AutoStitch: Panoramic Image Stitching


autostitch

What if your camera could see everything you can see?

The human visual system has a field of view of around 135 x 200 degrees, but a typical camera has a field of view of only 35 x 50 degrees. Panoramic image mosaicing works by taking lots of pictures from an ordinary camera, and stitching them together to form a composite image with a much larger field of view.
AutoStitch takes a step forward in panoramic image stitching by automatically recognising matching images. This allows entire panoramas to be constructed with no user input whatsoever. AutoStitch is incredibly simple to use! Just select a set of photos, and AutoStitch does the rest: digital photos in, panoramas out.
Mobile versions are no longer available, sorry! Please try the free demo instead

Download the free demo version for Windows

Note: the MacOS version is broken in Ventura/Sonoma so we are not distributing it here anymore.
If you have an old version it can still be run from the command line, e.g., cd /Applications/AutoStitch.app/Contents/MacOS; ./AutoStitch
32-bit Windows users here is the older Win32 demo version.

The AutoStitch Process

AutoStitch works from unordered collections of images, automatically finding matches between images using the SIFT algorithm. It then robustly aligns all images and uses advanced blending algorithms to form seamless panoramas (see below). For more details, see our research papers.
25 of 57 images aligned
All 57 images aligned
Final result


Publications

Automatic Panoramic Image Stitching using Invariant Features, Matthew Brown and David Lowe, IJCV 2007, pdf

Recognising Panoramas, Matthew Brown and David Lowe, ICCV 2003, pdf


Software

AutoStitch was licensed by the University of British Columbia to multiple companies including ILM and it appeared in several commercial products including Autopano Pro and Serif PanoramaPlus.

In 2004 and 2006-7 I worked with Rick Szeliski's group at Microsoft Research where we developed several related technologcial improvements, notably learned image descriptors. This contributed to several products including Photosynth and MSR Image Composite Editor. After my first internship an early version of Microsoft's Stitcher was demonstrated on CNN by Bill Gates.

In 2009 I founded Cloudburst Research Inc together with David Lowe and Bob Hearn. Cloudburst developed mobile versions of AutoStitch for iPhone, iPad and Android, which were very popular in the early 2010s.