{"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/density-adaptive-point-set-registration","title":"Density Adaptive Point Set Registration","arxiv_id":"1804.01495","date":"2018-04-04","proceeding":"CVPR 2018 6","authors":["Felix Järemo Lawin","Martin Danelljan","Fahad Shahbaz Khan","Per-Erik Forssén","Michael Felsberg"],"abstract":"Probabilistic methods for point set registration have demonstrated\ncompetitive results in recent years. These techniques estimate a probability\ndistribution model of the point clouds. While such a representation has shown\npromise, it is highly sensitive to variations in the density of 3D points. This\nfundamental problem is primarily caused by changes in the sensor location\nacross point sets. We revisit the foundations of the probabilistic registration\nparadigm. Contrary to previous works, we model the underlying structure of the\nscene as a latent probability distribution, and thereby induce invariance to\npoint set density changes. Both the probabilistic model of the scene and the\nregistration parameters are inferred by minimizing the Kullback-Leibler\ndivergence in an Expectation Maximization based framework. Our density-adaptive\nregistration successfully handles severe density variations commonly\nencountered in terrestrial Lidar applications. We perform extensive experiments\non several challenging real-world Lidar datasets. The results demonstrate that\nour approach outperforms state-of-the-art probabilistic methods for multi-view\nregistration, without the need of re-sampling. Code is available at\nhttps://github.com/felja633/DARE.","url_abs":"http://arxiv.org/abs/1804.01495v2","url_pdf":"http://arxiv.org/pdf/1804.01495v2.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":"density-adaptive-point-set-registration","repo_url":"https://github.com/felja633/DARE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.01495","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}