{"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/corri2p-deep-image-to-point-cloud","title":"CorrI2P: Deep Image-to-Point Cloud Registration via Dense Correspondence","arxiv_id":"2207.05483","date":"2022-07-12","proceeding":null,"authors":["Siyu Ren","Yiming Zeng","Junhui Hou","Xiaodong Chen"],"abstract":"Motivated by the intuition that the critical step of localizing a 2D image in the corresponding 3D point cloud is establishing 2D-3D correspondence between them, we propose the first feature-based dense correspondence framework for addressing the image-to-point cloud registration problem, dubbed CorrI2P, which consists of three modules, i.e., feature embedding, symmetric overlapping region detection, and pose estimation through the established correspondence. Specifically, given a pair of a 2D image and a 3D point cloud, we first transform them into high-dimensional feature space and feed the resulting features into a symmetric overlapping region detector to determine the region where the image and point cloud overlap each other. Then we use the features of the overlapping regions to establish the 2D-3D correspondence before running EPnP within RANSAC to estimate the camera's pose. Experimental results on KITTI and NuScenes datasets show that our CorrI2P outperforms state-of-the-art image-to-point cloud registration methods significantly. We will make the code publicly available.","url_abs":"https://arxiv.org/abs/2207.05483v3","url_pdf":"https://arxiv.org/pdf/2207.05483v3.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":"corri2p-deep-image-to-point-cloud","repo_url":"https://github.com/rsy6318/CorrI2P","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-to-point-cloud-registration","task_name":"Image to Point Cloud Registration"},{"task_slug":"point-cloud-registration","task_name":"Point Cloud Registration"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-to-point-cloud-registration-on-kitti","task":"Image to Point Cloud Registration","dataset":"KITTI","model":"CorrI2P","rank_in_archive_order":1,"of":1,"metrics":{"RRE":"2.07","RTE":"0.74"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.05483","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}