onders@raphael.ipl.rpi.edu (Timothy E. Onders) (03/26/91)
A couple of years ago, there was an article on Nova(on PBS), about research somewhere on converting a series of two dimensional images to a three dimensional representation. The example given was panning a camera past a model of a town and generating the 3D image from that. If anyone has any information on this, or similar work, please tell me. Thank You, Tim Onders onders@ipl.rpi.edu
grendel@opos.arc.nasa.gov (That monstrous man-eating descendant of Cain) (03/26/91)
In article <5d6f84k@rpi.edu>, onders@raphael.ipl.rpi.edu (Timothy E. Onders) writes: |> A couple of years ago, there was an article on Nova(on PBS), about research |> somewhere on converting a series of two dimensional images to a three |> dimensional representation. The example given was panning a camera past |> a model of a town and generating the 3D image from that. |> |> If anyone has any information on this, or similar work, please |> tell me. |> Thank You, |> Tim Onders |> onders@ipl.rpi.edu See published works by Takeo Kanade at Carnegie Mellon from the Robotics Center. -- Ray Suorsa, grendel@opos.arc.nasa.gov, NASA Ames Research Center,USA (415) 604-6334, Fax x3950
twriter@ohrd.uucp (Timothy Writer KR186_x6990) (04/10/91)
In article <5d6f84k@rpi.edu> onders@raphael.ipl.rpi.edu (Timothy E. Onders) writes: >A couple of years ago, there was an article on Nova(on PBS), about research >somewhere on converting a series of two dimensional images to a three >dimensional representation. The example given was panning a camera past >a model of a town and generating the 3D image from that. > > If anyone has any information on this, or similar work, please >tell me. I saw a paper in the Proceedings of the '91 International Symposium on Advanced Robot Technology ('91 ISART) held in Tokyo in early March where the authors did exactly what you ask in a nuclear power plant. I don't recall the title or the authors but if you get yourself a copy of the proceedings you should be able to find it. Tim
jet@karazm.math.uh.edu ("J. Eric Townsend") (04/10/91)
In article <5d6f84k@rpi.edu> onders@raphael.ipl.rpi.edu (Timothy E. Onders) writes: >A couple of years ago, there was an article on Nova(on PBS), about research >somewhere on converting a series of two dimensional images to a three >dimensional representation. The example given was panning a camera past >a model of a town and generating the 3D image from that. A little off the subject, perhaps, but there are a couple of programs for the Amiga that "auto-trace" 2D objects to generate a polygonal based object. From this, it's quite trivial to extend the object into 3D in most of the popular 3D rendering/raytracing Amiga programs. -- J. Eric Townsend - jet@uh.edu - bitnet: jet@UHOU - vox: (713) 749-2120 Skate UNIX or bleed, boyo... (UNIX is a trademark of Unix Systems Laboratories).
mccool@dgp.toronto.edu (Michael McCool) (04/12/91)
>In article <5d6f84k@rpi.edu> onders@raphael.ipl.rpi.edu (Timothy E. Onders) writes: >>A couple of years ago, there was an article on Nova(on PBS), about research >>somewhere on converting a series of two dimensional images to a three >>dimensional representation. The example given was panning a camera past >>a model of a town and generating the 3D image from that. I think what you are looking for is optical flow, which can convert a sequence of images into a depth map. Jepson here at the University of Toronto has done some work in this area. Note that this does not give you a 3D representation, but only a depth map (this might be alright for displacement maps, etc. though). Deriving a full 3D representation is basically the full vision problem, which is NP-hairy. Michael McCool@dgp.utoronto.ca, Dynamic Graphics Project, University of Toronto.