home.social

#gaussian — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #gaussian, aggregated by home.social.

fetched live
  1. 3D Formats member, Adam Morris (Bentley Systems/Cesium) sits down with host Muthu Kumar (Geoawesome) to break down how 3D Gaussian Splatting works, why it outperforms traditional 3D models in complex visual inspection tasks, and how ‪Khronos is standardizing the technology via a new glTF extension.

    youtu.be/a7bAUMbMEec?si=k25Nk_

  2. We are live at ! Come see us in Booth #1041 and talk to us about the latest news for glTF, OpenXR, Vulkan and the OMBI Sneeze metaverse browser. We also have cool luggage tags you can pick up.

    Learn more about Khronos' activities at AWE: khronos.org/events/highlights2

  3. Join developers and integrators from around the world at the 2026 Cesium Developer Conference in Philadelphia, where the community comes together to shape the future of open geospatial technologies.

    Khronos' glTF and work in Gaussian Splatting will be featured prevalently throughout the conference, especially in the Product Roadmaps and Advanced Technologies Track. Explore Cesium's event page for more information: cesium.com/events/cesium-devel

  4. Lightweight urban modeling and rendering with proxy buildings and Gaussian residuals for efficient and high-quality urban scene recreation #gaussian

    github.com/LiYukeee/CityGo

  5. #Gaussian splats viewer that works in your terminal. Yes, it's made of symbols!

    github.com/buildoak/tortuise

    Make your terminal happy!

  6. Calling all programmers!

    Khronos Group is hosting "3D on the Web" -- an evening of talks, demos & networking around , & splats.

    March 11 · 5:30-9:30 PM PDT
    Easy 12 minute walk from GDC in
    San Francisco

    Learn more and register: khr.io/1ne

  7. We are seeking short talks, demos, and presentations that showcase real world use of , , , and Splatting on the web for the 3D on the Web special event during the week of GDC.

    If you are building something interesting and would like to share it with the community, we would love to hear from you. Please note that sales forward presentations are unlikely to be selected.

    To submit a 10 minute talk or demo, please email your description to [email protected]

  8. The Khronos Group has announced a liaison agreement with the UHD World Association (UWA). The liaison establishes a framework for collaboration and information exchange as emerging media types increasingly combine elements of video and 3D technologies in sophisticated new ways.

    Learn more: khr.io/1ml

  9. Our paper reformulates #Gaussian processes as a form of procedural noise -- specifically, sparse convolution noise, simulated by placing kernels at random locations. This allows us to leverage the decades of work in graphics on efficient procedural noise synthesis and to express GPISes in a language familiar to practitioners in our field. [3/7]

  10. Today is the day! Join us in East Building, Room 8 of the Vancouver Convention Centre starting at 10:45 for a discussion of the current state of technologies, formats, and use cases to guide the evolution of Gaussian splat interoperability.

    khronos.org/events/siggraph-20

  11. 3D Gaussian Splats leading organizations across the geospatial, graphics, and standards domains — including Khronos Group, Open Geospatial Consortium (OGC), Niantic Spatial, Cesium, and Esri have come together to integrate 3D Geospatial Gaussian Splats into Khronos’ widely adopted glTF 3D asset format standard. This collaborative initiative aims to create a standardized, interoperable framework for encoding and sharing 3D Gaussian Splats.

    khr.io/1lp

  12. The almost perfect #Gaussian distribution here tells me I might have actually structured a #poll correctly. ^___^

    #LossyPNG

  13. 2025 One Hertz Challenge: Metronalmost is Gunning for Last Place - We’ve just begun to receive entries to the One Hertz Challenge, but we already hav... - hackaday.com/2025/07/15/2025-o #clockhacks #metronome #contests #gaussian #esp-12e

  14. 'Linear cost and exponentially convergent approximation of Gaussian Matérn processes on intervals', by David Bolin, Vaibhav Mehandiratta, Alexandre B. Simas.

    jmlr.org/papers/v26/24-1779.ht

    #gaussian #prediction #approximate

  15. 'Feature Learning in Finite-Width Bayesian Deep Linear Networks with Multiple Outputs and Convolutional Layers', by Federico Bassetti, Marco Gherardi, Alessandro Ingrosso, Mauro Pastore, Pietro Rotondo.

    jmlr.org/papers/v26/24-1158.ht

    #gaussian #gaussians #convol