IIIT Hyderabad Geometry Directed Browser for Personal Photographs Center for Visual Information Technology IIIT Hyderabad Aditya Deshpande, Siddharth Choudhary,

Slides:



Advertisements
Similar presentations
Image Retrieval with Geometry-Preserving Visual Phrases
Advertisements

Section 9.1 Computers in Marketing
Wheres Waldo: Matching People in Images of Crowds Rahul GargDeva RamananSteven M. Seitz Noah Snavely Problem Definition University of Washington University.
Wiki-Reality: Augmenting Reality with Community Driven Websites Speaker: Yi Wu Intel Labs/vision and image processing research Collaborators: Douglas Gray,
Services Course Windows Live SkyDrive Participant Guide.
Clustering Crowdsourced Videos by Line-of-Sight FOCUS: Clustering Crowdsourced Videos by Line-of-Sight Puneet Jain, Justin Manweiler, Arup Acharya, and.
Location Recognition Given: A query image A database of images with known locations Two types of approaches: Direct matching: directly match image features.
WELCOME TO THE ANALYSIS PLATFORM V4.1. HOME The updated tool has been simplified and developed to be more intuitive and quicker to use: 3 modes for all.
Photosynth is an entirely new visual medium developed by Microsoft Live Labs. Photosynth is an entirely new visual medium developed by Microsoft Live.
HNA-Drive Familiarization Presentation. From the address bar in your preferred internet browser, navigate to Site supports: Internet.
Virtual Dart: An Augmented Reality Game on Mobile Device Supervisor: Professor Michael R. Lyu Prepared by: Lai Chung Sum Siu Ho Tung.
Lecture 11: Structure from motion, part 2 CS6670: Computer Vision Noah Snavely.
Lecture 11: Structure from motion CS6670: Computer Vision Noah Snavely.
Sketchify Tutorial Graphics and Animation in Sketchify sketchify.sf.net Željko Obrenović
ISIS Katrinebjerg i n t e r a c t i v e s p a c e s. n e t 1 Frank Allan Hansen, Integrating the Web and the World: Contextual Trails on.
ISIS Katrinebjerg i n t e r a c t i v e s p a c e s. n e t 1 Frank Allan Hansen, Integrating the Web and the World: Contextual Trails on.
The sequence of folders to a file or folder is called a(n) ________.
IPhone 4 The iphone is a mobile phone with a lot of extras, theses include a camera video recording and MP3 player not to forget the mobile web browsing.
David Luebke Modeling and Rendering Architecture from Photographs A hybrid geometry- and image-based approach Debevec, Taylor, and Malik SIGGRAPH.
Introduction to EBSCOhost E-Books Access to thousands of e-books! Available 24/7!
Your Mobile Engineer CAD, Image, Movie Viewer Markup, Voice, Photo Insert Multi-users online discussion Wireless data accessing.
DEMONSTRATION FOR SIGMA DATA ACQUISITION MODULES Tempatron Ltd Data Measurements Division Darwin Close Reading RG2 0TB UK T : +44 (0) F :
Yingen Xiong and Kari Pulli
© 2006 Palm, Inc. All worldwide rights reserved. Photos application Library.
Research Area B Leif Kobbelt. Communication System Interface Research Area B 2.
Description: iMotion HD is an intuitive and powerful time- lapse and stop-motion app for iOS. It allows you to easily make your own movie by taking photos.
MyiLibrary® ‘Search & View’ Website Training June 8, 2010.
Starter for 10 Unit 10: Flickr & YouTube Transform IT SFT10_Flickr_YouTube.
Graphics cards: A video card (also called a graphics card) is an expansion card which generates a feed of output images to a display. Most video cards.
Satellites in Our Pockets: An Object Positioning System using Smartphones Justin Manweiler, Puneet Jain, Romit Roy Choudhury TsungYun
-1- Pujol S et al. National Alliance for Medical Image Computing 3D Visualization of FreeSurfer Data Sonia Pujol, Ph.D. Silas Mann, B.Sc. Randy Gollub,
© 2006 Palm, Inc. All worldwide rights reserved. Media Library.
AMI GUI Design V1.1 by Kilian Pohl - Reflects changes in AMI MRML Structure - Includes feedback from AMI Workshop in Dec 09.
Sikuli Ivailo Dinkov QA Engineer PhoneX Team Telerik QA Academy.
Image processing Gladys Nzita-Mak. Input devices A mouse is used to interact with your computer, the user is able to move the mouse, click and select.
Adobe Bridge Image management system. Used by Photographers to…  Browse, view and organize photos  Import images and batch rename  Organize images.
Automatic Registration of Color Images to 3D Geometry Computer Graphics International 2009 Yunzhen Li and Kok-Lim Low School of Computing National University.
1 Preview At least two views are required to access the depth of a scene point and in turn to reconstruct scene structure Multiple views can be obtained.
December 2014 LCCU Meeting We’ll answers members’ questions: –How do you upload photos from a camera and organize them, using Windows, Photo Gallery, Picasa,
Operating Systems. Without an operating system your computer would be useless! A computer contains an Operating System on its Hard Drive. This is loaded.
Eng.Abed Al Ghani H. Abu Jabal Introduction to computers.
Section 4 & 5 Review Google Adwords.  Contextual Targeting.
HTML Comprehensive Concepts and Techniques Second Edition.
IIIT HYDERABAD Image-based walkthroughs from partial and incremental scene reconstructions Kumar Srijan Syed Ahsan Ishtiaque C. V. Jawahar Center for Visual.
3 Copyright © 2004, Oracle. All rights reserved. Working in the Forms Developer Environment.
Scene Reconstruction Seminar presented by Anton Jigalin Advanced Topics in Computer Vision ( )
112/5/ :54 Graphics II Image Based Rendering Session 11.
Chapter 1 Getting Started With Dreamweaver. Exploring the Dreamweaver Workspace The Dreamweaver workspace is where you can find all the tools to create.
Kirk Bishop. What is Photosynth? Photosynth is a software application that analyzes digital photographs to build a three-dimensional models.
CSE 140: Computer Vision Camillo J. Taylor Assistant Professor CIS Dept, UPenn.
Chapter 1 Getting Started with Adobe Photoshop CS4.
Exploring Microsoft Windows 8 Prepared by: Ms. Esraa AL Mousa.
Geometry-aware Feature Matching for Structure from Motion Applications Rajvi Shah, Vanshika Srivastava, P J Narayanan Center for Visual Information Technology.
Overview 3D Slicer currently provides very basic technology for annotating images. This limits users in their ability to properly capture semantic information.
How to Recover Deleted Photos from Android Cell Phone? Android is keeping on improving their products and make sure to provide the best software service.
Stellar Phoenix Photo Recovery Recover Photos, Audio & Videos.
Photo recovery from water damaged XD memory card recovery-from-water-damaged-xd-memory-card.
IIIT HYDERABAD Techniques for Organization and Visualization of Community Photo Collections Kumar Srijan Faculty Advisor : Dr. C.V. Jawahar.
DISCOVERING COMPUTERS 2018 Digital Technology, Data, and Devices
Windows 7 and file management
Heritage App: Annotating Images on Mobile Phones
Pilot Walktour Operation Guide V3.5 (Android)
Capturing, Processing and Experiencing Indian Monuments
Pilot Walktour Operation Guide V3.4 (Android)
OneDrive for Business User Guide
Modeling the world with photos
DSA Standby Player App Digital Signage for Android Phones and Tablets
Noah Snavely.
Lecture 15: Structure from motion
Presentation transcript:

IIIT Hyderabad Geometry Directed Browser for Personal Photographs Center for Visual Information Technology IIIT Hyderabad Aditya Deshpande, Siddharth Choudhary, P J Narayanan, Kaustav Kundu, Krishna Kumar Singh, Aditya Singh, Apurva Kumar

IIIT Hyderabad We use SfM and other 3D computer vision techniques to provide intuitive Geometry Directed Photo Browsing. Photo-Browsing Digital Photography - No hard copy - Capture photographs and relive later on display device Photo-Browsers are tools to view digital photographs. E.g. Windows Photo Viewer, iPhoto, FSpot, KSquirrel etc. Photo Browsing model has not evolved much.

IIIT Hyderabad Related Work Face Detection & Tagging on Social Networking Sites. [Zhang et al. MM03], Automatic annotation of family albums. [Davis et al. MM05], Additional contextual data viz. time of capture, geo-tag, indoor/outdoor scene, co-occurring faces. Above techniques only improve photo-browsing experience of social engagements.

IIIT Hyderabad Our Goal Apart from social engagements, a large chunk of users personal photographs consist of tourist places & monuments. [Snavely et al. IJCV08, SIGGRAPH06] (Photosynth) - CPC Storage, local reconstruction to add new cameras Choudhary et al., Li et al., Sattler et al., Irschara et al. etc. - Localize new query images w/o exhaustive search. We combine SfM-Reconstruction + Localization to provide intuitive browsing of user photos in 3D space of the monument.

IIIT Hyderabad Assumptions Our target platform is an off-the-shelf laptop or a desktop. User is expected to click around 5-50 photographs for a particular monument. The system should localize these user photographs in a reasonable time. The system should provide a smooth visualization / transitions of all user photos and ~10 5 points of the monument.

IIIT Hyderabad System Design (1) Heavy SfM Reconstruction done offline in the cloud (2) GDBPackage : reconstruction + addnl. information downloaded to local disk (3) User uploads personal photos through a camera / phone (4) System registers users photos to the point cloud and provides 3D visualization.

IIIT Hyderabad System Block Diagram GDBPackage User Photos Registration Module Visualization Module System is divided in two parts : 1. Registration / Localization Module 2. Visualization Module 2 1 Estimated Cameras

IIIT Hyderabad Localizing User Photos Trivial if photograph is taken from GPS enabled device and is geo-tagged! What if no geo-tag information? Two Localization Approaches : Image based search in a geo-tagged Image Dataset [Panda et al.] Geo-locate digital heritage site photos. Using structure information in SfM Dataset [Irschara et al. CVPR09], match to nearby similar images. [Li et al. ECCV10], visibility prioritized 3D-2D matches. [Sattler et al. ICCV11, ECCV12], visual words to find 2D-3D matches.

IIIT Hyderabad Localization - Choudhary et al. [Choudhary et al. ECCV12] - Triangulate a seed point in the user photograph. - Further 3D-2D search is guided by visibility probabilities. - Find ~20 independent matches. - Use RANSAC to estimate camera parameters. Probability Guided 3D-2D correspondence 3D Position Up Vector View Direction

IIIT Hyderabad Advantages of Localization Method Data for Localization is stored in GDBPackage : (1) Cover Set (2) Visibility Matrix (3) Bi-Partite Visibility Graph CPC images need not be stored, data requirements are minimal. The method is fast and localizes images at the rate of 1sec/photo.

IIIT Hyderabad Non-Localizable Photographs In some cases the images lack sufficient monument geometry for localization to work : - Occluded by people. - Noisy images of nearby scenery/smaller monuments. - Zoomed in images of smaller monument structures etc. Zoomed In View of Small Structure (Pantheon Dataset) Completely Occluded by People (Colosseum Dataset)

IIIT Hyderabad Non-Localizable Photographs Photographs have time of capture stored in their EXIF-tags. A non-localized image is placed at a position that is weighted average of its immediate known predecessor and immediate known successor in time. Similarly, linear interpolation is also done for the view-direction vector to get the complete camera pose. The above method will not give the exact location, but placing it in temporal neighborhood suffices for display purposes.

IIIT Hyderabad Visualization Module 3D Viewer Mouse Navigation Button Navigation Add Screenshot Delete Path Generate Photo- Tour 2D Viewer

IIIT Hyderabad 3D Photo Browser : Geometry Directed Photo-Browsing Initial Mode : 3D Model and small preview (thumbnails) of user photographs. Select Mode : Animate to clicked photo and detailed view. Linear quaternion interpolation of Rotation Matrix for smooth transitions between images. Smooth transitions give a feel of the geometric space of the monument.

IIIT Hyderabad 3D Photo Browser : Generating Custom Photo Tours User can save the current viewpoint (Add Screenshots) Once a set of viewpoints are saved, he can smoothly animate over viewpoints. (Generate Photo-Tour / Animate Path) User can delete the viewpoints and generate a new photo-tour. Photo-Tours are a good way to creatively view personal photos taken at a tourist place.

IIIT Hyderabad Results Monument# Photos# Registered Photos Reg. Time (secs per photo) Colosseum Colosseum Pantheon Stone Chariot (Hampi) (a) Localization Module (b) Visualization Module

IIIT Hyderabad Conclusion and Future Work Minimal System Requirements. Intuitive 3D Visualization of User Photographs. Pipeline for 3D personal photo-viewing from SfM reconstruction. Port our system to a mobile phone and have a touch/gesture interface. 3D Photo-Viewing & Localization App

IIIT Hyderabad Thank you. Questions? More Results (a) Hampi Dataset (Stone Chariot) (b) Pantheon Dataset

IIIT Hyderabad Platform Details ItemSpecification CPUIntel ® CORE i5 Clock Speed2.44GHZ RAM4GB GPUIntel ® HD Graphics Accelerator