3D Scene Segmentation and Reconstruction by DDMCMC
Experimental results on the three datasets:

Florida dataset 1

Florida dataset 2

Brown dataset

Recently there are renewed and growing interest in computer vision research for parsing and reconstructing 3D scenes from range images, driven by new developments in sensor technologies and new demands in applications. Firstly, high precision laser range cameras are becoming accessible to many users, which makes it possible to acquire complex real world scenes like the following ones: 

There are also high precision 3D Lidar images for terrain maps and city scenes with up to centimeter accuracy. Secondly, there are new applications in graphics and visualization, such as image based rendering and augmented reality, and in spatial information management, such as constructing spatial temporal databases of 3D urban and suburban maps. All these request the reconstruction of complex 3D scenes, for which range data are much more accurate than other depth cues such as shading and stereo. Thirdly, Range data are also needed in studying the statistics of natural scenes  for the purposes of learning realistic prior models for real world imagery as well as for understanding the ecologic influences of the environment on biologic vision systems. For example, a prior model of 3D scenes is useful for many 3D reconstruction methods, such as multi-view stereo, space carving, shape recovery from occlusion, and so on.

In contrast to the new development and applications, current range image segmentation algorithms are mostly motivated by traditional applications in recognizing industry parts in an assembly line. Therefore these algorithms only deal with polyhedra scenes. In this project, we aim to segment and reconstruct all kinds of 3D scenes from laser range images and their associated reflectance maps.                                                                                                      

F. Han, Z. W. Tu, and S.C. Zhu,     "A  Stochastic Algorithm for Parsing and Reconstructing 3D Scenes"
 Proc. of 7th European Conference on Computer Vision, Copenhagen, Demark, 2002