Multi-perspective Panoramas Slides from a talk by Lihi Zelnik-Manor at ICCV’07 3DRR workshop.

Slides:



Advertisements
Similar presentations
Recognising Panoramas M. Brown and D. Lowe, University of British Columbia.
Advertisements

Multi-view Stereo via Volumetric Graph-cuts George Vogiatzis, Philip H. S. Torr Roberto Cipolla.
Generating Classic Mosaics with Graph Cuts Y. Liu, O. Veksler and O. Juan University of Western Ontario, Canada Ecole Centrale de Paris, France.
Character Animation from 2D Pictures and 3D Motion Data ACM Transactions on Graphics 2007.
Vision Sensing. Multi-View Stereo for Community Photo Collections Michael Goesele, et al, ICCV 2007 Venus de Milo.
Recap from Monday Frequency domain analytical tool computational shortcut compression tool.
Data-driven Visual Similarity for Cross-domain Image Matching
Tour Into the Picture [TIP]. Outline Introduction TIP Multi-Perspective Modeling.
Presented by Marlene Shehadeh Advanced Topics in Computer Vision ( ) Winter
Constructing immersive virtual space for HAI with photos Shingo Mori Yoshimasa Ohmoto Toyoaki Nishida Graduate School of Informatics Kyoto University GrC2011.
Multimedia for the Web: Creating Digital Excitement Multimedia Element -- Graphics.
Announcements Project 2 Out today Sign up for a panorama kit ASAP! –best slots (weekend) go quickly...
FRS 123: Technology in Art and Cultural Heritage Beyond Linear Perspective.
Recognising Panoramas
Direct Methods for Visual Scene Reconstruction Paper by Richard Szeliski & Sing Bing Kang Presented by Kristin Branson November 7, 2002.
Lecture 7: Image Alignment and Panoramas CS6670: Computer Vision Noah Snavely What’s inside your fridge?
Automatic Panoramic Image Stitching using Local Features Matthew Brown and David Lowe, University of British Columbia.
High-Quality Video View Interpolation
Lecture 11: Structure from motion CS6670: Computer Vision Noah Snavely.
Image Stitching and Panoramas
Lecture 13: Projection, Part 2
1Jana Kosecka, CS 223b Cylindrical panoramas Cylindrical panoramas with some slides from R. Szeliski, S. Seitz, D. Lowe, A. Efros,
CS664 Lecture #19: Layers, RANSAC, panoramas, epipolar geometry Some material taken from:  David Lowe, UBC  Jiri Matas, CMP Prague
Automatic Photo Popup Derek Hoiem Alexei A. Efros Martial Hebert Carnegie Mellon University.
CSCE 641: Computer Graphics Image-based Rendering Jinxiang Chai.
Panorama Stitching and Augmented Reality. Local feature matching with large datasets n Examples: l Identify all panoramas and objects in an image set.
Announcements Project 1 artifact voting Project 2 out today (help session at end of class)
Image Pyramids and Blending
© 2006 Autodesk1 Image-processing Technologies for Digital Content Creation
Light Field Video Stabilization ICCV 2009, Kyoto Presentation for CS 534: Computational Photography Friday, April 22, 2011 Brandon M. Smith Li Zhang University.
Mosaics CSE 455, Winter 2010 February 8, 2010 Neel Joshi, CSE 455, Winter Announcements  The Midterm went out Friday  See to the class.
Photocollage System. What is Photocollage? Photographic approach in combining multiple images to create a new whole Result is an expressive composition.
Reconstructing Relief Surfaces George Vogiatzis, Philip Torr, Steven Seitz and Roberto Cipolla BMVC 2004.
David Hockney, born in 1937, is an English artist, who is now based in California. David Hockney was an important contributor to the British Pop Art scene.
Automatic Registration of Color Images to 3D Geometry Computer Graphics International 2009 Yunzhen Li and Kok-Lim Low School of Computing National University.
Image Stitching Shangliang Jiang Kate Harrison. What is image stitching?
MRFs and Segmentation with Graph Cuts Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem 02/24/10.
Object Stereo- Joint Stereo Matching and Object Segmentation Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on Michael Bleyer Vienna.
Image-based rendering Michael F. Cohen Microsoft Research.
Mosaics Today’s Readings Szeliski, Ch 5.1, 8.1 StreetView.
Image stitching Digital Visual Effects Yung-Yu Chuang with slides by Richard Szeliski, Steve Seitz, Matthew Brown and Vaclav Hlavac.
Yu-Wing Tai, Hao Du, Michael S. Brown, Stephen Lin CVPR’08 (Longer Version in Revision at IEEE Trans PAMI) Google Search: Video Deblurring Spatially Varying.
Panorama Photography and Multiperspective Imaging Szymon Rusinkiewicz, Tim Weyrich: Technology in Art and Cultural Heritage. Princeton Freshman Seminar.
MSRI workshop, January 2005 Object Recognition Collected databases of objects on uniform background (no occlusions, no clutter) Mostly focus on viewpoint.
Rendering Synthetic Objects into Real Scenes: Bridging Traditional and Image-based Graphics with Global Illumination and High Dynamic Range Photography.
Image-Based Rendering of Diffuse, Specular and Glossy Surfaces from a Single Image Samuel Boivin and André Gagalowicz MIRAGES Project.
12/7/10 Looking Back, Moving Forward Computational Photography Derek Hoiem, University of Illinois Photo Credit Lee Cullivan.
Scene Reconstruction Seminar presented by Anton Jigalin Advanced Topics in Computer Vision ( )
112/5/ :54 Graphics II Image Based Rendering Session 11.
Smoothly Varying Affine Stitching [CVPR 2011]
The Lit Sphere: A Model for Capturing NPR Shading from Art Peter-Pike Sloan, William Martin, Amy Gooch & Bruce Gooch.
Discontinuous Displacement Mapping for Volume Graphics, Volume Graphics 2006, July 30, Boston, MA Discontinuous Displacement Mapping for Volume Graphics.
Visualizing the Cosmos: Smoke or Mirrors? Designing Visualization Imagery David Bock National Center for Supercomputing Applications University of Illinois,
Seamless Video Stitching from Hand-held Camera Inputs Kaimo Lin, Shuaicheng Liu, Loong-Fah Cheong, Bing Zeng National University of Singapore University.
Image Blending : Computational Photography
CS 4501: Introduction to Computer Vision Sparse Feature Detectors: Harris Corner, Difference of Gaussian Connelly Barnes Slides from Jason Lawrence, Fei.
COSC579: Image Align, Mosaic, Stitch
Image-Based Rendering
Multi-Perspective Panoramas
Multi-perspective Panoramas
© 2005 University of Wisconsin
Real-Time Image Mosaicing
Image Based Modeling and Rendering (PI: Malik)
Rob Fergus Computer Vision
Announcements Project 2 out today (help session at end of class)
“The Truth About Cats And Dogs”
Noah Snavely.
Announcements Project 1 artifact voting Project 2 out today
Lecture 15: Structure from motion
Occlusion and smoothness probabilities in 3D cluttered scenes
Presentation transcript:

Multi-perspective Panoramas Slides from a talk by Lihi Zelnik-Manor at ICCV’07 3DRR workshop

Pictures capture memories

Panoramas Registration: Brown & Lowe, ICCV’05 Blending: Burt & Adelson, Trans. Graphics,1983 Visualization: Kopf et al., SIGGRAPH, 2007

Bad panorama? Output of Brown & Lowe software

No geometrically consistent solution

Scientists solution to panoramas: Single center of projection Registration: Brown & Lowe, ICCV’05 Blending: Burt & Adelson, Trans. Graphics,1983 Visualization: Kopf et al., SIGGRAPH, 2007 No 3D!!!

From sphere to plane Distortions are unavoidable

Distorted panoramas Output of Brown & Lowe software Actual appearance

Objectives 1.Better looking panoramas 2.Let the camera move: Any view Natural photographing

Stand on the shoulders of giants Cartographers Artists

Cartographic projections

Common panorama projections θ φ Cylindircal PerspectiveStereographic

Global Projections Cylindircal PerspectiveStereographic

Learn from the artists Multiple view points De Chirico “Mystery and Melancholy of a Street”, 1914 perspective Sharp discontinuity

Renaissance painters solution “School of Athens”, Raffaello Sanzio ~1510 Give a separate treatment to different parts of the scene!!

Personalized projections “School of Athens”, Raffaello Sanzio ~1510 Give a separate treatment to different parts of the scene!!

Multiple planes of projection Sharp discontinuities can often be well hidden

Our multi-view result Single view

Our multi-view result Single view

Our multi-view result Single view

Applying personalized projections Foreground Input images Background panorama

Single view Our multi-view result

Single view Our multi-view result

Objectives - revisited 1.Better looking panoramas 2.Let the camera move: Any view Natural photographing Multiple views can live together

Multi-view compositions David Hockney, Place Furstenberg, (1985) 3D!!

Melissa Slemin, Place Furstenberg, 2003 Why multi-view? Multiple viewpointsSingle viewpoint David Hockney, Place Furstenberg, 1985

Multi-view panoramas Single viewMultiview Requires video input Zomet et al. (PAMI’03)

Long Imaging Agarwala et al. (SIGGRAPH 2006)

Smooth Multi-View Google maps

What’s wrong in the picture? Google maps

Non-smooth Google maps

The Chair David Hockney (1985)

Joiners are popular 4,985 photos matching joiners. 4,007 photos matching Hockney. 41 groups about Hockney Thousands of members Flickr statistics (Aug’07):

Main goals: Automate joiners Generalize panoramas to general image collections

Objectives For Artists: Reduce manual labor Manual: ~ 40min. Fully automatic

Objectives For Artists: Reduce manual labor For non-artists: Generate pleasing-to-the-eye joiners

Objectives For Artists: Reduce manual labor For non-artists: Generate pleasing-to-the-eye joiners For data exploration: Organize images spatially

What’s going on here?

A cacti garden

Principles

Convey topology Correct Incorrect

Principles Convey topology A 2D layering of images Blending: blurry Graph-cut: cuts hood Desired joiner

Principles Convey topology A 2D layering of images Don’t distort images rotatescaletranslate

Principles Convey topology A 2D layering of images Don’t distort images Minimize inconsistencies Good Bad

Algorithm

Step 1: Feature matching Brown & Lowe, ICCV’03

Step 2: Align Large inconsistencies Brown & Lowe, ICCV’03

Step 3: Order Reduced inconsistencies

Ordering images Try all orders: only for small datasets

Ordering images Try all orders: only for small datasets complexity: (m+n)  m = # images n = # overlaps  = # acyclic orders

Ordering images Observations: –Typically each image overlaps with only a few others –Many decisions can be taken locally

Ordering images Approximate solution: –Solve for each image independently –Iterate over all images

Can we do better?

Step 4: Improve alignment

Iterate Align-Order-Importance

Iterative refinement InitialFinal

Iterative refinement InitialFinal

Iterative refinement InitialFinal

What is this?

That’s me reading

Anza-Borrego

Tractor

Paolo Uccello, 1436 Art reproduction

Paolo Uccello, 1436 Zelnik & Perona, 2006 Art reproduction

Single view-point Zelnik & Perona, 2006 Art reproduction

Manual by Photographer

Our automatic result

Failure?

GUI

The Impossible Bridge

Homage to David Hockney

Incorrect geometries are possible and fun! Geometry is not enough, we need scene analysis A highly related work: "Scene Collages and Flexible Camera Arrays,” Y. Nomura, L. Zhang and S.K. Nayar, Eurographics Symposium on Rendering, Jun, Take home

Thank You