[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83324-en":3,"doc-seo-83324-105":30,"detail-sidebar-cat-0-en-105":92},{"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},83324,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","EVIS: A Physics-Grounded Event Camera Plugin for NVIDIA Isaac Sim","EVIS introduces a physics-grounded event camera plugin for NVIDIA Isaac Sim to generate high-rate, fully labeled event streams for robotics research. The plugin implements a faithful log-intensity contrast event model with per-pixel asynchronous reference updates and migrates from an RGB camera with minimal changes, integrating into Isaac Sim/Isaac Lab scenes. It inherits simulator physics and frame-perfect ground truth, is configurable, and supports GPU-efficient interpolation via sparse keyframes and bidirectional motion-vector warping. Optional sensor noise and motion blur improve realism, enabling direct use by pretrained event networks.","EVIS: A Physics-Grounded Event Camera Plugin for NVIDIA Isaac Sim  \nLinli Shi Ruijun Zhang Ziyun Wang*  \nJohns Hopkins University  \n{lshi42, [rzhan158](rzhan158}@jh.edu)[}](rzhan158}@jh.edu)[@jh.edu](rzhan158}@jh.edu) , [claude.w@jhu.edu](claude.w@jhu.edu)  \narXiv :2607 .08098v 1 [ cs .CV] 9 Jul 2026  \nFigure 1 . Top: a Franka wrist-mounted event camera circles a mustard bottle. Middle: a head-mounted event camera on a walking ANYmal  \nquadruped as objects drop. Bottom: a stereo event camera observes a falling object. Videos in the repository.  \nAbstract  \nEvent cameras offer microsecond temporal resolution, low latency, and high dynamic range, making them attractive for robotics. However, labeled event-camera data for a specific robot and scene is scarce and expensive to collect, which slows the development of event-based perception and control. We present EVIS: a physics-grounded event camera plugin for NVIDIA Isaac Sim that generates high-rate, fully labeled event streams directly inside a physics simulator. The plugin implements a faithful log-intensity contrast event model with per-pixel asynchronous reference updates; it migratesfrom a normal RGB  \ncamera with few changes and integrates into any Isaac Sim / Isaac Lab scene, inheriting the simulator’s physics and frame-perfect ground truth. It is fully configurable, and offers an interpolation option that renders only sparse keyframes and synthesizes the in-between frames through bidirectional motion-vector warping, making real-time generation on a single GPU possible. Optional sensor noise and motion blur further narrow the gap to real cameras. The generated streams are directly usable by pretrained event networks for downstream tasks. Code repository:  \n[https://github. com/spikelab-jhu/isaac](https://github. com/spikelab-jhu/isaac)sim-event-camera-plugin.  \n1. Introduction  \nEvent cameras do not output full synchronous frames like conventional cameras; instead they report per-pixel brightness changes asynchronously. This mechanism yields high temporal resolution, low latency, and high dynamic range, which makes them especially well-suited to fast-motion, contact-rich, or high-dynamic-range robotic settings. Yet the data ecosystem for event-based robotics remains thin. For a given robot embodiment and task, real event recordings are scarce, must be precisely labeled and aligned, and are costly to collect. Simulation is a natural remedy, but a good event-camera simulator must satisfy three requirements simultaneously.  \n(i) Fidelity. Events arise from brightness changes: the simulator needs a correct contrast-triggering model at a high effective frame rate, including the sensor’s noise processes.  \n(ii) Physics consistency. The events must come from a genuine physics-simulated scene with exact ground truth, not from a pre-recorded video.  \n(iii) Rendering throughput. Event generation must keep pace with the simulator, ideally at or above real time on a single GPU, so that event-based perception can be trained at the same scale as RGB pipelines.  \nTo meet all three, we build the event-camera simulator directly inside NVIDIA Isaac Sim, integrated through the Isaac Lab framework. Our contributions are:  \n1. A faithful, GPU-batched log-intensity contrast event model with per-pixel asynchronous reference latching, validated on downstream tasks: pretrained event networks run unmodified on the generated streams.  \n2. A direct integration with Isaac Sim: replacing an RGB camera configuration with an event-camera configuration lets any physics-simulated scene produce labeled event data.  \n3. A motion-vector frame-interpolation pipeline that renders only sparse RTX keyframes and synthesizes the high-rate frames in between, enabling real-time operation on a single GPU.  \n2. Related Work  \nEvent cameras have enabled a range of robotic perception tasks [5], including independent-motion segmentation [23], 3D reconstruction [21], wide-baseline feature matching [25], tracking [9], and h","cbCaikdxkGJnsseh","https://ap.wps.com/l/cbCaikdxkGJnsseh","pdf",18379141,6,1,9,"English","en",105,"# Introduction\n# Related Work\n# Event Model","[{\"question\":\"What problem does EVIS address in event-based robotics research?\",\"answer\":\"Labeled event-camera data for specific robots and scenes is scarce and expensive to collect, which slows event-based perception and control development. EVIS generates fully labeled event streams inside a physics simulator to reduce reliance on real recordings.\"},{\"question\":\"How does EVIS generate event streams in Isaac Sim?\",\"answer\":\"It uses a faithful log-intensity contrast event model with per-pixel asynchronous reference updates and replaces an RGB camera configuration with an event-camera configuration. The plugin leverages Isaac Sim/Isaac Lab to produce events alongside physics and frame-perfect ground truth.\"},{\"question\":\"How does EVIS support real-time generation on a single GPU?\",\"answer\":\"It includes a motion-vector frame-interpolation pipeline that renders only sparse RTX keyframes and synthesizes intermediate high-rate frames using bidirectional motion-vector warping. Optional sensor noise and motion blur further narrow the gap to real cameras.\"}]",1784186740,23,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"evis-a-physics-grounded-event-camera-plugin-for-nvidia-isaac-sim","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"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":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/evis-a-physics-grounded-event-camera-plugin-for-nvidia-isaac-sim/83324/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-07-25","2026-07-16",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does EVIS address in event-based robotics research?","Question",{"text":76,"@type":77},"Labeled event-camera data for specific robots and scenes is scarce and expensive to collect, which slows event-based perception and control development. EVIS generates fully labeled event streams inside a physics simulator to reduce reliance on real recordings.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does EVIS generate event streams in Isaac Sim?",{"text":81,"@type":77},"It uses a faithful log-intensity contrast event model with per-pixel asynchronous reference updates and replaces an RGB camera configuration with an event-camera configuration. The plugin leverages Isaac Sim/Isaac Lab to produce events alongside physics and frame-perfect ground truth.",{"name":83,"@type":74,"acceptedAnswer":84},"How does EVIS support real-time generation on a single GPU?",{"text":85,"@type":77},"It includes a motion-vector frame-interpolation pipeline that renders only sparse RTX keyframes and synthesizes intermediate high-rate frames using bidirectional motion-vector warping. Optional sensor noise and motion blur further narrow the gap to real cameras.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,115,120,123,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},"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":22,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":107,"slug":137},19,"General","general"]