{"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/dugma-dynamic-uncertainty-based-gaussian","title":"DUGMA: Dynamic Uncertainty-Based Gaussian Mixture Alignment","arxiv_id":"1803.07426","date":"2018-03-18","proceeding":null,"authors":["Can Pu","Nanbo Li","Radim Tylecek","Robert B. Fisher"],"abstract":"Registering accurately point clouds from a cheap low-resolution sensor is a\nchallenging task. Existing rigid registration methods failed to use the\nphysical 3D uncertainty distribution of each point from a real sensor in the\ndynamic alignment process mainly because the uncertainty model for a point is\nstatic and invariant and it is hard to describe the change of these physical\nuncertainty models in the registration process. Additionally, the existing\nGaussian mixture alignment architecture cannot be efficiently implement these\ndynamic changes.\n  This paper proposes a simple architecture combining error estimation from\nsample covariances and dual dynamic global probability alignment using the\nconvolution of uncertainty-based Gaussian Mixture Models (GMM) from point\nclouds. Firstly, we propose an efficient way to describe the change of each 3D\nuncertainty model, which represents the structure of the point cloud much\nbetter. Unlike the invariant GMM (representing a fixed point cloud) in\ntraditional Gaussian mixture alignment, we use two uncertainty-based GMMs that\nchange and interact with each other in each iteration. In order to have a wider\nbasin of convergence than other local algorithms, we design a more robust\nenergy function by convolving efficiently the two GMMs over the whole 3D space.\n  Tens of thousands of trials have been conducted on hundreds of models from\nmultiple datasets to demonstrate the proposed method's superior performance\ncompared with the current state-of-the-art methods. The new dataset and code is\navailable from https://github.com/Canpu999","url_abs":"http://arxiv.org/abs/1803.07426v2","url_pdf":"http://arxiv.org/pdf/1803.07426v2.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":"dugma-dynamic-uncertainty-based-gaussian","repo_url":"https://github.com/Canpu999/DUGMA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"dugma-dynamic-uncertainty-based-gaussian","repo_url":"https://github.com/Canpu999/Robust-Rigid-Point-Registration","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}