[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82955-en":3,"doc-seo-82955-105":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":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},82955,1099514068035,"Ezra","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models","Predicting object dynamics for robotic manipulation is central to world modeling, and deformable objects add major difficulty due to high-dimensional states and complex material behavior. Existing approaches mainly learn dynamics in 2D pixel space or in explicit 3D geometric space, yet their trade-offs remain unclear without large-scale real data. Deform360 provides 198 daily-life objects, 1,980 interaction sequences, and 215+ hours of multi-view visuotactile recordings, enabling dense 3D tracking and systematic evaluation.","arXiv :2607 .05390v 1 [ cs .RO] 6 Jul 2026  \nDeform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models  \nHongyu Li 1 ,2∗, Wanjia Fu 1∗, Xiaoyan Cong 1, Zekun Li 1,  \nBinghao Huang2, Hanxiao Jiang2, Xintong He 1 , Yiqing Liang 1, Rao Fu 1, Tao Lu 1, Srinath Sridhar 1, Kevin A. Smith3, George Konidaris 1, and Yunzhu Li2  \n1 Brown University, Providence, RI  \n2 Columbia University, New York, NY  \n3 Massachusetts Institute of Technology, Cambridge, MA  \n∗ Equal contribution  \nAbstract. Predicting object dynamics (i.e., world modeling) is a fundamental challenge for robotic manipulation, and modeling deformable objects presents a particularly difficult case due to their high-dimensional state spaces and complex material properties. While current world models approach this through two distinct paradigms: learning the dynamics over the 2D pixel space or more explicit 3D geometric space. A systematic understanding of their relative strengths and limitations remains elusive due to the lack of diverse, large-scale real-world data. To address this, we present Deform360, a large-scale visuotactile dataset featuring 198 daily-life objects, 1,980 interaction sequences, and over 215 hours of observations from 41 surround-view cameras and bimanual tactile grippersto capture both global motion and contact-induced local deformations.  \nLeveraging a novel markerless visuotactile 3D tracking pipeline to extract dense geometry and motion, we systematically evaluate current state-of-the-art world models, comparing 2D video models against 3D particle models. Finally, we provide a preliminary demonstration indicating the real-world applicability of our dataset by performing robot planning tasks on deformable objects. Our analysis reveals key insights into the trade-offs between structural priors and scalability, providing a solid benchmark for future research in generalizable deformable objectcentric world modeling. Project website: [https://deform360.lhy.xyz](https://deform360.lhy.xyz)  \nKeywords: World Models · Deformable Object Manipulation · Visuotactile Perception  \n1 Introduction  \nWorld modeling (i.e., action-conditioned future prediction) has emerged as a powerful paradigm for robots to simulate environments and plan actions [3, 4, 32,38] . Despite recent progress, accurately predicting the behavior of deformable  \n2 H. Li et al.  \nGripper Action Gripper Action  \nDeform360  \nManipulation Goal  \nMonocular Input  \nModel Predictive Control  \nFig. 1: Overview of Deform360 . We collect a massive multi-view visuotactile dataset with 198 deformable objects (a subset is shown), supporting 2D and 3D world models, contact detection, and real-world robot planning tasks.  \nobjects remains a significant challenge [14, 19, 60] . Deformable bodies possess theoretically infinite degrees of freedom, and contact-induced local deformations are frequently occluded by end-effectors or the object itself [13, 31, 56] . Consequently, capturing deformable dynamics accurately has attracted significant interest, particularly via tactile sensing to observe occluded interactions and provide ground-truth signals.  \nCurrent models predicting deformable dynamics follow two paradigms: predicting dynamics over 2D pixel space (e.g ., video generation) [35, 51, 68, 71] or 3D geometric space [9, 30, 45, 85, 86] . Evaluating their relative strengths requires diverse, large-scale, multi-view real-world datasets, which are essential for verifying generalizability and extracting ground-truth 3D states. However, existing datasets often lack object diversity [6, 9, 30, 52, 84], rely on synthetic data [5, 32, 45, 46, 66, 89], or miss high-fidelity annotations and contact-induced deformation modeling [12, 38, 43, 47] .  \nTo address this, we present Deform360, a massive and diverse visuotactile dataset for large-scale deformable dynamics modeling. The dataset encompasses 198 daily-use objects across 1,980 interaction sequences, spanning a wide spectrum of materials","cbCailZnP5AGcK6r","https://ap.wps.com/l/cbCailZnP5AGcK6r","pdf",34160032,1,41,"English","en",105,"# Introduction\n## Dataset Overview\n## Related Work and Limitations\n## Method and Evaluation\n## Robot Planning Demonstration","[{\"question\":\"What problem does Deform360 address in robotic world modeling?\",\"answer\":\"Deform360 targets accurate prediction of deformable object dynamics, where high-dimensional states and contact-induced local deformations are difficult to model and observe.\"},{\"question\":\"What does the Deform360 dataset include?\",\"answer\":\"It includes 198 daily-life deformable objects, 1,980 interaction sequences, and 215+ hours of visuotactile recordings captured by 41 surround-view cameras and bimanual tactile grippers.\"},{\"question\":\"How are 2D and 3D world model approaches evaluated with Deform360?\",\"answer\":\"A markerless visuotactile 3D tracking pipeline extracts dense geometry and motion, enabling systematic comparisons between 2D video models and 3D particle models.\"}]",1784184313,103,{"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},"deform360-a-massive-multi-view-visuotactile-dataset-for-deformable-world-models","",{"@graph":35,"@context":85},[36,53,68],{"@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/deform360-a-massive-multi-view-visuotactile-dataset-for-deformable-world-models/82955/",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","2026-07-17","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 Deform360 address in robotic world modeling?","Question",{"text":75,"@type":76},"Deform360 targets accurate prediction of deformable object dynamics, where high-dimensional states and contact-induced local deformations are difficult to model and observe.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What does the Deform360 dataset include?",{"text":80,"@type":76},"It includes 198 daily-life deformable objects, 1,980 interaction sequences, and 215+ hours of visuotactile recordings captured by 41 surround-view cameras and bimanual tactile grippers.",{"name":82,"@type":73,"acceptedAnswer":83},"How are 2D and 3D world model approaches evaluated with Deform360?",{"text":84,"@type":76},"A markerless visuotactile 3D tracking pipeline extracts dense geometry and motion, enabling systematic comparisons between 2D video models and 3D particle models.","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},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"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":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]