Project 1 grades out Announcements. Multiview stereo Readings S. M. Seitz and C. R. Dyer, Photorealistic Scene Reconstruction by Voxel Coloring, International.

Slides:



Advertisements
Similar presentations
Multi-view Stereo via Volumetric Graph-cuts George Vogiatzis, Philip H. S. Torr Roberto Cipolla.
Advertisements

Multi-view Stereo via Volumetric Graph-cuts
The fundamental matrix F
Stereo matching Class 7 Read Chapter 7 of tutorial Tsukuba dataset.
Multiview Reconstruction. Why More Than 2 Views? BaselineBaseline – Too short – low accuracy – Too long – matching becomes hard.
Some books on linear algebra Linear Algebra, Serge Lang, 2004 Finite Dimensional Vector Spaces, Paul R. Halmos, 1947 Matrix Computation, Gene H. Golub,
Stereo Many slides adapted from Steve Seitz. Binocular stereo Given a calibrated binocular stereo pair, fuse it to produce a depth image Where does the.
MultiView Stereo Steve Seitz CSE590SS: Vision for Graphics.
Multiview Reconstruction. Why More Than 2 Views? BaselineBaseline – Too short – low accuracy – Too long – matching becomes hard.
Silhouettes in Multiview Stereo Ian Simon. Multiview Stereo Problem Input: – a collection of images of a rigid object (or scene) – camera parameters for.
Last Time Pinhole camera model, projection
Project 3 extension: Wednesday at noon Final project proposal extension: Friday at noon >consult with Steve, Rick, and/or Ian now! Project 2 artifact winners...
Lecture 12: Structure from motion CS6670: Computer Vision Noah Snavely.
Computer Vision CSE576, Spring 2005 Richard Szeliski
Lecture 23: Structure from motion and multi-view stereo
Computational Photography: Image-based Modeling Jinxiang Chai.
CSCE 641 Computer Graphics: Image-based Modeling Jinxiang Chai.
Project 2 winners Think about Project 3 Guest lecture on Monday: Aseem Announcements.
1 Image-Based Visual Hulls Paper by Wojciech Matusik, Chris Buehler, Ramesh Raskar, Steven J. Gortler and Leonard McMillan [
Image-Based Visual Hulls Wojciech Matusik Chris Buehler Leonard McMillan Wojciech Matusik Chris Buehler Leonard McMillan Massachusetts Institute of Technology.
Multiview stereo. Volumetric stereo Scene Volume V Input Images (Calibrated) Goal: Determine occupancy, “color” of points in V.
Multi-view stereo Many slides adapted from S. Seitz.
The plan for today Camera matrix
Multiview Reconstruction. Why More Than 2 Views? BaselineBaseline – Too short – low accuracy – Too long – matching becomes hard.
Announcements Project Update Extension: due Friday, April 20 Create web page with description, results Present your project in class (~10min/each) on Friday,
Announcements PS3 Due Thursday PS4 Available today, due 4/17. Quiz 2 4/24.
From Images to Voxels Steve Seitz Carnegie Mellon University University of Washington SIGGRAPH 2000 Course on 3D Photography.
Lecture 25: Multi-view stereo, continued
Multiple View Geometry : Computational Photography Alexei Efros, CMU, Fall 2006 © Martin Quinn …with a lot of slides stolen from Steve Seitz and.
Accurate, Dense and Robust Multi-View Stereopsis Yasutaka Furukawa and Jean Ponce Presented by Rahul Garg and Ryan Kaminsky.
Review: Binocular stereo If necessary, rectify the two stereo images to transform epipolar lines into scanlines For each pixel x in the first image Find.
3-D Scene u u’u’ Study the mathematical relations between corresponding image points. “Corresponding” means originated from the same 3D point. Objective.
CSCE 641 Computer Graphics: Image-based Modeling Jinxiang Chai.
Image-Based Visual Hulls Wojciech Matusik Chris Buehler Ramesh Raskar Steven Gortler Leonard McMillan Presentation by: Kenton McHenry.
Computer Vision Spring ,-685 Instructor: S. Narasimhan WH 5409 T-R 10:30am – 11:50am Lecture #15.
Camera Calibration & Stereo Reconstruction Jinxiang Chai.
Reconstructing Relief Surfaces George Vogiatzis, Philip Torr, Steven Seitz and Roberto Cipolla BMVC 2004.
Finish Adaptive Space Carving Anselmo A. Montenegro †, Marcelo Gattass ‡, Paulo Carvalho † and Luiz Velho † †
Lecture 11 Stereo Reconstruction I Lecture 11 Stereo Reconstruction I Mata kuliah: T Computer Vision Tahun: 2010.
Some books on linear algebra Linear Algebra, Serge Lang, 2004 Finite Dimensional Vector Spaces, Paul R. Halmos, 1947 Matrix Computation, Gene H. Golub,
Structure from images. Calibration Review: Pinhole Camera.
3D Surface Reconstruction from 2D Images (Survey)
Graph Cut Algorithms for Binocular Stereo with Occlusions
Image-based rendering Michael F. Cohen Microsoft Research.
Stereo Many slides adapted from Steve Seitz.
A General-Purpose Platform for 3-D Reconstruction from Sequence of Images Ahmed Eid, Sherif Rashad, and Aly Farag Computer Vision and Image Processing.
Stereo Many slides adapted from Steve Seitz. Binocular stereo Given a calibrated binocular stereo pair, fuse it to produce a depth image image 1image.
Lec 22: Stereo CS4670 / 5670: Computer Vision Kavita Bala.
Computer Vision No. 7: Stereo part 2. Today’s topics u Projective geometry u Camera Projection Matrix u F Matrix u Multi View Shape Reconstruction.
Computer Vision Lecture #10 Hossam Abdelmunim 1 & Aly A. Farag 2 1 Computer & Systems Engineering Department, Ain Shams University, Cairo, Egypt 2 Electerical.
Finish Hardware Accelerated Voxel Coloring Anselmo A. Montenegro †, Luiz Velho †, Paulo Carvalho † and Marcelo Gattass ‡ †
Bahadir K. Gunturk1 Phase Correlation Bahadir K. Gunturk2 Phase Correlation Take cross correlation Take inverse Fourier transform  Location of the impulse.
stereo Outline : Remind class of 3d geometry Introduction
875 Dynamic Scene Reconstruction
Paper presentation topics 2. More on feature detection and descriptors 3. Shape and Matching 4. Indexing and Retrieval 5. More on 3D reconstruction 1.
The University of Ontario From photohulls to photoflux optimization Yuri Boykov University of Western Ontario Victor Lempitsky Moscow State University.
Project 2 due today Project 3 out today Announcements TexPoint fonts used in EMF. Read the TexPoint manual before you delete this box.: AAAAA.
CSCE 641 Computer Graphics: Image-based Modeling Jinxiang Chai.
Photoconsistency constraint C2 q C1 p l = 2 l = 3 Depth labels If this 3D point is visible in both cameras, pixels p and q should have similar intensities.
Lec 26: Fundamental Matrix CS4670 / 5670: Computer Vision Kavita Bala.
CSE 185 Introduction to Computer Vision Stereo 2.
Robot Vision SS 2011 Matthias Rüther / Matthias Straka 1 ROBOT VISION Lesson 7: Volumetric Object Reconstruction Matthias Straka.
From Photohulls to Photoflux Optimization
Silhouette Intersection
Announcements Midterm due now Project 2 artifacts: vote today!
MSR Image based Reality Project
Chapter 11: Stereopsis Stereopsis: Fusing the pictures taken by two cameras and exploiting the difference (or disparity) between them to obtain the depth.
Announcements Project 3 out today (help session at end of class)
Exact Voxel Occupancy with Graph Cuts
Stereo vision Many slides adapted from Steve Seitz.
Presentation transcript:

Project 1 grades out Announcements

Multiview stereo Readings S. M. Seitz and C. R. Dyer, Photorealistic Scene Reconstruction by Voxel Coloring, International Journal of Computer Vision, 35(2), 1999, pp Photorealistic Scene Reconstruction by Voxel Coloring > CMU’s 3D Room

width of a pixel Choosing the stereo baseline What’s the optimal baseline? Too small: large depth error Too large: difficult search problem Large Baseline Small Baseline all of these points project to the same pair of pixels

The Effect of Baseline on Depth Estimation

1/z width of a pixel width of a pixel 1/z pixel matching score

Multibaseline Stereo Basic Approach Choose a reference view Use your favorite stereo algorithm BUT >replace two-view SSD with SSD over all baselines Limitations Must choose a reference view (bad) Visibility! CMU’s 3D Room Video

The visibility problem Inverse Visibility known images Unknown Scene Which points are visible in which images? Known Scene Forward Visibility known scene

Volumetric stereo Scene Volume V Input Images (Calibrated) Goal: Determine occupancy, “color” of points in V

Discrete formulation: Voxel Coloring Discretized Scene Volume Input Images (Calibrated) Goal: Assign RGBA values to voxels in V photo-consistent with images

Complexity and computability Discretized Scene Volume N voxels C colors 3 All Scenes ( C N 3 ) Photo-Consistent Scenes True Scene

Issues Theoretical Questions Identify class of all photo-consistent scenes Practical Questions How do we compute photo-consistent models?

1. C=2 (shape from silhouettes) Volume intersection [Baumgart 1974] >For more info: Rapid octree construction from image sequences. R. Szeliski, CVGIP: Image Understanding, 58(1):23-32, July (this paper is apparently not available online) or >W. Matusik, C. Buehler, R. Raskar, L. McMillan, and S. J. Gortler, Image-Based Visual Hulls, SIGGRAPH 2000 ( pdf 1.6 MB )pdf 1.6 MB 2. C unconstrained, viewpoint constraints Voxel coloring algorithm [Seitz & Dyer 97] 3. General Case Space carving [Kutulakos & Seitz 98] Voxel coloring solutions

Reconstruction from Silhouettes (C = 2) Binary Images Approach: Backproject each silhouette Intersect backprojected volumes

Volume intersection Reconstruction Contains the True Scene But is generally not the same In the limit (all views) get visual hull >Complement of all lines that don’t intersect S

Voxel algorithm for volume intersection Color voxel black if on silhouette in every image for M images, N 3 voxels Don’t have to search 2 N 3 possible scenes! O( ? ),

Properties of Volume Intersection Pros Easy to implement, fast Accelerated via octrees [Szeliski 1993] or interval techniques [Matusik 2000] Cons No concavities Reconstruction is not photo-consistent Requires identification of silhouettes

Voxel Coloring Solutions 1. C=2 (silhouettes) Volume intersection [Baumgart 1974] 2. C unconstrained, viewpoint constraints Voxel coloring algorithm [Seitz & Dyer 97] >For more info: General Case Space carving [Kutulakos & Seitz 98]

1. Choose voxel 2. Project and correlate 3.Color if consistent (standard deviation of pixel colors below threshold) Voxel Coloring Approach Visibility Problem: in which images is each voxel visible?

Layers Depth Ordering: visit occluders first! SceneTraversal Condition: depth order is the same for all input views

Panoramic Depth Ordering Cameras oriented in many different directions Planar depth ordering does not apply

Panoramic Depth Ordering Layers radiate outwards from cameras

Panoramic Layering Layers radiate outwards from cameras

Panoramic Layering Layers radiate outwards from cameras

Compatible Camera Configurations Depth-Order Constraint Scene outside convex hull of camera centers Outward-Looking cameras inside scene Inward-Looking cameras above scene

Calibrated Image Acquisition Calibrated Turntable 360° rotation (21 images) Selected Dinosaur Images Selected Flower Images

Voxel Coloring Results (Video) Dinosaur Reconstruction 72 K voxels colored 7.6 M voxels tested 7 min. to compute on a 250MHz SGI Flower Reconstruction 70 K voxels colored 7.6 M voxels tested 7 min. to compute on a 250MHz SGI

Limitations of Depth Ordering A view-independent depth order may not exist pq Need more powerful general-case algorithms Unconstrained camera positions Unconstrained scene geometry/topology

Voxel Coloring Solutions 1. C=2 (silhouettes) Volume intersection [Baumgart 1974] 2. C unconstrained, viewpoint constraints Voxel coloring algorithm [Seitz & Dyer 97] 3. General Case Space carving [Kutulakos & Seitz 98] >For more info:

Space Carving Algorithm Image 1 Image N …... Initialize to a volume V containing the true scene Repeat until convergence Choose a voxel on the current surface Carve if not photo-consistent Project to visible input images

Which shape do you get? The Photo Hull is the UNION of all photo-consistent scenes in V It is a photo-consistent scene reconstruction Tightest possible bound on the true scene True Scene V Photo Hull V

Space Carving Algorithm The Basic Algorithm is Unwieldy Complex update procedure Alternative: Multi-Pass Plane Sweep Efficient, can use texture-mapping hardware Converges quickly in practice Easy to implement Results Algorithm

Multi-Pass Plane Sweep Sweep plane in each of 6 principle directions Consider cameras on only one side of plane Repeat until convergence True SceneReconstruction

Multi-Pass Plane Sweep Sweep plane in each of 6 principle directions Consider cameras on only one side of plane Repeat until convergence

Multi-Pass Plane Sweep Sweep plane in each of 6 principle directions Consider cameras on only one side of plane Repeat until convergence

Multi-Pass Plane Sweep Sweep plane in each of 6 principle directions Consider cameras on only one side of plane Repeat until convergence

Multi-Pass Plane Sweep Sweep plane in each of 6 principle directions Consider cameras on only one side of plane Repeat until convergence

Multi-Pass Plane Sweep Sweep plane in each of 6 principle directions Consider cameras on only one side of plane Repeat until convergence

Space Carving Results: African Violet Input Image (1 of 45)Reconstruction

Space Carving Results: Hand Input Image (1 of 100) Views of Reconstruction

Other Approaches Level-Set Methods [Faugeras & Keriven 1998] Evolve implicit function by solving PDE’s Probabilistic Voxel Reconstruction [DeBonet & Viola 1999], [Broadhurst et al. 2001] Solve for voxel uncertainty (also transparency) Transparency and Matting [Szeliski & Golland 1998] Compute voxels with alpha-channel Max Flow/Min Cut [Roy & Cox 1998] Graph theoretic formulation Mesh-Based Stereo [Fua & Leclerc 1995], [Zhang & Seitz 2001] Mesh-based but similar consistency formulation Virtualized Reality [Narayan, Rander, Kanade 1998] Perform stereo 3 images at a time, merge results