[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82479-en":3,"doc-seo-82479-105":29,"detail-sidebar-cat-0-en-105":90},{"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},82479,1099513958762,"Logic","https://ap-avatar.wpscdn.com/avatar/1000023916a998db790?x-image-process=image/resize,m_fixed,w_180,h_180&k=1782109480056885918",6,"Technology","VOCA Visual Odometry with Codec Awareness","Camera pose estimation from image streams is a critical component of spatial world models used for planning and decision-making. Most visual odometry and visual SLAM research evaluates on raw, uncompressed videos, even though real systems often compress and decode streams to save storage and bandwidth. Lossy compression creates artifacts that degrade tracking. VOCA is a causal stereo visual-odometry approach that exploits codec information to improve tracking on compressed streams, achieving state-of-the-art results for trajectory error and efficiency.","arXiv :2607 .00189v1 [ cs .CV] 30 Jun 2026  \nVOCA: Visual Odometry with Codec Awareness  \nNouri Alexander Hilscher⋆1 Mateo de Mayo∗ 1 ,2 Dominik Muhle 1 ,2 Christoph Otten genannt Hermes 1 Daniel Cremers 1 ,2  \n1 Technical University of Munich, Munich, Germany  \n2 Munich Center for Machine Learning, Munich, Germany  \n\n| ~~ ~~ Ground-truth ~~ ~~ VOCA ~~ ~~ OKVIS2 ~~ ~~ ORB-SLAM3 |  |  Start |  End |  Highlight |\n| --- | --- | --- | --- | --- |\n\nx [m]  \n−2.0 −1.0 0.0 1.0 2.0  \nATE [cm]  \n5   \n0   \n70 72 74 76 78 80 Time [s]  \n−1.0  \n−1.2  \n−1.4  \n−1.6  \n1.0  \n0.0  \n−1.0  \n−2.0  \nx [m]  \n−1 0 1 2 3 4  \n50 ~~ ~~  \n0   \n28 30 32 34 36 38 40  \nTime [s]  \n40 ~~ ~~ ~~ ~~  \n0 ~~ ~~ 24 27 30 33 36 39 42   \nTime [s]  \nFig. 1: Visual Odometry on Compressed Videos. We present VOCA, a novel Visual Odometry system that produces smoother, more stable trajectories than descriptor-based systems such as ORB-SLAM3 and OKVIS2, thanks to its codec-aware sparse optical-flow frontend. Our system enables Visual Odometry on data compressed by up to 100× . We visualize challenging segments with dashed-red markers, sampled from three different datasets. In the zoomed-in views, we show the previous pixel location that would be the prior in regular VO systems, the motion-vector prior that we introduce, and the optical flow solution. In most cases, motion-vector priors reduce the initialization distance to the solution to just a few pixels.  \nAbstract. Camera pose estimation from image streams is a critical component of spatial world models that integrate perception into planning and decision-making. Nearly all Visual Odometry (VO) and Simultaneous Localization and Mapping (SLAM) systems have focused on datasets containing raw, uncompressed videos. Many working systems instead use ubiquitous hardware units to efficiently compress and decode video streams, saving orders of magnitude in storage and bandwidth. However, this lossy compression introduces visual artifacts that hinder the performance of traditional tracking systems. We present VOCA, a causal stereo visual-odometry method that exploits codec information to improve tracking performance. We achieve state-of-the-art performance on causal VO for relative trajectory error, efficiency, and absolute trajectory error on compressed streams. This work highlights the potential of leveraging widely available video codec information for vision tasks.  \nKeywords: Visual Odometry · KLT-Tracking · Compressed Videos  \n⋆ equal contribution  \n2 N. Hilscher et al.  \n1 Introduction  \nSpatial computing systems make their way into our lives in a variety of forms, from mixed reality devices to autonomous systems such as robotic assistants, drones, and self-driving cars. Cameras have proven to be a rich and cost-effective sensor, driven in part by the ubiquity of mobile and embedded vision in consumer devices [3, 63] . Current trends in computer vision, learning, and robotics show increasing overlap in research, with no sign of slowing [9, 27, 47] . Furthermore, immense potential is expected from learning-based models that leverage the vast amount of internet videos captured by these sensors for training [2, 9] . In this context, tracking camera poses has become imperative for many applications and research [11, 19, 21, 23, 70] . There cannot be action and planning in 3D without first understanding the current location of a moving agent [22] .  \nThe high potential for cameras comes at the cost of large volumes of data. A raw image stream from a common setup of stereo monochrome cameras (8-bit pixels) with a resolution of 640 × 480 at 30 frames per second produces more thana gigabyte of data per minute. Since bandwidth and memory are expensive [72], practical systems rely on compression to transmit camera streams efficiently under the compress-then-analyze design paradigm [24] . Years of software and hardware development have gone into accelerating common encoders such as H.264, AV1, and VP9 [20,42,68] . Video codecs are no","cbCaibwG88KIlbdE","https://ap.wps.com/l/cbCaibwG88KIlbdE","pdf",8255134,1,27,"English","en",105,"# Introduction\n## Motivation: Compression in Spatial Computing\n## Problem: Lossy Artifacts in VO/VSLAM\n## Approach: VOCA and Codec-Aware Tracking\n## System Overview and Baseline","[{\"question\":\"Why is video compression challenging for visual odometry and visual SLAM?\",\"answer\":\"Because lossy compression introduces visual artifacts that hinder traditional tracking performance, especially when systems assume raw, uncompressed imagery.\"},{\"question\":\"What does VOCA improve compared with descriptor-based tracking systems?\",\"answer\":\"VOCA produces smoother, more stable trajectories by using a codec-aware sparse optical-flow frontend and motion-vector priors to guide initialization.\"},{\"question\":\"How does VOCA enable visual odometry on compressed video streams?\",\"answer\":\"VOCA leverages video codec information during tracking, allowing it to achieve strong performance on compressed streams, including data compressed by up to 100×.\"}]",1784180805,68,{"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":85,"head_meta":87,"extra_data":89,"updated_unix":27},"voca-visual-odometry-with-codec-awareness","",{"@graph":35,"@context":84},[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/technology/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/voca-visual-odometry-with-codec-awareness/82479/",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",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Why is video compression challenging for visual odometry and visual SLAM?","Question",{"text":74,"@type":75},"Because lossy compression introduces visual artifacts that hinder traditional tracking performance, especially when systems assume raw, uncompressed imagery.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What does VOCA improve compared with descriptor-based tracking systems?",{"text":79,"@type":75},"VOCA produces smoother, more stable trajectories by using a codec-aware sparse optical-flow frontend and motion-vector priors to guide initialization.",{"name":81,"@type":72,"acceptedAnswer":82},"How does VOCA enable visual odometry on compressed video streams?",{"text":83,"@type":75},"VOCA leverages video codec information during tracking, allowing it to achieve strong performance on compressed streams, including data compressed by up to 100×.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,112,117,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":110,"slug":111},50,"technology",{"id":113,"doc_module":4,"doc_module_name":45,"category_name":114,"show_sort_weight":115,"slug":116},7,"Healthcare",40,"healthcare",{"id":118,"doc_module":4,"doc_module_name":45,"category_name":119,"show_sort_weight":120,"slug":121},8,"Research & Report",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":105,"slug":137},19,"General","general"]