[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84363-en":3,"doc-seo-84363-105":30,"detail-sidebar-cat-0-en-105":91},{"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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},84363,13056703020460,"Valentina","https://ap-avatar.wpscdn.com/avatar/be000253dac470eee5d?_k=1778207105932848923",8,"Research & Report","On Exploring Input Resolution Scaling For Anytime LiDAR Object Detection","Making tradeoffs between execution latency and result utility (anytime computing) helps cyber-physical systems adapt to changing requirements. This work enables anytime computing for deep neural networks processing LiDAR point clouds for 3D object detection. A multi-resolution inference method dynamically scales input resolution for pillar/voxel models, using a single memory-efficient DNN instead of multiple resolution-specific models. A deadline-aware scheduler predicts runtime for irregular point clouds to choose the highest feasible resolution. Results on nuScenes and a simulated driving system show strong gains and collision-free navigation.","On Exploring Input Resolution Scaling For Anytime LiDAR Object Detection  \nAhmet Soyyigit, Shuochao Yao, and Heechul Yun  \n~~ ~~ ✦ ~~ ~~  \narXiv :2607 .0839 1v 1 [ cs .RO] 9 Jul 2026  \nAbstract—Making tradeoffs between execution latency and result utility (i.e., anytime computing) for adapting to dynamic operational requirements has been shown to enhance the performance of cyber-physical systems. In this work, we focus on enabling anytime computing for deep neural networks (DNNs) that process LiDAR point clouds for 3D object detection. We propose a novel method that enables multi-resolution inference for models that process point clouds as pillars or voxels, allowing the input to be dynamically scaled and processed at the resolution needed to meet timing requirements. Importantly, our memory-efficient approach requires the deployment of only a single DNN model, avoiding the need to deploy multiple models, each trained for a different input resolution. We also introduce a deadline-aware scheduler that selects the highest possible resolution for any given input by accurately predicting the execution time for all possible resolutions at runtime, which is challenging due to the irregularity of LiDAR point clouds. Experimental results on the nuScenes autonomous driving dataset demonstrate that our method significantly outperforms existing anytime computing approaches for LiDAR object detection. Finally, we deploy our approach in a simulated autonomous driving system, where it consistently enables collision-free navigation while avoiding unnecessary stalls caused by environmental complexity.  \nIndex Terms—LiDAR, 3D object detection, Deep neural networks, Anytime computing, Simulation  \n1 INTRODUCTION  \nAutonomous systems are critically dependent on the accurate detection of surrounding objects in real-time. For this task, numerous highly accurate LiDAR-based object detection deep neural networks (DNNs) have been proposed in recent years [1], [2], [3], [4] . However, these state-ofthe-art LiDAR object detection DNNs are computationally expensive, making deployment on resource-constrained embedded computing hardware challenging. This challenge is particularly pronounced in systems with strict size, weight, and power (SWaP) constraints, necessitating trade-offs between accuracy and latency.  \nThe required accuracy/latency trade-offs depend not only on the SWaP constraints but also on the dynamic operation environment [5], [6] . For example, in complex and crowded urban environments where objects move slowly, processing input in a fine-grained manner may be desirable  \nDr. Soyyigit is with The National Defense University, Istanbul, Turkiye (email: [ahmet.soyyigit@msu.edu.tr](ahmet.soyyigit@msu.edu.tr)). He is the corresponding author of this paper.  \nDr. Yao is with George Mason University, Fairfax, VA, USA (e-mail: [shuochao@gmu.edu](shuochao@gmu.edu)).  \nDr. Yun is with The University of Kansas, Lawrence, KS, USA (e-mail: [heechul.yun@ku.edu](heechul.yun@ku.edu)).  \nto maximize detection accuracy, even if it takes longer. However, in simpler environments with fast-moving objects, such as highways, it may be preferable to process quickly ina coarse-grained manner, as lower processing latency could be more important than high precision and fine-grained details.  \nAlgorithms that can trade off quality and latency are known as anytime algorithms in the literature, and there has been significant effort in recent years to make anytimecapable DNNs that process perceptual input data. For image classification and object detection tasks,“early-exit” architectures have been explored [7], [8], [9], [10], where additional output layers are integrated at intermediate stages of a DNN to allow predictions to be made before reaching the full depth of the model. Criticality-based slicing and scheduling of input [9], [11], [12], [13], [14] and dynamic scaling of image resolution [15], [16], [17] have been studied to enable anytime processing capabilitie","cbCaiefqmdvxPcAT","https://ap.wps.com/l/cbCaiefqmdvxPcAT","pdf",2346427,3,1,14,"English","en",105,"# Introduction\n## Anytime algorithms and DNN trade-offs\n## Prior work for LiDAR anytime detection\n## Motivation for input resolution scaling\n## Proposed approach: MURAL","[{\"question\":\"What problem does the paper address in LiDAR-based real-time object detection?\",\"answer\":\"LiDAR object detection DNNs are computationally expensive, and accuracy/latency trade-offs must adapt to both hardware constraints and dynamic environments.\"},{\"question\":\"How does the proposed method enable anytime computing for LiDAR models?\",\"answer\":\"It uses multi-resolution inference that dynamically scales input resolution for pillar/voxel networks, while deploying only a single DNN model to stay memory-efficient.\"},{\"question\":\"How is the resolution chosen to meet timing requirements?\",\"answer\":\"A deadline-aware scheduler predicts execution time for all candidate resolutions at runtime, allowing selection of the highest feasible resolution despite irregular LiDAR point clouds.\"}]",1784195104,35,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"on-exploring-input-resolution-scaling-for-anytime-lidar-object-detection","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/on-exploring-input-resolution-scaling-for-anytime-lidar-object-detection/84363/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-26","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the paper address in LiDAR-based real-time object detection?","Question",{"text":75,"@type":76},"LiDAR object detection DNNs are computationally expensive, and accuracy/latency trade-offs must adapt to both hardware constraints and dynamic environments.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed method enable anytime computing for LiDAR models?",{"text":80,"@type":76},"It uses multi-resolution inference that dynamically scales input resolution for pillar/voxel networks, while deploying only a single DNN model to stay memory-efficient.",{"name":82,"@type":73,"acceptedAnswer":83},"How is the resolution chosen to meet timing requirements?",{"text":84,"@type":76},"A deadline-aware scheduler predicts execution time for all candidate resolutions at runtime, allowing selection of the highest feasible resolution despite irregular LiDAR point clouds.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]