Abstract | ||
---|---|---|
•A surface reconstruction method from sparse data is proposed.•A statistical shape model is used as prior to compensate missing data.•The problem is formulated probabilistically using Gaussian Mixture Models (GMM).•Anisotropic covariances “oriented” by surface normals achieve a surface-based fitting.•A fast approximation having the same complexity as isotropic GMMs is proposed. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1016/j.media.2017.02.005 | Medical Image Analysis |
Keywords | Field | DocType |
Sparse shape reconstruction,Statistical shape model,Point distribution model,Gaussian mixture model,Expected conditional maximisation | Data point,Point distribution model,Active shape model,Surface reconstruction,Pattern recognition,Artificial intelligence,Maximum a posteriori estimation,Point cloud,Sparse matrix,Mixture model,Mathematics | Journal |
Volume | ISSN | Citations |
38 | 1361-8415 | 6 |
PageRank | References | Authors |
0.45 | 47 | 10 |
Name | Order | Citations | PageRank |
---|---|---|---|
Florian Bernard | 1 | 118 | 14.54 |
Luis Salamanca | 2 | 28 | 5.63 |
Johan Thunberg | 3 | 138 | 19.15 |
Alexander Tack | 4 | 6 | 0.79 |
Dennis Jentsch | 5 | 6 | 0.45 |
Hans Lamecker | 6 | 492 | 35.13 |
Stefan Zachow | 7 | 120 | 24.80 |
Frank Hertel | 8 | 26 | 4.19 |
Goncalves, J. | 9 | 404 | 42.24 |
Peter Gemmar | 10 | 30 | 5.54 |