Complex and photo-realistic scene representation based on range planar segmentation and model fusion

Abstract

We present an efficient 3D scene representation method from a set of 3D range scans captured from a large-scale indoor or outdoor scene based on range planar segmentation and model fusion. In our method, range images are partitioned into planar patches and non-planar regions. We first partition the range image into a set of rectangle blocks and fit a planar patch to all points of each block. Blocks that are not successfully fitted as planar patches, are iteratively partitioned into sub-blocks until reaching a minimum size. Second, we iteratively merge the planar patches and identify unclassified rectangle blocks or points. The segmentation is then refined by relabelling the boundary points of fitted planar patches with respect to the neighbouring planar patches. We further simplify the scene model representation by fusing range scans and welding neighbouring planar patches with clean straight boundaries. An efficient texture mapping approach is proposed to automatically map the reflectance/colour images onto the fused scene model composed of a set of planar patches. Finally we successfully demonstrate the performance of our algorithms on several challenging range data sets.