BEGIN:VCALENDAR METHOD:REQUEST PRODID:Microsoft Exchange Server 2010 VERSION:2.0 BEGIN:VTIMEZONE TZID:Central Standard Time BEGIN:STANDARD DTSTART:16010101T020000 TZOFFSETFROM:-0500 TZOFFSETTO:-0600 RRULE:FREQ=YEARLY;INTERVAL=1;BYDAY=1SU;BYMONTH=11 END:STANDARD BEGIN:DAYLIGHT DTSTART:16010101T020000 TZOFFSETFROM:-0600 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;INTERVAL=1;BYDAY=2SU;BYMONTH=3 END:DAYLIGHT END:VTIMEZONE BEGIN:VEVENT ORGANIZER;CN="Bergstrom, Aaron":mailto:aaron.bergstrom@und.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=ai@web3d.o rg:mailto:ai@web3d.org ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=Anita Have le:mailto:anita.havele@web3d.org ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=Nicholas P olys:mailto:npolys@vt.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=Don Brutzm an:mailto:don.brutzman@gmail.com DESCRIPTION;LANGUAGE=en-US:All\,\n\nJust a reminder that we have an AI Work ing Group meeting this week.\n\nProbably the last one we’ll have at 6am Pacific.\n\nI will put Gaussian Splats on the agenda again\, Generative AI \, and discuss link to the Meta YouTube presentation that was mentioned in the MSF AI group today.\n\nMonthly AI Working Group Meeting\nWed\, Dec 17 th\n6am Pacific – 9am Eastern\nhttps://us02web.zoom.us/j/86225731225?pwd =aUh3twfhNUaacXLyJolEof1tsZXSyA.1\n\nAaron\n\n\nFrom: x3d-public On Behalf Of GPU Group via x3d-public\nSent: Sunday\ , November 30\, 2025 11:50 AM\nTo: x3d-ai@web3d.org\nCc: GPU Group \; Extensible 3D (X3D) Graphics public discussion \nSubject: Re: [x3d-public] Gaussian splats\n\nHypothesis: Spl at rendering could be done with Proto containing first node Shape\, and wi th geometry node PointSet with attrib field containing (31.4.2) FloatVerte xAttribute node with 1 float per vertex representing scale \, a Programmab leShader to render points as individually scaled 2D rectangles\, a Script node to parse .ply file to PointSet\, and a new node type FileLoader to lo ad a .ply file for parsing.\n-Doug\nhttps://www.useblurry.com/blog/anatomy -of-a-ply-file\n- shows variant of .ply for gaussian splats\n- John noted Aaron's ply samples don't have spherical harmonic parameters (so a simpler shader)\n\nOn Fri\, Nov 28\, 2025 at 10:24 PM Don Brutzman > wrote:\nJust found several mor e interesting references relating to Gaussian splats.\n\n * NY Times\, Spatial Journalism: A Field Guide To Gaussian Splatting\n * by By A.J. Chavar\, Oscar Durand\, Mint Boonyapanachoti\n * December 16\, 2024\n * Gaussian splatting holds a lot of promise for 3D recreation and spatia l storytelling. It’s faster and more photorealistic than photogrammetry\ , and much easier to process and interact with than neural radiance fields — giving journalists and readers the best of both worlds.\n * These advantages are due to the novel way that splats reconstruct 3D scenes. In a splat\, people\, places\, and objects are made up of a point cloud defin ed by gaussian functions. Each gaussian function is essentially a 2D disc assigned to a point in 3D space with attributes for orientation\, color\, transparency\, and size. When viewed in aggregate\, these coalesce into a 3D scene that can very accurately represent certain things that other volu metric captures cannot: reflection\, transparency\, fine detail and the qu alities of the light in a scene.\n * In this guide\, we give an overvie w of the practical takeaways we learned exploring exploring gaussian splat ting for spatial journalism. We tested a variety of capture and processing techniques using a variety of hardware and software\, and found solutions on desktop and mobile devices. We also assessed splatting against the ben chmarks we typically associate with photogrammetry\, the current standard for 3D recreation.\n * https://rd.nytimes.com/projects/gaussian-splatti ng-guide\n\n * NY Times\, Spatial Journalism: Pushing the Limits of G aussian Splatting for Spatial Storytelling\n * By AJ Chavar\, Mint Boon yapanchoti\, Juan Cabrera\, Oscar Durand\, Yasmin Elayat\, Claudia Miranda \, Kojo Opuni\n * December 16\, 2024\n * Abstract. Advancements in capturing and rendering 3D scenes have the potential to create spatial st ories faster and more easily than has previously been possible. Building o ff of our earlier experiments with photogrammetry and neural radiance fiel ds (NeRF)\, R&D\, with support from the Graphics Department\, set out to u nderstand gaussian splatting and continue to explore the future of photogr aphy and 3D media. Modern gaussian splatting caught our eye after "3D Gaus sian Splatting for Real-Time Radiance Field Rendering" was named one of th e best papers of SIGGRAPH 2023. While photogrammetry is a tried-and-tested method\, it’s extremely labor- and compute- intensive\, and it reliably fails to reconstruct certain textures and settings. NeRF technology addre sses some of these concerns\, but is extremely difficult to deliver these radiance fields to audiences. We wanted to see how splatting fared under s imilar circumstances.\n * https://rd.nytimes.com/projects/gaussian-spla tting\n\n * 3D Gaussian Splatting for Real-Time Radiance Field Renderin g\n * SIGGRAPH 2023 (ACM Transactions on Graphics)\n * Bernhard Kerb l* 1\,2 Georgios Kopanas* 1\,2 Thomas Leimkühler3 George D rettakis1\,2\n * Abstract. Radiance Field methods have recently revolu tionized novel-view synthesis of scenes captured with multiple photos or v ideos. However\, achieving high visual quality still requires neural netwo rks that are costly to train and render\, while recent faster methods inev itably trade off speed for quality. For unbounded and complete scenes (rat her than isolated objects) and 1080p resolution rendering\, no current met hod can achieve real-time display rates.\n * We introduce three key ele ments that allow us to achieve state-of-the-art visual quality while maint aining competitive training times and importantly allow high-quality real- time (≥ 100 fps) novel-view synthesis at 1080p resolution.\n * First\ , starting from sparse points produced during camera calibration\, we repr esent the scene with 3D Gaussians that preserve desirable properties of co ntinuous volumetric radiance fields for scene optimization while avoiding unnecessary computation in empty space\; Second\, we perform interleaved o ptimization/density control of the 3D Gaussians\, notably optimizing aniso tropic covariance to achieve an accurate representation of the scene\; Thi rd\, we develop a fast visibility-aware rendering algorithm that supports anisotropic splatting and both accelerates training and allows realtime re ndering. We demonstrate state-of-the-art visual quality and real-time rend ering on several established datasets.\n * https://repo-sam.inria.fr/fu ngraph/3d-gaussian-splatting\n\n UID:040000008200E00074C5B7101A82E0080000000010D1D6CAE06DDC01000000000000000 010000000AF4FE0089165C9439C9DC906C742DF52 SUMMARY;LANGUAGE=en-US:Monthly X3D-AI Meeting DTSTART;TZID=Central Standard Time:20251217T080000 DTEND;TZID=Central Standard Time:20251217T090000 CLASS:PUBLIC PRIORITY:5 DTSTAMP:20251215T223713Z TRANSP:OPAQUE STATUS:CONFIRMED SEQUENCE:1 LOCATION;LANGUAGE=en-US:Zoom Link - https://us02web.zoom.us/j/86225731225?p wd=aUh3twfhNUaacXLyJolEof1tsZXSyA.1 X-MICROSOFT-CDO-APPT-SEQUENCE:1 X-MICROSOFT-CDO-OWNERAPPTID:951044073 X-MICROSOFT-CDO-BUSYSTATUS:TENTATIVE X-MICROSOFT-CDO-INTENDEDSTATUS:BUSY X-MICROSOFT-CDO-ALLDAYEVENT:FALSE X-MICROSOFT-CDO-IMPORTANCE:1 X-MICROSOFT-CDO-INSTTYPE:0 X-MICROSOFT-DONOTFORWARDMEETING:FALSE X-MICROSOFT-DISALLOW-COUNTER:FALSE X-MICROSOFT-REQUESTEDATTENDANCEMODE:DEFAULT X-MICROSOFT-ISRESPONSEREQUESTED:TRUE X-MICROSOFT-LOCATIONS:[{"DisplayName":"Zoom Link - https://us02web.zoom.us/ j/86225731225?pwd=aUh3twfhNUaacXLyJolEof1tsZXSyA.1"\,"LocationAnnotation": ""\,"LocationUri":""\,"LocationStreet":""\,"LocationCity":""\,"LocationSta te":""\,"LocationCountry":""\,"LocationPostalCode":""\,"LocationFullAddres s":""}] BEGIN:VALARM DESCRIPTION:REMINDER TRIGGER;RELATED=START:-PT15M ACTION:DISPLAY END:VALARM END:VEVENT END:VCALENDAR