[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84499-en":3,"doc-seo-84499-105":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},84499,549758146520,"Patrick","https://ap-avatar.wpscdn.com/avatar/80002397d8c0411e94?_k=1775819394049821470",8,"Research & Report","Hierarchical and Holistic Open Vocabulary Functional 3D Scene Graphs for Indoor Spaces","Functional 3D scene graphs represent objects, interactive elements, and functional relationships for 3D understanding and robotic manipulation, but prior benchmarks and pipelines remain limited, especially for hierarchical structures and dense tabletop coverage. This work expands benchmark coverage with dense small objects and explicit multi-level functional relations, introducing challenges from small similar instances, weak visual anchoring, cross-frame instance confusion, and uncertain attribution under dynamic viewpoints. An open-vocabulary pipeline anchors fine-grained functional edges from 2D visual evidence and performs 3D graph optimization with temporal graph formulation, then reshapes global hierarchy to recover structured graphs.","arXiv :2605 . 15753v2 [ cs .RO] 13 Jul 2026  \nHierarchical and Holistic Open-Vocabulary Functional 3D Scene Graphs for Indoor Spaces  \nXinggang Hu 1 ,2⋆, Chenyangguang Zhang3⋆, Alexandros Delitzas3 ,4 , Xiangkui Zhang2 , Marc Pollefeys3 ,5 , Francis Engelmann6 , and Xiangyang Ji 1†  \n1 Tsinghua University, China 2 Dalian University of Technology, China  \n3 ETH Zurich, Switzerland 4 MPI for Informatics, Germany  \n5 Microsoft, Switzerland 6 USI Lugano, Switzerland  \nAbstract. Functional 3D scene graphs offer a versatile and flexible representation for 3D scene understanding and robotic manipulation, defined by object nodes, interactive elements, and functional relationship edges. However, their potential remains underexplored due to the limited coverage of existing benchmarks and the overly straightforward design of previous pipelines, which primarily focus on large-scale furniture but lack of hierarchical structures. Therefore, in this work, we extend the benchmark coverage by introducing dense tabletop objects and explicit multi-level functional relationships. This expansion introduces critical challenges involving small-scale, dense, and similar instances, with lack of visual anchoring in relational reasoning, instance confusion during crossframe fusion, and attribution uncertainty under dynamic viewpoints. To address these issues, we propose an open-vocabulary pipeline based on 2D visual grounding and 3D graph optimization. Specifically, we anchor finegrained functional edges from 2D visual evidence, and associate nodes across frames in 3D using multiple cues. Furthermore, edge association is formulated as temporal graph optimization, integrating evidence accumulation, entropy regularization, and temporal smoothing to robustly determine the functional connections of each node. Finally, global hierarchy shaping is performed to recover the hierarchical graph structure. Extensive experiments demonstrate that the proposed method can reliably infer functional 3D scene graphs in challenging real-world scenes, thereby further unlocking their potential for practical applications. Code is available at [https://github.com/Hbelief1998/HHOpenFunGraph-ECCV26](https://github.com/Hbelief1998/HHOpenFunGraph-ECCV26) .  \nKeywords: 3D Scene Graph · Scene Understanding · Open Vocabulary  \n1 Introduction  \nAs virtual reality, robotics, and embodied intelligence continue to advance, it becomes increasingly vital to develop a versatile and accurate 3D scene repre  \nsentation that bridges the gap between high-level 3D understanding and downstream tasks such as manipulation and content generation. Traditionally, 3D * Equal contribution. †Corresponding author.  \n2 X. Hu et al.  \nFig. 1: Hierarchical and holistic functional 3D scene graphs. In contrast to prior approaches [75], we model tabletop manipulable objects and explicit hierarchical object–part structures in functional 3D scene graphs.  \nscene graphs [2,6,19,32,33,50,51,60,66] have been proposed as discrete graphbased representations of 3D environments, consisting of object nodes and their spatial relationships. While such representations have proven effective for robotic navigation and scene understanding, their coarse granularity limits their applicability to fine-grained tasks such as manipulation.  \nRecently, OpenFunGraph [75] introduced the concept of functional 3D scene graphs by extending traditional scene graphs to include objects, interactive elements, and functional relationships. Although this representation is theoretically flexible and capable of encoding rich semantic and relational properties, its benchmark and pipeline remain limited. The existing setup cannot handle the complexity commonly observed in real-world scenarios. Specifically, the annotations in SceneFun3D [11] and FunGraph3D [75] consider only large furniture items (e.g., cabinets, bathtubs, wardrobes) and lack the tabletop objects that are more common in robotic manipulation tasks. In addition, the intrinsic parton","cbCaifJvT4GmkAjJ","https://ap.wps.com/l/cbCaifJvT4GmkAjJ","pdf",23564568,1,19,"English","en",105,"# Introduction\n## Motivation for hierarchical functional scene graphs\n## Benchmark extension for tabletop objects\n## Key challenges in perception and relational reasoning\n# Proposed approach\n## Open-vocabulary pipeline with visual grounding\n## Temporal graph optimization for edge association\n## Global hierarchy shaping\n# Experiments and results","[{\"question\":\"What is the main goal of the hierarchical and holistic functional 3D scene graph approach?\",\"answer\":\"To infer functional 3D scene graphs that include both tabletop manipulable objects and explicit multi-level object–part hierarchies, improving suitability for robotic manipulation and fine-grained reasoning.\"},{\"question\":\"Why does extending benchmarks to dense tabletop objects and hierarchical structures create new challenges?\",\"answer\":\"Small, similar instances and hierarchical part proliferation lead to visual anchoring failures, 3D bounding box aliasing, instance confusion during cross-frame fusion, and attribution uncertainty when viewpoints change.\"},{\"question\":\"How does the proposed pipeline determine functional relationships in an open-vocabulary setting?\",\"answer\":\"It grounds fine-grained functional edges from 2D visual evidence, associates nodes across frames using multiple cues in 3D, formulates edge association as temporal graph optimization, and finally reshapes the global hierarchy to recover structured graphs.\"}]",1784196088,48,{"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},"hierarchical-and-holistic-open-vocabulary-functional-3d-scene-graphs-for-indoor-spaces","",{"@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/hierarchical-and-holistic-open-vocabulary-functional-3d-scene-graphs-for-indoor-spaces/84499/",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 is the main goal of the hierarchical and holistic functional 3D scene graph approach?","Question",{"text":75,"@type":76},"To infer functional 3D scene graphs that include both tabletop manipulable objects and explicit multi-level object–part hierarchies, improving suitability for robotic manipulation and fine-grained reasoning.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why does extending benchmarks to dense tabletop objects and hierarchical structures create new challenges?",{"text":80,"@type":76},"Small, similar instances and hierarchical part proliferation lead to visual anchoring failures, 3D bounding box aliasing, instance confusion during cross-frame fusion, and attribution uncertainty when viewpoints change.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed pipeline determine functional relationships in an open-vocabulary setting?",{"text":84,"@type":76},"It grounds fine-grained functional edges from 2D visual evidence, associates nodes across frames using multiple cues in 3D, formulates edge association as temporal graph optimization, and finally reshapes the global hierarchy to recover structured graphs.","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":21,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},"General","general"]