{"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/rpnet-an-end-to-end-network-for-relative","title":"RPNet: an End-to-End Network for Relative Camera Pose Estimation","arxiv_id":"1809.08402","date":"2018-09-22","proceeding":null,"authors":["Sovann En","Alexis Lechervy","Frédéric Jurie"],"abstract":"This paper addresses the task of relative camera pose estimation from raw\nimage pixels, by means of deep neural networks. The proposed RPNet network\ntakes pairs of images as input and directly infers the relative poses, without\nthe need of camera intrinsic/extrinsic. While state-of-the-art systems based on\nSIFT + RANSAC, are able to recover the translation vector only up to scale,\nRPNet is trained to produce the full translation vector, in an end-to-end way.\nExperimental results on the Cambridge Landmark dataset show very promising\nresults regarding the recovery of the full translation vector. They also show\nthat RPNet produces more accurate and more stable results than traditional\napproaches, especially for hard images (repetitive textures, textureless\nimages, etc). To the best of our knowledge, RPNet is the first attempt to\nrecover full translation vectors in relative pose estimation.","url_abs":"http://arxiv.org/abs/1809.08402v1","url_pdf":"http://arxiv.org/pdf/1809.08402v1.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":"rpnet-an-end-to-end-network-for-relative","repo_url":"https://github.com/ensv/RPNet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"camera-pose-estimation","task_name":"Camera Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1809.08402","atlas_url":"https://app.syntology.ai/?focus=1809.08402","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}