Gigapixel stitching software

I have been looking for some support for an image stitcher that will take many digital pictures taken one after another in rows and columns and stitch them together to make a very large seamless picture much like how photoshop cs4’s photomerge does, or autopano or ptgui. however these are all processor bound and while they do utilize multiple cores it takes a whole day to compile and blend a gigapixel image together; and as my photos become larger and larger it just takes too much time. I feel this would be a GREAT example to show the power of CUDA and gpu processors.

Does anybody know of an application that would take advantage of my GPU or a TESLA processor to stitch photos together in a reasonable amount of time? photoshop cs4 does a great job with stitching and blending a seemless picture automatically, is there a way to add support for tesla to this application? or maybe to one of the others i mentioned.

Thank You very much for any help or comments.

On 12/25, 2009, the following CUDA GPU-accelerated panorama stitching software showed up:

What is PTStitcherNG ?

PTStitcherNG reads and transforms any number and type of input images, and combines them into one seamless panoramic image with larger field-of-view. Given enough input images, full spherical 360x180 degree views can be synthesized suitable for virtual-reality viewers or printing.
Transformation parameters and names of the input images are read from a plain-text projectfile. The transformations consist of correcting distortions due to camera lenses, perspective tranlation and remapping to any of the usual panorama projections. Merging employs an eight level multiresolution algorithm which hides seams even if the source images fit badly. PTStitcherNG natively reads PPM, TIFF and JPEG images, and almost any raw or other format through plug-ins.

PTStitcherNG combines a panorama stitcher and multiresolution blender in one application. It is optimized for speed by using parallel processing (SIMD-instructions, multiple processor cores). The main novel feature is the tight coupling of the remapper and blender, with an optimized management of temporary data. This enables PTStitcherNG to keep all intermediate data and processed images in ram (in the case of the CUDA-version: in
gpu-ram) even when stitching hundreds of images to gigapixel sized panoramas. As a result, no data have to be written to disk, or reread from disk with corresponding speed improvements. As an aside, this makes PTStitcherNG perform fast even on low profile host systems: E.g. the 2.1s result mentioned above is obtained on a single-core Celeron system.

PTStitcherNG is free software. No license is required to download and use it.

More info and download at http://www.fh-furtwangen.de/~dersch