Digital landscapes created by driving around in Haspengouw Belgium. Working around the theme of world simulations.
Digital landscapes created by driving around in Haspengouw Belgium. Working around the theme of world simulations.
During this Education Session, hosted by the Forum's 3D Assets Working Group, members from The Khronos Group, Alliance for OpenUSD (AOUSD), and MPEG gave their latest updates on various Gaussian splats efforts.
https://youtu.be/f7tn0MA8TXM?si=yezT9st7e0obYudw
#gaussian #splats #splatting #3D #graphics

GSWT: Gaussian Splatting Wang Tiles
https://yunfan.zone/gswt_webpage/
#HackerNews #GSWT #Gaussian #Splatting #Wang #Tiles #computergraphics #machinelearning #technology #innovation
Apple uses 3D Gaussian splatting for Personas and 3D conversions of photos
#HackerNews #Apple #3D #Gaussian #Splatting #Personas #VirtualReality #TechInnovation
Voyager: Real-Time Splatting City-Scale 3D Gaussians on Your Phone
https://arxiv.org/abs/2506.02774
#HackerNews #Voyager #RealTime #Splatting #3D #Gaussians #Mobile #Technology
3D Gaussian Splatting (3DGS) is an emerging technique for photorealistic 3D scene rendering. However, rendering city-scale 3DGS scenes on mobile devices, e.g., your smartphones, remains a significant challenge due to the limited resources on mobile devices. A natural solution is to offload computation to the cloud; however, naively streaming rendered frames from the cloud to the client introduces high latency and requires bandwidth far beyond the capacity of current wireless networks. In this paper, we propose an effective solution to enable city-scale 3DGS rendering on mobile devices. Our key insight is that, under normal user motion, the number of newly visible Gaussians per second remains roughly constant. Leveraging this, we stream only the necessary Gaussians to the client. Specifically, on the cloud side, we propose asynchronous level-of-detail search to identify the necessary Gaussians for the client. On the client side, we accelerate rendering via a lookup table-based rasterization. Combined with holistic runtime optimizations, our system can deliver low-latency, city-scale 3DGS rendering on mobile devices. Compared to existing solutions, Voyager achieves over 100$\times$ reduction on data transfer and up to 8.9$\times$ speedup while retaining comparable rendering quality.
'gsplat: An Open-Source Library for Gaussian Splatting', by Vickie Ye et al.
http://jmlr.org/papers/v26/24-1476.html
#gsplat #gaussian #splatting
Raymond Fei from Adobe will present at the 3D Asset Interoperability Working Group on February 19th on Gaussian Splatting in Adobe Substance 3D Viewer. All MSF members are welcome to attend!
Not a member? Join us: https://metaverse-standards.org/members/
#Gaussian #splats #splatting
A really exciting piece of #Gaussian #Splatting research, by Lan et al. 2025
3DGS²: Near Second-order Converging 3D Gaussian Splatting
https://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.