home.social

#splatting — Public Fediverse posts

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

  1. Digital landscapes created by driving around in Haspengouw Belgium. Working around the theme of world simulations.

    #Gaussian #Splatting #Landscape #Digital

  2. Wow, groundbreaking news! 🎉 #GitHub now does *real-time* #splatting and paints pretty pictures with math—because everyone knows Gaussian blur was just too slow and you're definitely going to splat your way to software nirvana. 🙄 Meanwhile, they forgot to tell you: Splats won't fix your spaghetti code. 🍝
    github.com/axbycc/LiveSplat #RealTime #GaussianBlur #SoftwareNirvana #SpaghettiCode #HackerNews #ngated

  3. Wow, groundbreaking news! 🎉 #GitHub now does *real-time* #splatting and paints pretty pictures with math—because everyone knows Gaussian blur was just too slow and you're definitely going to splat your way to software nirvana. 🙄 Meanwhile, they forgot to tell you: Splats won't fix your spaghetti code. 🍝
    github.com/axbycc/LiveSplat #RealTime #GaussianBlur #SoftwareNirvana #SpaghettiCode #HackerNews #ngated

  4. Wow, groundbreaking news! 🎉 #GitHub now does *real-time* #splatting and paints pretty pictures with math—because everyone knows Gaussian blur was just too slow and you're definitely going to splat your way to software nirvana. 🙄 Meanwhile, they forgot to tell you: Splats won't fix your spaghetti code. 🍝
    github.com/axbycc/LiveSplat #RealTime #GaussianBlur #SoftwareNirvana #SpaghettiCode #HackerNews #ngated

  5. Wow, groundbreaking news! 🎉 #GitHub now does *real-time* #splatting and paints pretty pictures with math—because everyone knows Gaussian blur was just too slow and you're definitely going to splat your way to software nirvana. 🙄 Meanwhile, they forgot to tell you: Splats won't fix your spaghetti code. 🍝
    github.com/axbycc/LiveSplat #RealTime #GaussianBlur #SoftwareNirvana #SpaghettiCode #HackerNews #ngated

  6. A really exciting piece of #Gaussian #Splatting research, by Lan et al. 2025

    3DGS²: Near Second-order Converging 3D Gaussian Splatting

    arxiv.org/pdf/2501.13975

    "[.] we argue that training 3DGS fundamentally differs
    from generic deep learning. Simply “copy-and-paste” the standard [SGD-based] learning procedure for 3DGS is neither efficient nor effective."

    Splits up the scene, no SGD required, really fast convergence.

    Curious to see "only for static scenes" listed first under the limitations.

  7. A really exciting piece of #Gaussian #Splatting research, by Lan et al. 2025

    3DGS²: Near Second-order Converging 3D Gaussian Splatting

    arxiv.org/pdf/2501.13975

    "[.] we argue that training 3DGS fundamentally differs
    from generic deep learning. Simply “copy-and-paste” the standard [SGD-based] learning procedure for 3DGS is neither efficient nor effective."

    Splits up the scene, no SGD required, really fast convergence.

    Curious to see "only for static scenes" listed first under the limitations.

  8. A really exciting piece of #Gaussian #Splatting research, by Lan et al. 2025

    3DGS²: Near Second-order Converging 3D Gaussian Splatting

    arxiv.org/pdf/2501.13975

    "[.] we argue that training 3DGS fundamentally differs
    from generic deep learning. Simply “copy-and-paste” the standard [SGD-based] learning procedure for 3DGS is neither efficient nor effective."

    Splits up the scene, no SGD required, really fast convergence.

    Curious to see "only for static scenes" listed first under the limitations.

  9. A really exciting piece of #Gaussian #Splatting research, by Lan et al. 2025

    3DGS²: Near Second-order Converging 3D Gaussian Splatting

    arxiv.org/pdf/2501.13975

    "[.] we argue that training 3DGS fundamentally differs
    from generic deep learning. Simply “copy-and-paste” the standard [SGD-based] learning procedure for 3DGS is neither efficient nor effective."

    Splits up the scene, no SGD required, really fast convergence.

    Curious to see "only for static scenes" listed first under the limitations.