{"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/learning-less-is-more-6d-camera-localization","title":"Learning Less is More - 6D Camera Localization via 3D Surface Regression","arxiv_id":"1711.10228","date":"2017-11-28","proceeding":"CVPR 2018 6","authors":["Eric Brachmann","Carsten Rother"],"abstract":"Popular research areas like autonomous driving and augmented reality have\nrenewed the interest in image-based camera localization. In this work, we\naddress the task of predicting the 6D camera pose from a single RGB image in a\ngiven 3D environment. With the advent of neural networks, previous works have\neither learned the entire camera localization process, or multiple components\nof a camera localization pipeline. Our key contribution is to demonstrate and\nexplain that learning a single component of this pipeline is sufficient. This\ncomponent is a fully convolutional neural network for densely regressing\nso-called scene coordinates, defining the correspondence between the input\nimage and the 3D scene space. The neural network is prepended to a new\nend-to-end trainable pipeline. Our system is efficient, highly accurate, robust\nin training, and exhibits outstanding generalization capabilities. It exceeds\nstate-of-the-art consistently on indoor and outdoor datasets. Interestingly,\nour approach surpasses existing techniques even without utilizing a 3D model of\nthe scene during training, since the network is able to discover 3D scene\ngeometry automatically, solely from single-view constraints.","url_abs":"http://arxiv.org/abs/1711.10228v2","url_pdf":"http://arxiv.org/pdf/1711.10228v2.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":"learning-less-is-more-6d-camera-localization","repo_url":"https://github.com/vislearn/LessMore","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"camera-localization","task_name":"Camera Localization"},{"task_slug":"visual-localization","task_name":"Visual Localization"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.10228","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}