Logo


CaS: Collection-aware Segmentation
This research work aims an algorithm for object decomposition that takes into account the context where the object lay. Unlike most approaches to 3D model segmentation, which decomposes objects independently of the collection it belongs, the Collection-aware Segmentation (CaS) approach performs the decomposition in objects considering the details that distinguishes it from others in the collection. The final result will consist on decomposing objects into sets of segments relevant to describe it, with respect to the collection.

Overview
Download
  Win32 binary [ZIP 10.8 MB]
 
Usage
CASdecomposer [options] <source> [<decomposition-file>]
Options:
--help,  -h   Show Help
--gpl, -gpl  Print the GNU GPL
--quiet, -q Quiet processing
--shows, -s Shows time or not
--stl Read STL files
--off Read OFF files
--dae Produce DAE files with decomposed models
--vrml Produce VRML files with decomposed models
--vrml-node Produce VRML files with segments of the decomposed models
--no-axis Indicates that VRML models do not include coordinate axis
--no-signatures No ASCII signatures should be written
--keep-intermediate Indicates that intermediate files will be kept
--shape-pool Indicates if it is to use the predefined shape pool

Notice
If you find this tool useful, discover any bug or have any suggestions, feel free to contact us by


Funded by:


European Union — Structural Funds

FCT


Portuguese Republic