Research Institute of Visual Computing

Select a project of interest using the advanced search:

MRF Labeling for Multi-View Range Image Integration

Authors: Ran Song1, Yonghuai Liu1, Ralph R. Martin2, and Paul L. Rosin2

DOI: 10.1007/978-3-642-19309-5_3

Abstract:

Multi-view range image integration focuses on producing a single reasonable 3D point cloud from multiple 2.5D range images for the reconstruction of a watertight manifold surface. However, registration errors and scanning noise usually lead to a poor integration and, as a result, the reconstructed surface cannot have topology and geometry consistent with the data source. This paper proposes a novel method cast in the framework of Markov random elds (MRF) to address the problem. We de ne a probabilistic description of a MRF labeling based on all input range images and then employ loopy belief propagation to solve this MRF, leading to a globally optimised integration with accurate local details. Experiments show the advantages and superiority of our MRF-based approach over existing methods.

Link to Paper

Authors

Dr Ran Song

Dr Ran Song

Shape analysis; Mesh saliency; Multi-view surface reconstruction

Dr Yonghuai Liu

Dr Yonghuai Liu

3D imaging, analysis and applications

Prof. Ralph Martin

Prof. Ralph Martin

Polygon mesh processing including registration, noise removal, segmentation and surface fitting.

Prof. Paul Rosin

Prof. Paul Rosin

Various aspects of computer vision, including 2D and 3D facial analysis and synthesis.