{"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/regnet-multimodal-sensor-registration-using","title":"RegNet: Multimodal Sensor Registration Using Deep Neural Networks","arxiv_id":"1707.03167","date":"2017-07-11","proceeding":null,"authors":["Nick Schneider","Florian Piewak","Christoph Stiller","Uwe Franke"],"abstract":"In this paper, we present RegNet, the first deep convolutional neural network\n(CNN) to infer a 6 degrees of freedom (DOF) extrinsic calibration between\nmultimodal sensors, exemplified using a scanning LiDAR and a monocular camera.\nCompared to existing approaches, RegNet casts all three conventional\ncalibration steps (feature extraction, feature matching and global regression)\ninto a single real-time capable CNN. Our method does not require any human\ninteraction and bridges the gap between classical offline and target-less\nonline calibration approaches as it provides both a stable initial estimation\nas well as a continuous online correction of the extrinsic parameters. During\ntraining we randomly decalibrate our system in order to train RegNet to infer\nthe correspondence between projected depth measurements and RGB image and\nfinally regress the extrinsic calibration. Additionally, with an iterative\nexecution of multiple CNNs, that are trained on different magnitudes of\ndecalibration, our approach compares favorably to state-of-the-art methods in\nterms of a mean calibration error of 0.28 degrees for the rotational and 6 cm\nfor the translation components even for large decalibrations up to 1.5 m and 20\ndegrees.","url_abs":"http://arxiv.org/abs/1707.03167v1","url_pdf":"http://arxiv.org/pdf/1707.03167v1.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":"regnet-multimodal-sensor-registration-using","repo_url":"https://github.com/MindCode-4/code-4/tree/main/reformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.03167","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}