[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-81532-en":3,"doc-seo-81532-105":29,"detail-sidebar-cat-0-en-105":82},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},81532,687197100911,"Himbo","https://ap-avatar.wpscdn.com/avatar/a000239b6f1da00475?x-image-process=image/resize,m_fixed,w_180,h_180&k=1782698725881665579",8,"Research & Report","Single-Frame Point-Pixel Registration via Supervised Cross-Modal Feature Matching","Point-pixel registration between LiDAR point clouds and camera images is critical for autonomous driving and robotic perception, yet difficult due to the modality gap and, in sparse single-frame LiDAR, severe sparsity and noise. The method proposes a detector-free, projection-based framework for direct point-pixel matching, avoiding separate encoders that inadequately bridge modalities. A repeatability scoring mechanism acts as a soft visibility prior, suppressing unreliable matches. Experiments on KITTI, nuScenes, and MIASLCEC-TF70 show state-of-the-art results, including improved performance on nuScenes using only single-frame LiDAR.","Single-Frame Point-Pixel Registration via Supervised Cross-Modal  \nFeature Matching  \nYu Han , Zhiwei Huang , Yanting Zhang , Fangjun Ding , Shen Cai , Xiaoyu Tang , Yanchao Dong , and Rui Fan , Senior Member, IEEE  \narXiv :2506 .22784v2 [ cs .CV] 10 Jul 2026  \nAbstract— Point-pixel registration between LiDAR point clouds and camera images is a fundamental yet challenging task in autonomous driving and robotic perception. A key difficulty lies in the modality gap between unstructured point clouds and structured images, especially under sparse single-frame LiDAR settings. Existing methods typically extract features separately from point clouds and images, then rely on hand-crafted or learned matching strategies. This separate encoding fails to bridge the modality gap effectively, and more critically, these methods struggle with the sparsity and noise of single-frame LiDAR, often requiring point cloud accumulation or additional priors to improve reliability. Inspired by recent progress in detector-free matching paradigms, we revisit the projection-based approach and introduce the detector-free framework for direct point-pixel matching between LiDAR and camera views. To further enhance matching reliability, we introduce a repeatability scoring mechanism that acts as a soft visibility prior. This guides the network to suppress unreliable matches in regions with low intensity variation, improving robustness under sparse input. Extensive experiments on KITTI, nuScenes, and MIASLCEC-TF70 benchmarks demonstrate that our method achieves state-of-the-art performance, outperforming prior approaches on nuScenes (even those relying on accumulated point clouds), despite using only single-frame LiDAR.  \nNote to Practitioners—In many practical robotic and autonomous driving systems, only sparse LiDAR sensors (e.g., 16-or 32-line) are available due to cost and deployment constraints. This sparsity makes online LiDAR-camera calibration particularly challenging, since traditional methods often rely on dense multi-frame point clouds or additional calibration targets. Our proposed detector-free framework directly establishes point-pixel correspondences from a single sparse LiDAR scan, ensuring robust calibration even under noisy and low-density conditions. This enables practical online re-calibration after sensor maintenance or accidental impacts without requiring specialized setups.  \nYu Han and Zhiwei Huang are co-first authors. Corresponding author: Yanting Zhang and Rui Fan.  \nYu Han, Yanting Zhang, Fangjun Ding, and Shen Cai are with the School of Information and Intelligent Science, Donghua University, Shanghai 201620, China (e-mails: [2232816@mail.dhu.edu.cn](2232816@mail.dhu.edu.cn), [ytzhang@dhu.edu.cn](ytzhang@dhu.edu.cn), [220800613@mail.dhu.edu.cn](220800613@mail.dhu.edu.cn), [cs@dhu.edu.cn](cs@dhu.edu.cn)) .  \nZhiwei Huang and Yanchao Dong are with the Department of Control Science & Engineering, the College of Electronics & Information Engineering, Tongji University, Shanghai 201804, China (e-mails: {2431985, dongyan[chao](chao}@tongji.edu.cn)[}](chao}@tongji.edu.cn)[@tongji.edu.cn](chao}@tongji.edu.cn)).  \nXiaoyu Tang is with the School of Electronics and Information Engineering, and Xingzhi College, South China Normal University, Shanwei, 516600, China (e-mail: [tangxy@scnu.edu.cn](tangxy@scnu.edu.cn)).  \nRui Fan is with the Department of Control Science & Engineering, the College of Electronics & Information Engineering, Shanghai Research Institute for Intelligent Autonomous Systems, the State Key Laboratory of Intelligent Autonomous Systems, and Frontiers Science Center for Intelligent Autonomous Systems, Tongji University, Shanghai 201804, China, as well as with the National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an 710049, Shaanxi, China (e-mail: [rui.fan@ieee.org](rui.fan@ieee.org)).  \nDifferent Robot Platforms  \nFig. 1. Ou","cbCaiqPrhEXsFTxe","https://ap.wps.com/l/cbCaiqPrhEXsFTxe","pdf",3441899,1,13,"English","en",105,"# Abstract\n# Note to Practitioners\n# Index Terms\n# Introduction","[{\"question\":\"How does the repeatability scoring mechanism improve robustness under sparse inputs?\",\"answer\":\"It provides a soft visibility prior that guides the network to suppress unreliable matches in regions with low intensity variation, improving stability when LiDAR input is sparse and noisy.\"}]",1784174087,33,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":77,"head_meta":79,"extra_data":81,"updated_unix":27},"single-frame-point-pixel-registration-via-supervised-cross-modal-feature-matching","",{"@graph":35,"@context":76},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/single-frame-point-pixel-registration-via-supervised-cross-modal-feature-matching/81532/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70],{"name":71,"@type":72,"acceptedAnswer":73},"How does the repeatability scoring mechanism improve robustness under sparse inputs?","Question",{"text":74,"@type":75},"It provides a soft visibility prior that guides the network to suppress unreliable matches in regions with low intensity variation, improving stability when LiDAR input is sparse and noisy.","Answer","https://schema.org",{"og:url":51,"og:type":78,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":80,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":83},[84,88,92,96,101,106,111,114,119,122,126],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":45,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":45,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":112,"slug":113},30,"research-report",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":45,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general"]