Single-view 3D Reconstruction Computational Photography Derek Hoiem, University of Illinois 10/12/10 Some slides from Alyosha Efros, Steve Seitz.

Slides:



Advertisements
Similar presentations
Vanishing points  .
Advertisements

Single-view Metrology and Camera Calibration
3D reconstruction.
CS 691 Computational Photography Instructor: Gianfranco Doretto 3D to 2D Projections.
Paris town hall.
Lecture 8: Stereo.
Camera calibration and epipolar geometry
Structure from motion.
Single-view metrology
Lecture 19: Single-view modeling CS6670: Computer Vision Noah Snavely.
Homographies and Mosaics : Computational Photography Alexei Efros, CMU, Fall 2005 © Jeffrey Martin (jeffrey-martin.com) with a lot of slides stolen.
Epipolar geometry. (i)Correspondence geometry: Given an image point x in the first view, how does this constrain the position of the corresponding point.
Structure from motion. Multiple-view geometry questions Scene geometry (structure): Given 2D point matches in two or more images, where are the corresponding.
Uncalibrated Geometry & Stratification Sastry and Yang
Scene Modeling for a Single View : Computational Photography Alexei Efros, CMU, Fall 2005 René MAGRITTE Portrait d'Edward James …with a lot of slides.
Announcements Project 2 questions Midterm out on Thursday
Lecture 7: Image Alignment and Panoramas CS6670: Computer Vision Noah Snavely What’s inside your fridge?
CS485/685 Computer Vision Prof. George Bebis
Projective geometry Slides from Steve Seitz and Daniel DeMenthon
Panorama signups Panorama project issues? Nalwa handout Announcements.
1Jana Kosecka, CS 223b Cylindrical panoramas Cylindrical panoramas with some slides from R. Szeliski, S. Seitz, D. Lowe, A. Efros,
Lecture 16: Single-view modeling, Part 2 CS6670: Computer Vision Noah Snavely.
Automatic Photo Popup Derek Hoiem Alexei A. Efros Martial Hebert Carnegie Mellon University.
Single-view Metrology and Camera Calibration Computer Vision Derek Hoiem, University of Illinois 02/26/15 1.
CSE473/573 – Stereo Correspondence
CSE 576, Spring 2008Projective Geometry1 Lecture slides by Steve Seitz (mostly) Lecture presented by Rick Szeliski.
Scene Modeling for a Single View : Computational Photography Alexei Efros, CMU, Spring 2010 René MAGRITTE Portrait d'Edward James …with a lot of.
Cameras, lenses, and calibration
3-D Scene u u’u’ Study the mathematical relations between corresponding image points. “Corresponding” means originated from the same 3D point. Objective.
3D Scene Models Object recognition and scene understanding Krista Ehinger.
Single-view Metrology and Cameras Computational Photography Derek Hoiem, University of Illinois 10/8/13.
Single-view metrology
Projective Geometry and Single View Modeling CSE 455, Winter 2010 January 29, 2010 Ames Room.
Single-view modeling, Part 2 CS4670/5670: Computer Vision Noah Snavely.
CSC 589 Lecture 22 Image Alignment and least square methods Bei Xiao American University April 13.
Image-based modeling Digital Visual Effects, Spring 2008 Yung-Yu Chuang 2008/5/6 with slides by Richard Szeliski, Steve Seitz and Alexei Efros.
COMP 175: Computer Graphics March 24, 2015
Single-view 3D Reconstruction Computational Photography Derek Hoiem, University of Illinois 10/18/12 Some slides from Alyosha Efros, Steve Seitz.
02/26/02 (c) 2002 University of Wisconsin, CS 559 Last Time Canonical view pipeline Orthographic projection –There was an error in the matrix for taking.
Single-view Metrology and Camera Calibration Computer Vision Derek Hoiem, University of Illinois 01/25/11 1.
Recovering Surface Layout from a Single Image D. Hoiem, A.A. Efros, M. Hebert Robotics Institute, CMU Presenter: Derek Hoiem CS 598, Spring 2009 Jan 29,
Metrology 1.Perspective distortion. 2.Depth is lost.
Single View Geometry Course web page: vision.cis.udel.edu/cv April 9, 2003  Lecture 20.
Project 2 –contact your partner to coordinate ASAP –more work than the last project (> 1 week) –you should have signed up for panorama kitssigned up –sign.
Computational Photography Derek Hoiem, University of Illinois
Single-view Metrology and Cameras Computational Photography Derek Hoiem, University of Illinois 10/06/15.
Basic Perspective Projection Watt Section 5.2, some typos Define a focal distance, d, and shift the origin to be at that distance (note d is negative)
Single-view 3D Reconstruction
stereo Outline : Remind class of 3d geometry Introduction
Review on Graphics Basics. Outline Polygon rendering pipeline Affine transformations Projective transformations Lighting and shading From vertices to.
Three-Dimensional Viewing Hearn & Baker Chapter 7
12/24/2015 A.Aruna/Assistant professor/IT/SNSCE 1.
More with Pinhole + Single-view Metrology
12/15/ Fall 2006 Two-Point Perspective Single View Geometry Final Project Faustinus Kevin Gozali an extended tour.
Project 1 Due NOW Project 2 out today –Help session at end of class Announcements.
Image-Based Rendering Geometry and light interaction may be difficult and expensive to model –Think of how hard radiosity is –Imagine the complexity of.
Project 2 went out on Tuesday You should have a partner You should have signed up for a panorama kit Announcements.
55:148 Digital Image Processing Chapter 11 3D Vision, Geometry
Single-view metrology
CSCE 441 Computer Graphics 3-D Viewing
Scene Modeling for a Single View
Modeling 101 For the moment assume that all geometry consists of points, lines and faces Line: A segment between two endpoints Face: A planar area bounded.
Epipolar geometry.
Projective geometry Readings
Viewing (Projections)
Viewing (Projections)
Announcements list – let me know if you have NOT been getting mail
Calibration and homographies
Announcements Project 2 extension: Friday, Feb 8
Presentation transcript:

Single-view 3D Reconstruction Computational Photography Derek Hoiem, University of Illinois 10/12/10 Some slides from Alyosha Efros, Steve Seitz

Questions about Project 4? Get me your labels asap if not already done (will count as late days after today) – Will post everything I’ve got later today So far have labels from: Adair, Arash, Bret, Brian, Derek, Doheum, Lewis, Prateek, Raj, Russ, SteveD, WeiLou

Project 3 Class favorites: would like more votes – vote today if you haven’t – “Favorites” will be presented Thursday

Take-home Question 1) Suppose we have two triangles: ABC and DEF. What transformation will map A to D, B to E, and C to F? How can we get the parameters? A D B E F C 9/23/2010

Take-home question Suppose a 3D cube is facing the camera at a distance. 1.Draw the cube in perspective projection 2.Now draw the cube in weak perspective projection 10/5/10

Take-home question Suppose you have estimated three vanishing points corresponding to orthogonal directions. How can you recover the rotation matrix that is aligned with the 3D axes defined by these points? – Assume that intrinsic matrix K has three parameters – Remember, in homogeneous coordinates, we can write a 3d point at infinity as (X, Y, Z, 0) 10/7/2010 Photo from online Tate collection VP x VP z. VP y

Take-home question Assume that the camera height is 5 ft. – What is the height of the man? – What is the height of the building? – How long is the right side of the building compared to the small window on the right side of the building? 10/7/2010

Today’s class: 3D Reconstruction

The challenge One 2D image could be generated by an infinite number of 3D geometries ? ? ?

The solution Make simplifying assumptions about 3D geometry Unlikely Likely

Today’s class: Two Models Box + frontal billboards Ground plane + non-frontal billboards

“Tour into the Picture” (Horry et al. SIGGRAPH ’97) Create a 3D “theatre stage” of five billboards Specify foreground objects through bounding polygons Use camera transformations to navigate through the scene Following slides modified from Efros

The idea Many scenes (especially paintings), can be represented as an axis-aligned box volume (i.e. a stage) Key assumptions All walls are orthogonal Camera view plane is parallel to back of volume How many vanishing points does the box have? Three, but two at infinity Single-point perspective Can use the vanishing point to fit the box to the particular scene

Fitting the box volume User controls the inner box and the vanishing point placement (# of DOF???) Q: What’s the significance of the vanishing point location? A: It’s at eye (camera) level: ray from COP to VP is perpendicular to image plane.

High Camera Example of user input: vanishing point and back face of view volume are defined

High Camera Example of user input: vanishing point and back face of view volume are defined

Low Camera

Example of user input: vanishing point and back face of view volume are defined

High CameraLow Camera Comparison of how image is subdivided based on two different camera positions. You should see how moving the box corresponds to moving the eyepoint in the 3D world.

Left Camera Another example of user input: vanishing point and back face of view volume are defined

Left Camera Another example of user input: vanishing point and back face of view volume are defined

Right Camera Another example of user input: vanishing point and back face of view volume are defined

Right Camera Another example of user input: vanishing point and back face of view volume are defined

Left CameraRight Camera Comparison of two camera placements – left and right. Corresponding subdivisions match view you would see if you looked down a hallway.

Question Think about the camera center and image plane… – What happens when we move the box? – What happens when we move the vanishing point?

2D to 3D conversion First, we can get ratios leftright top bottom vanishing point back plane

Size of user-defined back plane determines width/height throughout box (orthogonal sides) Use top versus side ratio to determine relative height and width dimensions of box Left/right and top/bot ratios determine part of 3D camera placement leftright top bottom camera pos 2D to 3D conversion

Depth of the box Can compute by similar triangles (CVA vs. CV’A’) Need to know focal length f (or FOV) Note: can compute position on any object on the ground – Simple unprojection – What about things off the ground?

Homography A B C D A’ B’ C’D’ 2d coordinates 3d plane coordinates

Image rectification To unwarp (rectify) an image solve for homography H given p and p’: wp’=Hp p p’ On board

Solving for homographies

Ah0 Defines a least squares problem: 2n × 9 92n Since h is only defined up to scale, solve for unit vector ĥ Solution: ĥ = eigenvector of A T A with smallest eigenvalue Works with 4 or more points

Tour into the picture algorithm 1.Set the box corners

Tour into the picture algorithm 1.Set the box corners 2.Set the VP 3.Get 3D coordinates – Compute height, width, and depth of box 4.Get texture maps – homographies for each face x

Result Render from new views

Foreground Objects Use separate billboard for each For this to work, three separate images used: – Original image. – Mask to isolate desired foreground images. – Background with objects removed

Foreground Objects Add vertical rectangles for each foreground object Can compute 3D coordinates P0, P1 since they are on known plane. P2, P3 can be computed as before (similar triangles)

Foreground Result Video from CMU class: mGwcuM mGwcuM

Automatic Photo Pop-up Input Ground Vertical Sky Geometric LabelsCut’n’Fold3D Model Image Learned Models Hoiem et al. 2005

Cutting and Folding Fit ground-vertical boundary – Iterative Hough transform

Cutting and Folding Form polylines from boundary segments – Join segments that intersect at slight angles – Remove small overlapping polylines Estimate horizon position from perspective cues

Cutting and Folding ``Fold’’ along polylines and at corners ``Cut’’ at ends of polylines and along vertical-sky boundary

Cutting and Folding Construct 3D model Texture map

Results Automatic Photo Pop-up Input Image Cut and Fold

Results Automatic Photo Pop-up Input Image

Comparison with Manual Method Input Image Automatic Photo Pop-up (30 sec)! [Liebowitz et al. 1999]

Failures Labeling Errors

Failures Foreground Objects

Adding Foreground Labels Recovered Surface Labels + Ground-Vertical Boundary Fit Object Boundaries + Horizon

Final project ideas 1 Person – Interactive program to make 3D model from an image (e.g., output in VRML, or draw path for animation) 2 Person – Add tools for cutting out foreground objects and automatic hole-filling

Summary 2D  3D is mathematically impossible Need right assumptions about the world geometry Important tools – Vanishing points – Camera matrix – Homography

The future…. 10/26: Kevin Karsch will show his work that applies many ideas from this section (cutting, texture synthesis, projective geometry, etc.) Next class, we start a new section – Finding correspondences automatically – Image stitching – Various forms of recognition