Robust reconstruction of watertight 3D models from non-uniformly sampled point clouds without normal information

210 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Multi-View Stereo: A Tutorial (2015, methodology): “There also exist methods to reconstruct a mesh from unoriented point cloud, and hence, unsigned distance functions [103, 29].”
A Globally Optimal Algorithm for Robust TV-L1 Range Image Integration (2007, background): “crust voxels in [17]) offers a solution in this case.”
Global Optimization for Shape Fitting (2007, result): “Our results for sparse or incomplete 3D data from laser scanning and passive multi-view stereo are robust to noise, outliers, missing parts, and varying sampling density.”
Voronoi-based variational reconstruction of unoriented point sets (2007, unknown): “Given this intrinsic difficulty, recent work has polarized on handling raw, unoriented point sets without attempting to locally estimate or orient the normals (e.g., [KSO04,WCS05, HK06 ,PSQ06]).”
A Survey of Surface Reconstruction from Point Clouds (2017, unknown): “A limitation of [HK06] is that source/sink nodes are speciﬁed by ﬁrst deﬁning a small crust on the exterior and interior through a dilation operation on point-occupied voxels, where the crust must reﬂect the topology of the shape for the graph cut to produce a topologically-correct surface.”