[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84525-en":3,"doc-seo-84525-105":29,"detail-sidebar-cat-0-en-105":83},{"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},84525,962075006959,"Anda","https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297",8,"Research & Report","Meshtryoshka Differentiable Rendering of Real World Scenes via Mesh Rasterization","Meshtryoshka introduces a mesh-based differentiable rendering method for reconstructing both object-centric and real-world, unbounded scenes. The approach extracts multiple level sets from a 3D signed distance function, independently rasterizes the resulting triangle meshes with a non-differentiable rasterizer, then alpha-composites the images. Gradients update vertex-related information only through opacities, enabling compatibility with off-the-shelf mesh renderers and producing novel view synthesis quality approaching non-mesh methods.","arXiv :2606 .28622v2 [ cs .CV] 11 Jul 2026  \nMeshtryoshka: Differentiable Rendering of Real-World Scenes via Mesh Rasterization  \nDAVID CHARATAN∗ , Massachusetts Institute of Technology, United States DANIEL XU∗ , Massachusetts Institute of Technology, United States RICHARD SZELISKI, University of Washington, United States GEORGE KOPANAS, Google DeepMind, United States  \nVINCENT SITZMANN, Massachusetts Institute of Technology, United States  \nInitialization  Mesh-Based Differentiable Rendering  Final Model  \nFig. 1. We present Meshtryoshka, a mesh-based differentiable rendering method that is capable of reconstructing both object-centric and real-world scenes. Our method extracts multiple level sets of a signed distance function, individually renders the resulting triangle meshes using a non-differentiable rasterizer, and then alpha-composites the resulting images to produce a rendered view. Unlike previous mesh-based differentiable renderers, our method is able toreconstruct real-world, unbounded scenes.  \nDifferentiable rendering has emerged as a powerful approach for 3D reconstruction and novel view synthesis. Today, state-of-the-art differentiable rendering methods combine a variety of custom representations of 3D geometry and appearance with specialized renderers. However, most downstream tasks in computer graphics rely on 3D meshes, which provide superior portability, allow for hardware-accelerated rendering, and are at the core of most computer graphics workflows. While prior work has attempted differentiable rendering with mesh representations, these approaches are limited to object-centric scenes and fail to reconstruct large-scale, unbounded scenes. In this work, we introduce Meshtryoshka, a novel mesh differentiable rendering framework that combines an off-the-shelf triangle rasterizer with a 3D representation that consists of nested mesh shells which resemble a  \n∗ Equal contribution; order decided by coin flip.  \nAuthors’ Contact Information: David Charatan, Massachusetts Institute of Technology, Cambridge, Massachusetts, United States, [charatan@mit.edu](charatan@mit.edu); Daniel Xu, Massachusetts Institute of Technology, Cambridge, Massachusetts, United States, [danielxu@mit.edu](danielxu@mit.edu); Richard Szeliski, University of Washington, Seattle, Washington, United States, [szeliski@cs.washington.edu](szeliski@cs.washington.edu); George Kopanas, Google DeepMind, San Francisco, California, United States, [george.kopanas@gmail.com](george.kopanas@gmail.com); Vincent Sitzmann, Massachusetts Institute of Technology, Cambridge, Massachusetts, United States, [sitzmann@mit.edu](sitzmann@mit.edu).  \nmatryoshka doll. In every forward pass, the mesh shells are extracted anew from a 3D signed distance function via iso-surface extraction, and the opacities for each vertex are computed as a function of signed distance. Each mesh shell is then rasterized independently, and the final image is created via alpha compositing. Crucially, mesh vertex positions are updated only indirectly via gradients that flow through the opacity values into the signed distance function, and hence, our method is compatible with off-the-shelf mesh renderers that need not be differentiable with respect to vertex positions. On object-centric scenes, our method performs competitively with surface-based differentiable rendering techniques. Our differentiable mesh rendering method scales to unbounded, real-world 3D scenes, where it yields high-quality novel view synthesis results approaching those of state-of-theart, non-mesh methods. Our method suggests that it may be possible to solve the differentiable rendering problem without relying on specialized renderers, only using conventional tools from the computer graphics toolbox. Project website: [https://danielxu9393.github.io/meshtryoshka-website/](https://danielxu9393.github.io/meshtryoshka-website/) .  \nCCS Concepts: • Computing methodologies → Rendering.  \nAdditional Key Words and Phrases: novel","cbCaiaNlIgaMm7Ow","https://ap.wps.com/l/cbCaiaNlIgaMm7Ow","pdf",19777377,1,10,"English","en",105,"# Initialization\n# Mesh-Based Differentiable Rendering\n# Final Model\n# Introduction","[{\"question\":\"How are mesh vertex positions updated while keeping compatibility with non-differentiable mesh renderers?\",\"answer\":\"Vertex positions are not directly differentiated; instead, gradients flow through computed opacities as functions of signed distance back into the signed distance function. This indirect update makes the method compatible with off-the-shelf rasterizers that need not be differentiable w.r.t. vertex positions.\"}]",1784196375,25,{"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":78,"head_meta":80,"extra_data":82,"updated_unix":27},"meshtryoshka-differentiable-rendering-of-real-world-scenes-via-mesh-rasterization","",{"@graph":35,"@context":77},[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/meshtryoshka-differentiable-rendering-of-real-world-scenes-via-mesh-rasterization/84525/",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],{"name":72,"@type":73,"acceptedAnswer":74},"How are mesh vertex positions updated while keeping compatibility with non-differentiable mesh renderers?","Question",{"text":75,"@type":76},"Vertex positions are not directly differentiated; instead, gradients flow through computed opacities as functions of signed distance back into the signed distance function. This indirect update makes the method compatible with off-the-shelf rasterizers that need not be differentiable w.r.t. vertex positions.","Answer","https://schema.org",{"og:url":51,"og:type":79,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":81,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,112,115,120,123,126],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":45,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":45,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":108,"doc_module":4,"doc_module_name":45,"category_name":109,"show_sort_weight":110,"slug":111},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":113,"slug":114},30,"research-report",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":45,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":21,"slug":125},"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":98,"slug":129},19,"General","general"]