[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85091-en":3,"doc-seo-85091-105":30,"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":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},85091,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","HoloTetSphere: Unified TetSphere Mesh Reconstruction for Physical Simulations","Physics-ready 3D reconstruction pipelines often split surface extraction from tetrahedralization, leaving the final volumetric meshing step vulnerable to errors. Lagrangian approaches such as TetSphere Splatting attempt to optimize volumetric primitives directly, but homeomorphic constraints block topology-adaptive learning, producing disconnected tetrahedra instead of a single connected mesh. HoloTetSphere introduces end-to-end topology and geometry optimization: Gaussian spheres coupled to tetrahedral elements estimate a continuous opacity field for differentiable pruning, while alternating mesh smoothing and multi-view Gaussian rendering loss preserve topological adaptivity. Extensive experiments show improved geometric accuracy and unified, topologically coherent meshes that better support downstream physical simulation.","HoloTetSphere: Unified TetSphere Mesh Reconstruction for Physical Simulations  \nYaQiao Dai 1⋆, Renjiao Yi 1 ⋆ , Zhirui Gao 1 , Wei Chen 1 , Kai Xu2 , and Chenyang  \nZhu 1 ⋆⋆  \n1 National University of Defense Technology, Changsha, China  \n2 Institute of AI for Industries, Chinese Academy of Sciences, Nanjing, China  \narXiv :2607 .08398v 1 [ cs .GR] 9 Jul 2026  \nInitial Final  \nImage Inputs TetSphere  \nInitial Final Physical Simulation  \nHoloTetSphere  \nFig. 1: Unlike TetSphere’s initialization-dependent topology, our method generates holistic tetrahedral meshes through adaptive topology optimization during reconstruction, producing unified and topologically coherent volumetric meshes suitable for downstream physical simulation.  \nAbstract. Standard pipelines for physics-ready 3D reconstruction rely on a decoupled two-stage paradigm: extracting surface geometry followed by an error-prone tetrahedralization process. While recent Lagrangian methods like TetSphere Splatting attempt to bypass this by directly optimizing volumetric primitives, their homeomorphic constraints prevent topology-adaptive optimization. Consequently, they produce disjoint tetrahedra rather than a single connected mesh, rendering the structures unsuitable for further physical simulations. To address this, we propose a topology-adaptive framework for holistic tetrahedral mesh reconstruction through end-to-end topological and geometric optimization. First, by coupling Gaussian spheres to tetrahedral elements and leveraging edge connections, we estimate a continuous opacity field for differentiable element pruning. Next, jointly minimizing mesh smoothing energy and multi-view Gaussian rendering error drives alternating geometric refinement while preserving topological adaptivity. Consequently, our approach effectively constructs a unified and topologically coherent tetrahedral mesh. Extensive experiments demonstrate that our method outperforms state-of-the-art techniques by achieving superior geometric accuracy and producing coherent, single-connected tetrahedral meshes,  \n⋆ Equal contribution.  \n⋆⋆ Corresponding [author.](author. zhuchenyang07@nudt.edu.cn)[ zhuchenyang07@nudt.edu.cn](author. zhuchenyang07@nudt.edu.cn)  \n2 Y. Dai et al.  \nthereby effectively bypassing the error-prone conventional tetrahedralization step for reconstructed surface meshes and streamlining downstream physical simulation.  \nKeywords: Tetrahedral mesh · Volumetric reconstruction · Physical simulation · Topology optimization · Gaussian splatting  \n1 Introduction  \nAccurate 3D shape modeling serves as a cornerstone for numerous applications ranging from virtual reality to physical simulation and robotics. Current approaches primarily fall into two distinct paradigms: Eulerian and Lagrangian representations. Eulerian methods define geometry on a fixed grid structure, where shape information is encoded at predetermined spatial locations, enabling precise topological control but often at significant computational cost. In contrast, Lagrangian representations track geometry through movable elements that deform with the shape, offering computational efficiency but traditionally suffering from limited reconstruction accuracy due to their discrete and disconnected nature. While Lagrangian approaches excel in computation efficiency, their inability to maintain topological consistency and surface integrity has hindered their adoption in applications requiring physically plausible geometry.  \nRecent work by Guo et al. [15] introduced TetSphere Splatting, a promising advancement that bridges this gap by incorporating tetrahedral mesh connectivity into the Lagrangian framework. By representing shape as deformable tetrahedral primitives, TetSphere achieves remarkable reconstruction quality while maintaining the computational advantages of Lagrangian methods. This approach successfully generates high-fidelity meshes with inherent connectivity, addressing a critical limitation of previous point-base","cbCairalUI975g3h","https://ap.wps.com/l/cbCairalUI975g3h","pdf",41204790,2,1,31,"English","en",105,"# Introduction\n## Eulerian vs. Lagrangian representations\n## Limitations of TetSphere Splatting\n## HoloTetSphere: topology-adaptive reconstruction","[{\"question\":\"Why do standard physics-ready 3D reconstruction pipelines struggle with tetrahedral meshing?\",\"answer\":\"They separate surface extraction from tetrahedralization, making the tetrahedralization step error-prone and reducing reliability for physics-ready outputs.\"},{\"question\":\"What prevents TetSphere Splatting from producing topology-adaptive meshes?\",\"answer\":\"Homeomorphic constraints in its optimization hinder true topology adaptation, so it relies on predefined disjoint primitives that depend heavily on initialization quality.\"},{\"question\":\"How does HoloTetSphere achieve unified, topologically coherent tetrahedral meshes?\",\"answer\":\"It couples Gaussian spheres to tetrahedral elements to estimate a continuous opacity field for differentiable element pruning, then alternates geometric refinement using mesh smoothing energy and multi-view Gaussian rendering error to preserve topological adaptivity.\"}]",1784201034,78,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"holotetsphere-unified-tetsphere-mesh-reconstruction-for-physical-simulations","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/holotetsphere-unified-tetsphere-mesh-reconstruction-for-physical-simulations/85091/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-23","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},"Why do standard physics-ready 3D reconstruction pipelines struggle with tetrahedral meshing?","Question",{"text":75,"@type":76},"They separate surface extraction from tetrahedralization, making the tetrahedralization step error-prone and reducing reliability for physics-ready outputs.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What prevents TetSphere Splatting from producing topology-adaptive meshes?",{"text":80,"@type":76},"Homeomorphic constraints in its optimization hinder true topology adaptation, so it relies on predefined disjoint primitives that depend heavily on initialization quality.",{"name":82,"@type":73,"acceptedAnswer":83},"How does HoloTetSphere achieve unified, topologically coherent tetrahedral meshes?",{"text":84,"@type":76},"It couples Gaussian spheres to tetrahedral elements to estimate a continuous opacity field for differentiable element pruning, then alternates geometric refinement using mesh smoothing energy and multi-view Gaussian rendering error to preserve topological adaptivity.","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":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"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":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]