Microsoft Photosynth
Encyclopedia
Photosynth is a software application from Microsoft Live Labs
and the University of Washington
that analyzes digital photographs and generates a three-dimensional
model of the photos and a point cloud
of a photographed object. Pattern recognition components compare portions of images to create points, which are then compared to convert the image into a model. Users are able to view and generate their own models using a software tool available for download at the Photosynth website.
in early 2006, that team began work on Photosynth, under the direction of Seadragon founder Blaise Aguera y Arcas
.
Microsoft released a free tech preview version on November 9, 2006. Users could view models generated by Microsoft or the BBC
, but not create their own models at that time. Microsoft teamed up with NASA
on August 6, 2007 allowing users to preview its Photosynth technology showing the Space Shuttle Endeavour
. On August 20, 2007, a preview showing the tiles of Endeavour during the backflip process was made available for viewing.
On August 20, 2008, Microsoft officially released Photosynth to the public, allowing users to upload their images and generate their own Photosynth models.
In March 2010, Photosynth added support for Gigapixel panoramas
stitched in Microsoft ICE. The panoramas use Seadragon
based technology similar to the system already used in synths.
and matching algorithm developed by Microsoft Research
which is similar in function to UBC
's Scale-invariant feature transform
. This process identifies specific features, for example the corner of a window frame or a door handle. Features in one photograph are then compared to and matched with the same features in the other photographs. Thus photographs of the same areas are identified. By analyzing the position of matching features within each photograph, the program can identify which photographs belong on which side of others. By analyzing subtle differences in the relationships between the features (angle, distance, etc.), the program identifies the 3D position of each feature, as well as the position and angle at which each photograph was taken. This process is known scientifically as Bundle adjustment
and is commonly used in the field of photogrammetry
, with similar products available such as Imodeller and D-Sculptor. This first step is extremely computationally intensive, but only has to be performed once on each set of photographs.
The second step involves the display of and navigation through the 3D point cloud of features identified in the first step. This is done with the publicly downloadable Photosynth viewer. The viewer resides on a client computer and maintains a connection to a server that stores the original photographs. It enables a user to, among other things, see any of the photographs from their original vantage point. It incorporates DeepZoom technology Microsoft obtained through its acquisition of Seadragon in January 2006. The Seadragon
technology enables smooth zooming into the high-resolution photographs without downloading them to the user's machine.
The Photosynth Direct 3D-based viewing software is only available to the Windows 7, Windows Vista
and Windows XP
operating systems. However, the team released a Silverlight version of the viewer which has succeeded the D3D viewer as the main option to view photosynths.
As of March 2009 user uploaded Photosynth collections are now available for viewing on iPhone
s using iSynth (3D) or Seadragon Mobile (2D only).
and then upload them on the online Photosynth web service. Images uploaded on Photosynth give people the ability to seamlessly view landmarks, public spaces and objects from all sides.
Microsoft Live Labs
Microsoft Live Labs was a partnership between MSN and Microsoft Research that focused on applied research for Internet products and services at Microsoft. Live Labs was headed by Dr...
and the University of Washington
University of Washington
University of Washington is a public research university, founded in 1861 in Seattle, Washington, United States. The UW is the largest university in the Northwest and the oldest public university on the West Coast. The university has three campuses, with its largest campus in the University...
that analyzes digital photographs and generates a three-dimensional
Three-dimensional space
Three-dimensional space is a geometric 3-parameters model of the physical universe in which we live. These three dimensions are commonly called length, width, and depth , although any three directions can be chosen, provided that they do not lie in the same plane.In physics and mathematics, a...
model of the photos and a point cloud
Point cloud
A point cloud is a set of vertices in a three-dimensional coordinate system. These vertices are usually defined by X, Y, and Z coordinates, and typically are intended to be representative of the external surface of an object....
of a photographed object. Pattern recognition components compare portions of images to create points, which are then compared to convert the image into a model. Users are able to view and generate their own models using a software tool available for download at the Photosynth website.
History
Photosynth is based on Photo Tourism, a research project by University of Washington graduate student Noah Snavely. Shortly after Microsoft's acquisition of SeadragonSeadragon Software
Seadragon was a team within the Microsoft Live Labs. Seadragon is a web optimized visualization technology that allows graphics and photos to be smoothly browsed, regardless of their size...
in early 2006, that team began work on Photosynth, under the direction of Seadragon founder Blaise Aguera y Arcas
Blaise Agüera y Arcas
Blaise Agüera y Arcas is a software architect, designer, and imagery expert. As of 2010, he is the architect of Bing Maps and Bing Mobile.He founded Seadragon Software in 2003, which was acquired by Microsoft Live Labs in 2006...
.
Microsoft released a free tech preview version on November 9, 2006. Users could view models generated by Microsoft or the BBC
BBC
The British Broadcasting Corporation is a British public service broadcaster. Its headquarters is at Broadcasting House in the City of Westminster, London. It is the largest broadcaster in the world, with about 23,000 staff...
, but not create their own models at that time. Microsoft teamed up with NASA
NASA
The National Aeronautics and Space Administration is the agency of the United States government that is responsible for the nation's civilian space program and for aeronautics and aerospace research...
on August 6, 2007 allowing users to preview its Photosynth technology showing the Space Shuttle Endeavour
Space Shuttle Endeavour
Space Shuttle Endeavour is one of the retired orbiters of the Space Shuttle program of NASA, the space agency of the United States. Endeavour was the fifth and final spaceworthy NASA space shuttle to be built, constructed as a replacement for Challenger...
. On August 20, 2007, a preview showing the tiles of Endeavour during the backflip process was made available for viewing.
On August 20, 2008, Microsoft officially released Photosynth to the public, allowing users to upload their images and generate their own Photosynth models.
In March 2010, Photosynth added support for Gigapixel panoramas
Panorama
A panorama is any wide-angle view or representation of a physical space, whether in painting, drawing, photography, film/video, or a three-dimensional model....
stitched in Microsoft ICE. The panoramas use Seadragon
Seadragon Software
Seadragon was a team within the Microsoft Live Labs. Seadragon is a web optimized visualization technology that allows graphics and photos to be smoothly browsed, regardless of their size...
based technology similar to the system already used in synths.
Process
The Photosynth technology works in two steps. The first step involves the analysis of multiple photographs taken of the same area. Each photograph is processed using an interest point detectionInterest point detection
Interest point detection is a recent terminology in computer vision that refers to the detection of interest points for subsequent processing...
and matching algorithm developed by Microsoft Research
Microsoft Research
Microsoft Research is the research division of Microsoft created in 1991 for developing various computer science ideas and integrating them into Microsoft products. It currently employs Turing Award winners C.A.R. Hoare, Butler Lampson, and Charles P...
which is similar in function to UBC
University of British Columbia
The University of British Columbia is a public research university. UBC’s two main campuses are situated in Vancouver and in Kelowna in the Okanagan Valley...
's Scale-invariant feature transform
Scale-invariant feature transform
Scale-invariant feature transform is an algorithm in computer vision to detect and describe local features in images. The algorithm was published by David Lowe in 1999....
. This process identifies specific features, for example the corner of a window frame or a door handle. Features in one photograph are then compared to and matched with the same features in the other photographs. Thus photographs of the same areas are identified. By analyzing the position of matching features within each photograph, the program can identify which photographs belong on which side of others. By analyzing subtle differences in the relationships between the features (angle, distance, etc.), the program identifies the 3D position of each feature, as well as the position and angle at which each photograph was taken. This process is known scientifically as Bundle adjustment
Bundle adjustment
Given a set of images depicting a number of 3D points from different viewpoints, bundle adjustment can be defined as the problem of simultaneously refining the 3D coordinates describing the scene geometry as well as the parameters of the relative motion and the optical characteristics of the camera...
and is commonly used in the field of photogrammetry
Photogrammetry
Photogrammetry is the practice of determining the geometric properties of objects from photographic images. Photogrammetry is as old as modern photography and can be dated to the mid-nineteenth century....
, with similar products available such as Imodeller and D-Sculptor. This first step is extremely computationally intensive, but only has to be performed once on each set of photographs.
The second step involves the display of and navigation through the 3D point cloud of features identified in the first step. This is done with the publicly downloadable Photosynth viewer. The viewer resides on a client computer and maintains a connection to a server that stores the original photographs. It enables a user to, among other things, see any of the photographs from their original vantage point. It incorporates DeepZoom technology Microsoft obtained through its acquisition of Seadragon in January 2006. The Seadragon
Seadragon Software
Seadragon was a team within the Microsoft Live Labs. Seadragon is a web optimized visualization technology that allows graphics and photos to be smoothly browsed, regardless of their size...
technology enables smooth zooming into the high-resolution photographs without downloading them to the user's machine.
The Photosynth Direct 3D-based viewing software is only available to the Windows 7, Windows Vista
Windows Vista
Windows Vista is an operating system released in several variations developed by Microsoft for use on personal computers, including home and business desktops, laptops, tablet PCs, and media center PCs...
and Windows XP
Windows XP
Windows XP is an operating system produced by Microsoft for use on personal computers, including home and business desktops, laptops and media centers. First released to computer manufacturers on August 24, 2001, it is the second most popular version of Windows, based on installed user base...
operating systems. However, the team released a Silverlight version of the viewer which has succeeded the D3D viewer as the main option to view photosynths.
As of March 2009 user uploaded Photosynth collections are now available for viewing on iPhone
IPhone
The iPhone is a line of Internet and multimedia-enabled smartphones marketed by Apple Inc. The first iPhone was unveiled by Steve Jobs, then CEO of Apple, on January 9, 2007, and released on June 29, 2007...
s using iSynth (3D) or Seadragon Mobile (2D only).
Capabilities
Current generation photosynths are easy to capture, as photographs uploaded on Photosynth can be taken by any regular digital camera or mobile phone. In general, the higher the megapixels, the clearer the pictures. Users have the option to geotag their digital shots on sites such as FlickrFlickr
Flickr is an image hosting and video hosting website, web services suite, and online community that was created by Ludicorp in 2004 and acquired by Yahoo! in 2005. In addition to being a popular website for users to share and embed personal photographs, the service is widely used by bloggers to...
and then upload them on the online Photosynth web service. Images uploaded on Photosynth give people the ability to seamlessly view landmarks, public spaces and objects from all sides.
- Walk or fly through a scene to see photos from any angle
- Zoom in or out of a photo
- See where pictures were taken in relation to one another
- Smoothly change viewing angle between nearby photos
- Smoothly zoom in and out of high-resolution photos
- Find similar photos to the one you're currently viewing
In the media
- On April 30, 2008, Photosynth was featured in the episode Admissions of the television show CSI: New York
- CNNCNNCable News Network is a U.S. cable news channel founded in 1980 by Ted Turner. Upon its launch, CNN was the first channel to provide 24-hour television news coverage, and the first all-news television channel in the United States...
utilized Photosynth for a user-contributed 3D vision of the inauguration of Barack Obama as the President of the United States. - In the Angels & Demons "Path of Illumination Contest," Photosynth is used as well as advertised in the website.
- In MSNMSNMSN is a collection of Internet sites and services provided by Microsoft. The Microsoft Network debuted as an online service and Internet service provider on August 24, 1995, to coincide with the release of the Windows 95 operating system.The range of services offered by MSN has changed since its...
's coverage of the 70th anniversary of the RAF victory in the Battle of BritainBattle of BritainThe Battle of Britain is the name given to the World War II air campaign waged by the German Air Force against the United Kingdom during the summer and autumn of 1940...
, a Photosynth hangar of some of the fighter planes from the battle was built. A series of Photosynths have also been created for the Imperial War Museum DuxfordImperial War Museum DuxfordImperial War Museum Duxford is a branch of the Imperial War Museum near the village of Duxford in Cambridgeshire, England. Britain's largest aviation museum, Duxford houses the museum's large exhibits, including nearly 200 aircraft, military vehicles, artillery and minor naval vessels in seven...
so that web users could experience the planes up close from a range of angles.
See also
- Microsoft Image Composite Editor, a free advanced panorama stitching system;
- SeadragonSeadragon SoftwareSeadragon was a team within the Microsoft Live Labs. Seadragon is a web optimized visualization technology that allows graphics and photos to be smoothly browsed, regardless of their size...
- Hugin (software)Hugin (software)Hugin is a cross-platform open source panorama photo stitching and HDR merging program developed by Pablo d'Angelo and others. It is a GUI front-end for Helmut Dersch's Panorama Tools and Andrew Mihal's Enblend and Enfuse...
, a cross-platform open source panorama stitching system; - QuickTime VRQuickTime VRQuickTime VR is a type of image file format developed by Apple Inc. for QuickTime. It allows the creation and viewing of photographically-captured panoramas and the exploration of objects through images taken at multiple viewing angles...
- MeshLabMeshLabMeshLab, is a free 3D mesh processing software program; MeshLab, started in late 2005, is an open-source general-purpose system aimed to help the processing of the typical not-so-small unstructured 3D models that arise in the pipeline of processing of the data coming from 3D scanning...
, a cross-platform open source mesh processing tool that allow to import the point cloudsPoint cloudA point cloud is a set of vertices in a three-dimensional coordinate system. These vertices are usually defined by X, Y, and Z coordinates, and typically are intended to be representative of the external surface of an object....
reconstructed by PhotoSynth; - Bundler, an open-source implementation of the algorithms behind Photosynth
- PixelStruct, an open-source program similar to Photosynth that uses Bundler as a base