[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83852-en":3,"doc-seo-83852-105":29,"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":20,"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},83852,8796095462418,"Noah","https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780",8,"Research & Report","Cam2Sim Neural Scenario Reconstruction for Closed-Loop Autonomous Driving Simulation","Simulation-based testing enables safe, repeatable evaluation of autonomous driving systems but is constrained by the sim-to-real gap between synthetic simulator outputs and real camera observations. Cam2Sim converts real-world driving recordings into playable CARLA scenarios by reconstructing road geometry, ego trajectories, parked vehicles, and simulation assets from camera images and poses, then using Gaussian Splatting to render camera-like views. The pipeline supports ROS data extraction, OpenStreetMap map generation, CARLA scenario construction, training, trajectory replay, and closed-loop execution. Validation on real urban driving improves visual fidelity and behavioral similarity versus a simulation-only baseline.","Cam2Sim: Neural Scenario Reconstruction for Closed-Loop Autonomous Driving Simulation  \nDavide Jannussi  \nPolitecnico di Torino Torino, Italy  \ns331391@studenti.polito.it  \nStefano Carlo Lambertenghi  \nTUM, fortiss Munich, Germany [stefanocarlo.lambertenghi@tum.de](stefanocarlo.lambertenghi@tum.de)  \narXiv :2607 .04770v 1 [ cs . SE] 6 Jul 2026  \nConstantin Carste  \nTUM  \nMunich, Germany [constantin.carste@tum.de](constantin.carste@tum.de)  \nAbstract  \nSimulation-based testing enables safe and repeatable evaluation of autonomous driving systems, but its effectiveness is limited by the gap between synthetic simulator outputs and real-world camera observations. To address this problem, we present Cam2Sim, a tool that transforms real-world driving recordings into playable CARLA simulation scenarios. Starting from camera images and poses, Cam2Sim reconstructs road geometry, ego trajectories, parked vehicles, and simulation assets, and augments the reconstructed environment with Gaussian Splatting to render camera observations that resemble the original recording. The framework supports ROSbased data extraction, parked-vehicle detection, OpenStreetMapbased map generation, CARLA scenario construction, Gaussian Splatting training, trajectory replay, and closed-loop execution with a system under test. We validate Cam2Sim on a real-world urban-driving scenario with a camera-based end-to-end driving model, comparing reconstruction quality, image-generation quality, and closed-loop behavior against both a simulation-only baseline and the real-world target. Results show that Gaussian-Splattingbased rendering reduces the visual gap with respect to standard simulator rendering and improves behavioral similarity to the realworld reference runs. The artifact is publicly available at [https:](https:)//[github.com/ast-fortiss-tum/cam2sim](github.com/ast-fortiss-tum/cam2sim), and a screencast showing the tool is available at [https://youtu.be/KmZ74l1__lI](https://youtu.be/KmZ74l1__lI).  \nACM Reference Format:  \nDavide Jannussi, Stefano Carlo Lambertenghi, Constantin Carste, and Andrea Stocco. 2026. Cam2Sim: Neural Scenario Reconstruction for ClosedLoop Autonomous Driving Simulation. In Proceedings of Proceedings of the 41st IEEE/ACM International Conference on Automated Software Engineering (ASE ’26). ACM, New York, NY, USA, 5 pages. [https://doi.org/XXXXXXX](https://doi.org/XXXXXXX). XXXXXXX  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission [and/or a fee. Request permissions from permissions@acm.org](and/or a fee. Request permissions from permissions@acm.org).  \nASE’26, Munich, Germany  \n© 2026 Copyright held by the owner/author(s) . Publication rights licensed to ACM. ACM ISBN 978-1-4503-XXXX-X/2026/06  \n[https://doi.org/XXXXXXX.XXXXXXX](https://doi.org/XXXXXXX.XXXXXXX)  \nAndrea Stocco  \nTUM, fortiss  \nMunich, Germany  \n[andrea.stocco@tum.de](andrea.stocco@tum.de)  \n1 Introduction  \nAutonomous driving systems (ADS) must be evaluated before deployment because failures can have safety-critical consequences [26] . Modern ADS rely heavily on machine learning and deep learning components for perception and decision-making [17], whose datadriven nature introduces failure modes that differ fundamentally from those of traditional software, motivating specialized testing techniques [10] . Real-world testing provides the strongest evidence of system performance under realistic operating conditions, but it is expensive, difficult to reproduce, time-consuming, and unsafe for many corner ","cbCaijOBiDJf6cRc","https://ap.wps.com/l/cbCaijOBiDJf6cRc","pdf",22247704,5,1,"English","en",105,"# Abstract\n# Introduction\n## Motivation: sim-to-real gap and evaluation limits\n## Related work: neural rendering and scenario reconstruction\n## Contribution: Cam2Sim framework","[{\"question\":\"What problem does Cam2Sim target in autonomous driving simulation?\",\"answer\":\"It targets the sim-to-real gap, where differences between synthetic simulator outputs and real camera observations lead to different behaviors in autonomous driving systems.\"},{\"question\":\"How does Cam2Sim turn real driving recordings into CARLA scenarios?\",\"answer\":\"It reconstructs road geometry, ego trajectories, parked vehicles, and CARLA simulation assets from front-facing camera images and poses, then renders camera-like views using Gaussian Splatting.\"},{\"question\":\"What does the evaluation compare, and what are the results?\",\"answer\":\"The evaluation compares reconstruction quality, image-generation quality, and closed-loop behavior against a simulation-only baseline and the real-world target, showing reduced visual gap and improved behavioral similarity.\"}]",1784190994,13,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":27},"cam2sim-neural-scenario-reconstruction-for-closed-loop-autonomous-driving-simulation","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":21},"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/cam2sim-neural-scenario-reconstruction-for-closed-loop-autonomous-driving-simulation/83852/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-25","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 Cam2Sim target in autonomous driving simulation?","Question",{"text":75,"@type":76},"It targets the sim-to-real gap, where differences between synthetic simulator outputs and real camera observations lead to different behaviors in autonomous driving systems.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does Cam2Sim turn real driving recordings into CARLA scenarios?",{"text":80,"@type":76},"It reconstructs road geometry, ego trajectories, parked vehicles, and CARLA simulation assets from front-facing camera images and poses, then renders camera-like views using Gaussian Splatting.",{"name":82,"@type":73,"acceptedAnswer":83},"What does the evaluation compare, and what are the results?",{"text":84,"@type":76},"The evaluation compares reconstruction quality, image-generation quality, and closed-loop behavior against a simulation-only baseline and the real-world target, showing reduced visual gap and improved behavioral similarity.","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":24},{"code":4,"msg":5,"data":92},[93,97,101,105,109,114,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":20,"slug":137},19,"General","general"]