Last update: Sept. 10, 2000

F.Leymarie et al., «REALISE: Reconstruction of Reality from Images Sequences», Proc. of IEEE «International Conference on Image Processing» (ICIP'96), Vol.III, pp.651-654, P.Delogne ed., Lausanne, Switzerland, Sept. 1996.

REALISE has for principal goals to extract from sequences of images, acquired with a moving camera, information necessary for determining the 3D (CAD-like) structure of a real-life scene together with information about the radiometric signatures of surfaces bounding the extracted 3D objects (e.g. reflectance behaviour). The retrieved information is then integrated in a Virtual Reality (VR) software environment. R&D work is been performed principally in the following areas of Computer Vision & Computer Graphics: structure from motion, recovery of geometries, recovery of photometric and texture information, highly realistic rendering on the basis of empirically-based reflectance models, design and development of improved rendering processes together with a new VR system. Beside this innovative R&D work another key aspect of REALISE is to have Computer Vision & Computer Graphics cooperate to produce realistic 3D data efficiently.

For an HTML (and updated) version of the paper : click here

For an RTF version of the paper as it appears in the Proceedings : click here
(compressed with gzip : 750K).

Test Sequences for Realise.

TotalCalib: a semi-automatic tool for calibrating image sequences.

3D Modeling from images: a java-based interface allowing you to build on-line 3D models from calibrated image sequences.

CUReT: a database of empirical BRDFs (Bidirectional Reflectance Distribution Functions) and associated photo-textures.

• REALviZ: http://www.realviz.com/

• SKOL: http://www.skolsoft.de/

Page created & maintained by Frederic Leymarie, 1998-2000.
Comments, suggestions, etc., mail to: leymarie@lems.brown.edu