{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/shape-aware-surface-reconstruction-from","title":"Shape-aware Surface Reconstruction from Sparse 3D Point-Clouds","arxiv_id":"1602.08425","date":"2016-02-26","proceeding":null,"authors":["Florian Bernard","Luis Salamanca","Johan Thunberg","Alexander Tack","Dennis Jentsch","Hans Lamecker","Stefan Zachow","Frank Hertel","Jorge Goncalves","Peter Gemmar"],"abstract":"The reconstruction of an object's shape or surface from a set of 3D points\nplays an important role in medical image analysis, e.g. in anatomy\nreconstruction from tomographic measurements or in the process of aligning\nintra-operative navigation and preoperative planning data. In such scenarios,\none usually has to deal with sparse data, which significantly aggravates the\nproblem of reconstruction. However, medical applications often provide\ncontextual information about the 3D point data that allow to incorporate prior\nknowledge about the shape that is to be reconstructed. To this end, we propose\nthe use of a statistical shape model (SSM) as a prior for surface\nreconstruction. The SSM is represented by a point distribution model (PDM),\nwhich is associated with a surface mesh. Using the shape distribution that is\nmodelled by the PDM, we formulate the problem of surface reconstruction from a\nprobabilistic perspective based on a Gaussian Mixture Model (GMM). In order to\ndo so, the given points are interpreted as samples of the GMM. By using mixture\ncomponents with anisotropic covariances that are \"oriented\" according to the\nsurface normals at the PDM points, a surface-based fitting is accomplished.\nEstimating the parameters of the GMM in a maximum a posteriori manner yields\nthe reconstruction of the surface from the given data points. We compare our\nmethod to the extensively used Iterative Closest Points method on several\ndifferent anatomical datasets/SSMs (brain, femur, tibia, hip, liver) and\ndemonstrate superior accuracy and robustness on sparse data.","url_abs":"http://arxiv.org/abs/1602.08425v2","url_pdf":"http://arxiv.org/pdf/1602.08425v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"shape-aware-surface-reconstruction-from","repo_url":"https://github.com/fbernardpi/sparsePdmFitting","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"anatomy","task_name":"Anatomy"},{"task_slug":"medical-image-analysis","task_name":"Medical Image Analysis"},{"task_slug":"surface-reconstruction","task_name":"Surface Reconstruction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}