approximation to global optimization methods  Test on other reflection models  Recovering of the global parameters:  Light  Cameras  Detect the first pair of correspondence

Y. Moses  91 Future Work  Extend to general 3 images under 3 viewpoints and 3 illuminations.  Extend to non-lambertian surfaces.

Y. Moses  92 Thanks

Y. Moses  93 x z image object

Y. Moses  94 Integration Constraint

Y. Moses  95 Integration Constraint

Y. Moses  96 Searching for E  Illumination must satisfy:   E is further constrained by the image second derivatives.

Y. Moses  97 Image second derivatives: Where 4 linear equations in 3 unknown

Y. Moses  98 For each corresponding pair and E: 4 linear equations in 3 unknown. Where Image second derivatives

Y. Moses  99 Counting  5 unknowns for each pair: z x,z y,z xx,z xy,z yy  3 global unknowns: E  For each pair: 6 equations.  For n pairs: 5n+3 unknowns 6n equations. 3 pairs are sufficient

Y. Moses  100 Correspondence

Y. Moses  101 Variations  Known/unknown distant light source  Known/unknown viewpoint  Symmetric/non-symmetric image  Frontal/non-frontal viewpoint  Frontal/non-frontal illumination

Y. Moses  102 Correspondence  Epipolar geometry is the only geometric constraint on the correspondence.  Weak photometric constraint on the correspondence.

Y. Moses  103 Lambertian Surface 5 Basic radiometric I =I = E * * P E E  n2n2  n1n1 

Y. Moses  104 E Photometric Stereo  First proposed by Woodham,  Assume that we have two images..