Noah Snavely Steven M. Seitz. Richard Szeliski. University of Washington. Microsoft Research. Modified from authors slides
|
|
|
- Blake Bruce
- 5 years ago
- Views:
Transcription
1 Photo Tourism: Exploring Photo Collections in 3D Noah Snavely Steven M. Seitz University of Washington Richard Szeliski Microsoft Research Noah Snavely Noah Snavely Modified from authors slides
2 15,464 37,383 76,389
3 15,464 37,383 76,389
4 Reproduced with permission of Yahoo! Inc by Yahoo! Inc. YAHOO! and the YAHOO! logo are trademarks of Yahoo! Inc.
5 Photo Tourism
6 Photo Tourism overview Input photographs Scene reconstruction Relative camera positions and orientations Point cloud Sparse correspondence Photo Explorer
7 Related work Image-based modeling Debevec, et al. SIGGRAPH 1996 Schaffalitzky and Zisserman Brown and Lowe ECCV DIM 2005 Image-based rendering Aspen Movie Map Lippman, et al., 1978 Photorealistic IBR: Levoy and Hanrahan, SIGGRAPH 1996 Gortler, et al, SIGGRAPH 1996 Seitz and Dyer, SIGGRAPH 1996 Aliaga, et al, SIGGRAPH 2001 and many others
8 Related work Image browsing Toyama, et al, McCurdy and Griswold Sivic and Zisserman Int. Conf. Multimedia, 2003 Mobisys 2003 ICCV 2003
9 Photo Tourism overview Scene reconstruction Input photographs Photo Explorer
10 Scene reconstruction Automatically estimate position, orientation, and focal length of cameras 3D positions of feature points Feature detection Pairwise feature matching Incremental structure from motion Correspondence estimation
![2004]](/docs-images/88/115822484/images/11-6.jpg)
11 Feature detection Detect t features using SIFT [Lowe, IJCV 2004]
12 Feature detection Detect t features using SIFT [Lowe, IJCV 2004]
13 Pairwise feature matching Match features between each pair of images
14 Pairwise feature matching Refine matching using RANSAC [Fischler & Bolles 1987] to estimate fundamental matrices between pairs
![2004]](/docs-images/88/115822484/images/15-4.jpg)
15 Feature detection Detect features using SIFT [Lowe, IJCV 2004]
![2004]](/docs-images/88/115822484/images/16-6.jpg)
16 Feature detection Detect features using SIFT [Lowe, IJCV 2004]
17 Feature detection Detect features using SIFT [Lowe, IJCV 2004]
18 Feature matching Match features between each pair of images
19 Correspondence estimation Link up pairwise i matches to form connected components of matches across several images Image 1 Image 2 Image 3 Image 4
20 Structure from motion p 4 p 1 p 4 p 3 minimize p 2 f (R,T,P) T p 5 p 7 p 5 p 6 p 7 Camera 1 Camera 3 R 1,t 1 Camera 2 R 3,t 3 R 2,t 2
21 Incremental structure from motion
22 Incremental structure from motion
23 Incremental structure from motion
24 Incremental structure from motion
25 Incremental structure from motion
26 Incremental structure from motion
27 Reconstruction performance For photo sets from the Internet, t 20% to 75% of the photos were registered Most unregistered photos belonged to different connected components Running time: < 1 hour for 80 photos > 1 week for 2600 photo
28 Photo Tourism overview Input photographs Scene reconstruction Photo Explorer
29 Photo Explorer
30 Demo
31 Photo Tourism overview Scene reconstruction Input photographs Photo Explorer Navigation Rendering Annotations
32 Navigation controls Free-flight navigation Object-based based browsing Relation-based browsing Overhead map
33 Object-based based browsing
34 Object-based based browsing Visibilityibili Resolution Head-on view
35 Relation-based browsing Find all similar images Find all details Find all zoom outs Zoom in Move left Move right Zoom out
36 Relation-based browsing is to the left of Image B is detail of Image A is a zoom out of Image C Image D
37 Relation-based browsing is to the left of Image B is detail of Image A is a zoom out of Image C Image D
38 Relation-based browsing Image A Image B
39 Relation-based browsing Image A Image B
40 Relation-based browsing to the right of Image A Image B Image C
41 Relation-based browsing to the right of Image A Image B Image C
42 Relation-based browsing to the right of Image A Image B is detail of Image C Image D
43 Relation-based browsing to the right of Image A Image B is detail of Image C Image D
44 Relation-based browsing to the left of to the right of Image A Image B is zoom-out of is detail of is detail of is detail of is zoom-out of is zoom-out of Image C is detail of Image D
45 Prague Old Town Square
46 Photo Tourism overview Scene reconstruction Input photographs Photo Explorer Navigation Rendering Annotations
47 Rendering
48 Rendering
49 Rendering
50 Rendering transitions
51 Rendering transitions
52 Rendering transitions
53 Rendering transitions Camera A Camera B
54 Photo Tourism overview Scene reconstruction Input photographs Photo Explorer Navigation Rendering Annotations
55 Annotations
56 Annotations Reproduced with permission of Yahoo! Inc by Yahoo! Inc. YAHOO! and the YAHOO! logo are trademarks of Yahoo! Inc.
57 Annotations
58 Paris Prague Rome Yosemite
59 Yosemite
60 Contributions Automated t system for registering i photo collections in 3D for interactive exploration Structure from motion algorithm demonstrated on hundreds of photos from the Internet Photo exploration system combining new image- based rendering and photo navigation techniques
61 Limitations / Future work Not all photos can be reliably matched Better feature detection / matching Integrating GPS & other localization info. Structure t from motion scalability More efficient (sparse) algorithms Plane-based transitions lack parallax
62 Limitations / Future work
63 Limitations / Future work Not all photos can be reliably matched Better feature detection / matching Integrating GPS & other localization info. Structure t from motion scalability More efficient (sparse) algorithms Plane-based transitions lack parallax Richer transitions Photo explorer scalability
64 Future work Photo explorer scalability Design client-server architecture for streaming images and geometry at required resolution Scale to all of the world s photos (and videos ) Photosynth project at Microsoft Live Labs (live demo)
65 Acknowledgements National Science Foundation Achievement Rewards for College Scientists (ARCS) The many people who allowed use of their photos UW GRAIL Lab MSR Interactive Visual Media Lab Kevin Chiu and Andy Hou for writing the Java applet
66 Conclusion Indexing everyone s photos provides a new way to share and experience our world To find out more: Exhibition booth #2619 Saint Basil's Cathedral Trafalgar Square Rockefeller Center Mount Rushmore
67
68 Statistics Dataset # input # registered Trevi Fountain Yosemite 325 1,893 Notre Dame 597 2,635 Prague Great Wall Trafalgar Square 278 1,893
69 Reconstruction running time Great Wall: 82 / 120 photos registered Running time: ~ 3 hours Notre Dame: 597 / 2,635 photos registered Running time: ~ 2 weeks
70 Future work Incorporate other metadata t (e.g., time, photographer) and media (e.g., panoramas, video) Enhanced morphing Scale up structure from motion algorithm
71 Visibility
72 Visibility
73 Advantages of 3D over 2D 3D geometry has multi-image i consistency Can annotate point cloud directly Can import annotations from georeferenced sources (e.g., landmark databases) Can use depth as cue for rejecting outliers in selection
74 Post-processing the reconstruction Compute gravity direction Center point cloud at the origin Scale model to unit variance
Photo Tourism: Exploring Photo Collections in 3D
Photo Tourism: Exploring Photo Collections in 3D Noah Snavely Steven M. Seitz University of Washington Richard Szeliski Microsoft Research 15,464 37,383 76,389 2006 Noah Snavely 15,464 37,383 76,389 Reproduced
Photo Tourism: Exploring Photo Collections in 3D
Photo Tourism: Exploring Photo Collections in 3D SIGGRAPH 2006 Noah Snavely Steven M. Seitz University of Washington Richard Szeliski Microsoft Research 2006 2006 Noah Snavely Noah Snavely Reproduced with
Camera Calibration. COS 429 Princeton University
Camera Calibration COS 429 Princeton University Point Correspondences What can you figure out from point correspondences? Noah Snavely Point Correspondences X 1 X 4 X 3 X 2 X 5 X 6 X 7 p 1,1 p 1,2 p 1,3
Homographies and RANSAC
Homographies and RANSAC Computer vision 6.869 Bill Freeman and Antonio Torralba March 30, 2011 Homographies and RANSAC Homographies RANSAC Building panoramas Phototourism 2 Depth-based ambiguity of position
Photo Tourism: Exploring Photo Collections in 3D
Click! Click! Oooo!! Click! Zoom click! Click! Some other camera noise!! Photo Tourism: Exploring Photo Collections in 3D Click! Click! Ahhh! Click! Click! Overview of Research at Microsoft, 2007 Jeremy
Image correspondences and structure from motion
Image correspondences and structure from motion http://graphics.cs.cmu.edu/courses/15-463 15-463, 15-663, 15-862 Computational Photography Fall 2017, Lecture 20 Course announcements Homework 5 posted.
The Light Field and Image-Based Rendering
Lecture 11: The Light Field and Image-Based Rendering Visual Computing Systems Demo (movie) Royal Palace: Madrid, Spain Image-based rendering (IBR) So far in course: rendering = synthesizing an image from
Lecture 15: Image-Based Rendering and the Light Field. Kayvon Fatahalian CMU : Graphics and Imaging Architectures (Fall 2011)
Lecture 15: Image-Based Rendering and the Light Field Kayvon Fatahalian CMU 15-869: Graphics and Imaging Architectures (Fall 2011) Demo (movie) Royal Palace: Madrid, Spain Image-based rendering (IBR) So
Sparse 3D Model Reconstruction from photographs
Sparse 3D Model Reconstruction from photographs Kanchalai Suveepattananont ksuvee@seas.upenn.edu Professor Norm Badler badler@seas.upenn.edu Advisor Aline Normoyle alinen@seas.upenn.edu Abstract Nowaday,
CS5670: Computer Vision
CS5670: Computer Vision Noah Snavely Multi-view stereo Announcements Project 3 ( Autostitch ) due Monday 4/17 by 11:59pm Recommended Reading Szeliski Chapter 11.6 Multi-View Stereo: A Tutorial Furukawa
Large Scale 3D Reconstruction by Structure from Motion
Large Scale 3D Reconstruction by Structure from Motion Devin Guillory Ziang Xie CS 331B 7 October 2013 Overview Rome wasn t built in a day Overview of SfM Building Rome in a Day Building Rome on a Cloudless
Region Graphs for Organizing Image Collections
Region Graphs for Organizing Image Collections Alexander Ladikos 1, Edmond Boyer 2, Nassir Navab 1, and Slobodan Ilic 1 1 Chair for Computer Aided Medical Procedures, Technische Universität München 2 Perception
Hierarchical Photo Organization using Geo-Relevance
Proceedings of the 15th International Symposium on Advances in Geographic Information Systems ACM GIS 2007 Hierarchical Photo Organization using Geo-Relevance Boris Epshtein Borisep@microsoft.com Eyal
Structure from Motion
/8/ Structure from Motion Computer Vision CS 43, Brown James Hays Many slides adapted from Derek Hoiem, Lana Lazebnik, Silvio Saverese, Steve Seitz, and Martial Hebert This class: structure from motion
Instance-level recognition
Instance-level recognition 1) Local invariant features 2) Matching and recognition with local features 3) Efficient visual search 4) Very large scale indexing Matching of descriptors Matching and 3D reconstruction
Structure from Motion CSC 767
Structure from Motion CSC 767 Structure from motion Given a set of corresponding points in two or more images, compute the camera parameters and the 3D point coordinates?? R,t R 2,t 2 R 3,t 3 Camera??
Instance-level recognition
Instance-level recognition 1) Local invariant features 2) Matching and recognition with local features 3) Efficient visual search 4) Very large scale indexing Matching of descriptors Matching and 3D reconstruction
Structure from Motion
11/18/11 Structure from Motion Computer Vision CS 143, Brown James Hays Many slides adapted from Derek Hoiem, Lana Lazebnik, Silvio Saverese, Steve Seitz, and Martial Hebert This class: structure from
International Journal for Research in Applied Science & Engineering Technology (IJRASET) A Review: 3D Image Reconstruction From Multiple Images
A Review: 3D Image Reconstruction From Multiple Images Rahul Dangwal 1, Dr. Sukhwinder Singh 2 1 (ME Student) Department of E.C.E PEC University of TechnologyChandigarh, India-160012 2 (Supervisor)Department
Structure from motion
Structure from motion Structure from motion Given a set of corresponding points in two or more images, compute the camera parameters and the 3D point coordinates?? R 1,t 1 R 2,t R 2 3,t 3 Camera 1 Camera
Prof. Trevor Darrell Lecture 18: Multiview and Photometric Stereo
C280, Computer Vision Prof. Trevor Darrell trevor@eecs.berkeley.edu Lecture 18: Multiview and Photometric Stereo Today Multiview stereo revisited Shape from large image collections Voxel Coloring Digital
Structure from motion
Structure from motion Structure from motion Given a set of corresponding points in two or more images, compute the camera parameters and the 3D point coordinates?? R 1,t 1 R 2,t 2 R 3,t 3 Camera 1 Camera
Advanced Digital Photography and Geometry Capture. Visual Imaging in the Electronic Age Lecture #10 Donald P. Greenberg September 24, 2015
Advanced Digital Photography and Geometry Capture Visual Imaging in the Electronic Age Lecture #10 Donald P. Greenberg September 24, 2015 Eye of a Fly AWARE-2 Duke University http://www.nanowerk.com/spotlight/spotid=3744.php
Chaplin, Modern Times, 1936
Chaplin, Modern Times, 1936 [A Bucket of Water and a Glass Matte: Special Effects in Modern Times; bonus feature on The Criterion Collection set] Multi-view geometry problems Structure: Given projections
Stereo Epipolar Geometry for General Cameras. Sanja Fidler CSC420: Intro to Image Understanding 1 / 33
Stereo Epipolar Geometry for General Cameras Sanja Fidler CSC420: Intro to Image Understanding 1 / 33 Stereo Epipolar geometry Case with two cameras with parallel optical axes General case Now this Sanja
Image-Based Modeling and Rendering
Image-Based Modeling and Rendering Richard Szeliski Microsoft Research IPAM Graduate Summer School: Computer Vision July 26, 2013 How far have we come? Light Fields / Lumigraph - 1996 Richard Szeliski
Local Feature Detectors
Local Feature Detectors Selim Aksoy Department of Computer Engineering Bilkent University saksoy@cs.bilkent.edu.tr Slides adapted from Cordelia Schmid and David Lowe, CVPR 2003 Tutorial, Matthew Brown,
Srikumar Ramalingam. Review. 3D Reconstruction. Pose Estimation Revisited. School of Computing University of Utah
School of Computing University of Utah Presentation Outline 1 2 3 Forward Projection (Reminder) u v 1 KR ( I t ) X m Y m Z m 1 Backward Projection (Reminder) Q K 1 q Presentation Outline 1 2 3 Sample Problem
Image-Based Modeling and Rendering
Traditional Computer Graphics Image-Based Modeling and Rendering Thomas Funkhouser Princeton University COS 426 Guest Lecture Spring 2003 How would you model and render this scene? (Jensen) How about this
Computer Vision. I-Chen Lin, Assistant Professor Dept. of CS, National Chiao Tung University
Computer Vision I-Chen Lin, Assistant Professor Dept. of CS, National Chiao Tung University About the course Course title: Computer Vision Lectures: EC016, 10:10~12:00(Tues.); 15:30~16:20(Thurs.) Pre-requisites:
Multi-view stereo. Many slides adapted from S. Seitz
Multi-view stereo Many slides adapted from S. Seitz Beyond two-view stereo The third eye can be used for verification Multiple-baseline stereo Pick a reference image, and slide the corresponding window
3D Wikipedia: Using online text to automatically label and navigate reconstructed geometry
3D Wikipedia: Using online text to automatically label and navigate reconstructed geometry Bryan C. Russell et al. SIGGRAPH Asia 2013 Presented by YoungBin Kim 2014. 01. 10 Abstract Produce annotated 3D
C280, Computer Vision
C280, Computer Vision Prof. Trevor Darrell trevor@eecs.berkeley.edu Lecture 11: Structure from Motion Roadmap Previous: Image formation, filtering, local features, (Texture) Tues: Feature-based Alignment
A Systems View of Large- Scale 3D Reconstruction
Lecture 23: A Systems View of Large- Scale 3D Reconstruction Visual Computing Systems Goals and motivation Construct a detailed 3D model of the world from unstructured photographs (e.g., Flickr, Facebook)
Lecture 10: Multi-view geometry
Lecture 10: Multi-view geometry Professor Stanford Vision Lab 1 What we will learn today? Review for stereo vision Correspondence problem (Problem Set 2 (Q3)) Active stereo vision systems Structure from
Advanced Digital Photography and Geometry Capture. Visual Imaging in the Electronic Age Lecture #10 Donald P. Greenberg September 24, 2015
Advanced Digital Photography and Geometry Capture Visual Imaging in the Electronic Age Lecture #10 Donald P. Greenberg September 24, 2015 Eye of a Fly AWARE-2 Duke University http://www.nanowerk.com/spotlight/spotid=3744.php
Image stitching. Digital Visual Effects Yung-Yu Chuang. with slides by Richard Szeliski, Steve Seitz, Matthew Brown and Vaclav Hlavac
Image stitching Digital Visual Effects Yung-Yu Chuang with slides by Richard Szeliski, Steve Seitz, Matthew Brown and Vaclav Hlavac Image stitching Stitching = alignment + blending geometrical registration
BSB663 Image Processing Pinar Duygulu. Slides are adapted from Selim Aksoy
BSB663 Image Processing Pinar Duygulu Slides are adapted from Selim Aksoy Image matching Image matching is a fundamental aspect of many problems in computer vision. Object or scene recognition Solving
Miniature faking. In close-up photo, the depth of field is limited.
Miniature faking In close-up photo, the depth of field is limited. http://en.wikipedia.org/wiki/file:jodhpur_tilt_shift.jpg Miniature faking Miniature faking http://en.wikipedia.org/wiki/file:oregon_state_beavers_tilt-shift_miniature_greg_keene.jpg
CS 4495 Computer Vision A. Bobick. Motion and Optic Flow. Stereo Matching
Stereo Matching Fundamental matrix Let p be a point in left image, p in right image l l Epipolar relation p maps to epipolar line l p maps to epipolar line l p p Epipolar mapping described by a 3x3 matrix
Instance-level recognition part 2
Visual Recognition and Machine Learning Summer School Paris 2011 Instance-level recognition part 2 Josef Sivic http://www.di.ens.fr/~josef INRIA, WILLOW, ENS/INRIA/CNRS UMR 8548 Laboratoire d Informatique,
Painting-to-3D Model Alignment Via Discriminative Visual Elements. Mathieu Aubry (INRIA) Bryan Russell (Intel) Josef Sivic (INRIA)
Painting-to-3D Model Alignment Via Discriminative Visual Elements Mathieu Aubry (INRIA) Bryan Russell (Intel) Josef Sivic (INRIA) This work Browsing across time 1699 1740 1750 1800 1800 1699 1740 1750
Lecture 10: Multi view geometry
Lecture 10: Multi view geometry Professor Fei Fei Li Stanford Vision Lab 1 What we will learn today? Stereo vision Correspondence problem (Problem Set 2 (Q3)) Active stereo vision systems Structure from
CS 4495 Computer Vision A. Bobick. Motion and Optic Flow. Stereo Matching
Stereo Matching Fundamental matrix Let p be a point in left image, p in right image l l Epipolar relation p maps to epipolar line l p maps to epipolar line l p p Epipolar mapping described by a 3x3 matrix
Efficient and Rich Annotations for Large Photo Collections
Efficient and Rich Annotations for Large Photo Collections Jayaguru Panda jayaguru.panda@research.iiit.ac.in IIIT Hyderabad, India C V Jawahar jawahar@iiit.ac.in IIIT Hyderabad, India Abstract Large unstructured
EE 6882 Visual Search Engine
3/9/22 EE 6882 Visual Search Engine Prof. Shih Fu Chang, March 9, 22 Lecture #8 Mid Term Project Presentation Structure from Motion: Photo Synth/Tourism Course Project 3/26 mid term presentation slides
Image-based rendering using plane-sweeping modelisation
Author manuscript, published in "IAPR Machine Vision and Applications MVA2005, Japan (2005)" Image-based rendering using plane-sweeping modelisation Vincent Nozick, Sylvain Michelin and Didier Arquès Marne
CS664 Lecture #19: Layers, RANSAC, panoramas, epipolar geometry
CS664 Lecture #19: Layers, RANSAC, panoramas, epipolar geometry Some material taken from: David Lowe, UBC Jiri Matas, CMP Prague http://cmp.felk.cvut.cz/~matas/papers/presentations/matas_beyondransac_cvprac05.ppt
Structure from Motion
04/4/ Structure from Motion Comuter Vision CS 543 / ECE 549 University of Illinois Derek Hoiem Many slides adated from Lana Lazebnik, Silvio Saverese, Steve Seitz his class: structure from motion Reca
CS 4758: Automated Semantic Mapping of Environment
CS 4758: Automated Semantic Mapping of Environment Dongsu Lee, ECE, M.Eng., dl624@cornell.edu Aperahama Parangi, CS, 2013, alp75@cornell.edu Abstract The purpose of this project is to program an Erratic
A New Representation for Video Inspection. Fabio Viola
A New Representation for Video Inspection Fabio Viola Outline Brief introduction to the topic and definition of long term goal. Description of the proposed research project. Identification of a short term
Patch Descriptors. EE/CSE 576 Linda Shapiro
Patch Descriptors EE/CSE 576 Linda Shapiro 1 How can we find corresponding points? How can we find correspondences? How do we describe an image patch? How do we describe an image patch? Patches with similar
Epipolar Geometry CSE P576. Dr. Matthew Brown
Epipolar Geometry CSE P576 Dr. Matthew Brown Epipolar Geometry Epipolar Lines, Plane Constraint Fundamental Matrix, Linear solution + RANSAC Applications: Structure from Motion, Stereo [ Szeliski 11] 2
Structure from Motion
Structure from Motion Computer Vision Jia-Bin Huang, Virginia Tech Many slides from S. Seitz, N Snavely, and D. Hoiem Administrative stuffs HW 3 due 11:55 PM, Oct 17 (Wed) Submit your alignment results!
Last lecture. Passive Stereo Spacetime Stereo
Last lecture Passive Stereo Spacetime Stereo Today Structure from Motion: Given pixel correspondences, how to compute 3D structure and camera motion? Slides stolen from Prof Yungyu Chuang Epipolar geometry
Morphable 3D-Mosaics: a Hybrid Framework for Photorealistic Walkthroughs of Large Natural Environments
Morphable 3D-Mosaics: a Hybrid Framework for Photorealistic Walkthroughs of Large Natural Environments Nikos Komodakis and Georgios Tziritas Computer Science Department, University of Crete E-mails: {komod,
Image-Based Rendering
Image-Based Rendering COS 526, Fall 2016 Thomas Funkhouser Acknowledgments: Dan Aliaga, Marc Levoy, Szymon Rusinkiewicz What is Image-Based Rendering? Definition 1: the use of photographic imagery to overcome
Image Based Reconstruction II
Image Based Reconstruction II Qixing Huang Feb. 2 th 2017 Slide Credit: Yasutaka Furukawa Image-Based Geometry Reconstruction Pipeline Last Lecture: Multi-View SFM Multi-View SFM This Lecture: Multi-View
3-D Shape Reconstruction from Light Fields Using Voxel Back-Projection
3-D Shape Reconstruction from Light Fields Using Voxel Back-Projection Peter Eisert, Eckehard Steinbach, and Bernd Girod Telecommunications Laboratory, University of Erlangen-Nuremberg Cauerstrasse 7,
Structure from Motion. Introduction to Computer Vision CSE 152 Lecture 10
Structure from Motion CSE 152 Lecture 10 Announcements Homework 3 is due May 9, 11:59 PM Reading: Chapter 8: Structure from Motion Optional: Multiple View Geometry in Computer Vision, 2nd edition, Hartley
CS231M Mobile Computer Vision Structure from motion
CS231M Mobile Computer Vision Structure from motion - Cameras - Epipolar geometry - Structure from motion Pinhole camera Pinhole perspective projection f o f = focal length o = center of the camera z y
Srikumar Ramalingam. Review. 3D Reconstruction. Pose Estimation Revisited. School of Computing University of Utah
School of Computing University of Utah Presentation Outline 1 2 3 Forward Projection (Reminder) u v 1 KR ( I t ) X m Y m Z m 1 Backward Projection (Reminder) Q K 1 q Q K 1 u v 1 What is pose estimation?
Epipolar Geometry and Stereo Vision
CS 1674: Intro to Computer Vision Epipolar Geometry and Stereo Vision Prof. Adriana Kovashka University of Pittsburgh October 5, 2016 Announcement Please send me three topics you want me to review next
Structure from motion
Structure from motion Structure from motion Given a set of corresponding points in two or more images, compute the camera parameters and the 3D point coordinates?? R 1,t 1 R 2,t 2 R 3,t 3 Camera 1 Camera
Final project bits and pieces
Final project bits and pieces The project is expected to take four weeks of time for up to four people. At 12 hours per week per person that comes out to: ~192 hours of work for a four person team. Capstone:
Geometry for Computer Vision
Geometry for Computer Vision Lecture 5b Calibrated Multi View Geometry Per-Erik Forssén 1 Overview The 5-point Algorithm Structure from Motion Bundle Adjustment 2 Planar degeneracy In the uncalibrated
Geometric Reconstruction Dense reconstruction of scene geometry
Lecture 5. Dense Reconstruction and Tracking with Real-Time Applications Part 2: Geometric Reconstruction Dr Richard Newcombe and Dr Steven Lovegrove Slide content developed from: [Newcombe, Dense Visual
Augmenting Reality, Naturally:
Augmenting Reality, Naturally: Scene Modelling, Recognition and Tracking with Invariant Image Features by Iryna Gordon in collaboration with David G. Lowe Laboratory for Computational Intelligence Department
Improving Initial Estimations for Structure from Motion Methods
Improving Initial Estimations for Structure from Motion Methods University of Bonn Outline Motivation Computer-Vision Basics Stereo Vision Bundle Adjustment Feature Matching Global Initial Estimation Component
Instance-level recognition II.
Reconnaissance d objets et vision artificielle 2010 Instance-level recognition II. Josef Sivic http://www.di.ens.fr/~josef INRIA, WILLOW, ENS/INRIA/CNRS UMR 8548 Laboratoire d Informatique, Ecole Normale
arxiv: v1 [cs.cv] 28 Sep 2018
![arxiv: v1 [cs.cv] 28 Sep 2018](/thumbs/93/113542646.jpg "arxiv: v1 [cs.cv] 28 Sep 2018")
Camera Pose Estimation from Sequence of Calibrated Images arxiv:1809.11066v1 [cs.cv] 28 Sep 2018 Jacek Komorowski 1 and Przemyslaw Rokita 2 1 Maria Curie-Sklodowska University, Institute of Computer Science,
SIMPLE ROOM SHAPE MODELING WITH SPARSE 3D POINT INFORMATION USING PHOTOGRAMMETRY AND APPLICATION SOFTWARE
SIMPLE ROOM SHAPE MODELING WITH SPARSE 3D POINT INFORMATION USING PHOTOGRAMMETRY AND APPLICATION SOFTWARE S. Hirose R&D Center, TOPCON CORPORATION, 75-1, Hasunuma-cho, Itabashi-ku, Tokyo, Japan Commission
Computational Photography
End of Semester is the last lecture of new material Quiz on Friday 4/30 Sample problems are posted on website Computational Photography Final Project Presentations Wednesday May 12 1-5pm, CII 4040 Attendance
Some books on linear algebra
Some books on linear algebra Finite Dimensional Vector Spaces, Paul R. Halmos, 1947 Linear Algebra, Serge Lang, 2004 Linear Algebra and its Applications, Gilbert Strang, 1988 Matrix Computation, Gene H.
Image-based modeling (IBM) and image-based rendering (IBR)
Image-based modeling (IBM) and image-based rendering (IBR) CS 248 - Introduction to Computer Graphics Autumn quarter, 2005 Slides for December 8 lecture The graphics pipeline modeling animation rendering
Some books on linear algebra
Some books on linear algebra Finite Dimensional Vector Spaces, Paul R. Halmos, 1947 Linear Algebra, Serge Lang, 2004 Linear Algebra and its Applications, Gilbert Strang, 1988 Matrix Computation, Gene H.
Step-by-Step Model Buidling
Step-by-Step Model Buidling Review Feature selection Feature selection Feature correspondence Camera Calibration Euclidean Reconstruction Landing Augmented Reality Vision Based Control Sparse Structure
Image-based Modeling and Rendering: 8. Image Transformation and Panorama
Image-based Modeling and Rendering: 8. Image Transformation and Panorama I-Chen Lin, Assistant Professor Dept. of CS, National Chiao Tung Univ, Taiwan Outline Image transformation How to represent the
But First: Multi-View Projective Geometry
View Morphing (Seitz & Dyer, SIGGRAPH 96) Virtual Camera Photograph Morphed View View interpolation (ala McMillan) but no depth no camera information Photograph But First: Multi-View Projective Geometry
Fundamental matrix. Let p be a point in left image, p in right image. Epipolar relation. Epipolar mapping described by a 3x3 matrix F
Fundamental matrix Let p be a point in left image, p in right image l l Epipolar relation p maps to epipolar line l p maps to epipolar line l p p Epipolar mapping described by a 3x3 matrix F Fundamental
3D Reconstruction on GPU: A Parallel Processing Approach
3D Reconstruction on GPU: A Parallel Processing Approach Shubham Gupta, Siddharth Choudhary, and P.J. Narayanan Center for Visual Information Technology International Institute of Information Technology
In-Situ 3D Indoor Modeler with a Camera and Self-Contained Sensors
In-Situ 3D Indoor Modeler with a Camera and Self-Contained Sensors Tomoya Ishikawa 1, Kalaivani Thangamani 12, Masakatsu Kourogi 1, Andrew P. Gee 3, Walterio Mayol-Cuevas 3, Keechul Jung 4 and Takeshi
A virtual tour of free viewpoint rendering
A virtual tour of free viewpoint rendering Cédric Verleysen ICTEAM institute, Université catholique de Louvain, Belgium cedric.verleysen@uclouvain.be Organization of the presentation Context Acquisition
Local features: detection and description. Local invariant features
Local features: detection and description Local invariant features Detection of interest points Harris corner detection Scale invariant blob detection: LoG Description of local patches SIFT : Histograms
Computer Vision for Computer Graphics
Computer Vision for Computer Graphics Mark Borg Computer Vision & Computer Graphics I Computer Vision Understanding the content of an image (normaly by creating a model of the observed scene) Computer
Computational Photography: Advanced Topics. Paul Debevec
Computational Photography: Advanced Topics Paul Debevec Class: Computational Photography, Advanced Topics Module 1: 105 minutes Debevec,, Raskar and Tumblin 1:45: A.1 Introduction and Overview (Raskar,
Computer Vision, CS766. Staff. Instructor: Li Zhang TA: Jake Rosin
Computer Vision, CS766 Staff Instructor: Li Zhang lizhang@cs.wisc.edu TA: Jake Rosin rosin@cs.wisc.edu Today Introduction Administrative Stuff Overview of the Course About Me Li Zhang ( 张力 ) Last name
Camera Geometry II. COS 429 Princeton University
Camera Geometry II COS 429 Princeton University Outline Projective geometry Vanishing points Application: camera calibration Application: single-view metrology Epipolar geometry Application: stereo correspondence
Structure from Motion and Multi- view Geometry. Last lecture
Structure from Motion and Multi- view Geometry Topics in Image-Based Modeling and Rendering CSE291 J00 Lecture 5 Last lecture S. J. Gortler, R. Grzeszczuk, R. Szeliski,M. F. Cohen The Lumigraph, SIGGRAPH,
Real-time Generation and Presentation of View-dependent Binocular Stereo Images Using a Sequence of Omnidirectional Images
Real-time Generation and Presentation of View-dependent Binocular Stereo Images Using a Sequence of Omnidirectional Images Abstract This paper presents a new method to generate and present arbitrarily
Image Based Rendering. D.A. Forsyth, with slides from John Hart
Image Based Rendering D.A. Forsyth, with slides from John Hart Topics Mosaics translating cameras reveal extra information, break occlusion Optical flow for very small movements of the camera Explicit
3D Reconstruction from Two Views
3D Reconstruction from Two Views Huy Bui UIUC huybui1@illinois.edu Yiyi Huang UIUC huang85@illinois.edu Abstract In this project, we study a method to reconstruct a 3D scene from two views. First, we extract
Image-Based Rendering. Johns Hopkins Department of Computer Science Course : Rendering Techniques, Professor: Jonathan Cohen
Image-Based Rendering Image-Based Rendering What is it? Still a difficult question to answer Uses images (photometric( info) as key component of model representation What s Good about IBR Model acquisition
Amateur photography was once largely a personal RECONSTRUCTING ROME
COVER FE ATURE RECONSTRUCTING ROME Sameer Agarwal and Yasutaka Furukawa, Google Noah Snavely, Cornell University Brian Curless, University of Washington Steven M. Seitz, Google and University of Washington
Applications of Image-Based Modeling and Rendering in Art and Cinema
Applications of Image-Based Modeling and Rendering in Art and Cinema Paul Debevec Overview Image-based techniques are used in many ways; for each we can ask: What is the model? How are images used? What
BIL Computer Vision Apr 16, 2014
BIL 719 - Computer Vision Apr 16, 2014 Binocular Stereo (cont d.), Structure from Motion Aykut Erdem Dept. of Computer Engineering Hacettepe University Slide credit: S. Lazebnik Basic stereo matching algorithm
Image-Based Rendering. Johns Hopkins Department of Computer Science Course : Rendering Techniques, Professor: Jonathan Cohen
Image-Based Rendering Image-Based Rendering What is it? Still a difficult question to answer Uses images (photometric( info) as key component of model representation What s Good about IBR Model acquisition
Lecture 8.2 Structure from Motion. Thomas Opsahl
Lecture 8.2 Structure from Motion Thomas Opsahl More-than-two-view geometry Correspondences (matching) More views enables us to reveal and remove more mismatches than we can do in the two-view case More
Midterm Wed. Local features: detection and description. Today. Last time. Local features: main components. Goal: interest operator repeatability
Midterm Wed. Local features: detection and description Monday March 7 Prof. UT Austin Covers material up until 3/1 Solutions to practice eam handed out today Bring a 8.5 11 sheet of notes if you want Review
A Scalable Collaborative Online System for City Reconstruction
A Scalable Collaborative Online System for City Reconstruction Ole Untzelmann, Torsten Sattler, Sven Middelberg and Leif Kobbelt RWTH Aachen University ole.untzelmann@rwth-aachen.de, {tsattler, middelberg,