3D Gaussian Splat tech is getting wild. What are the projected real-world practical use cases for it?
Off the top of my head:
-Real-estate, Airbnb, event spaces
-Ecommerce product viz
-Virtual camera moves
What else?
🚀Tired of floaters, flickering, and blur in 3DGS? We introduce a geometry-informed video generator that refines 3DGS renderings in the wild. 🎥✨
We let the video model actually "see" the rendering process using a Gaussian Primitive buffer. #CVPR2026@CVPR
Project page: https://t.co/IjE8h0QVuS
🔥 Highlights:
✅ Geometry-Buffer-conditioned video generator
✅ Refines optimization-based & feed-forward 3DGS
✅ Novel artifact simulation pipeline
✅ Highly efficient bidirectional processing ⚡
Thread 👇
The web has become a #GaussianSplatting playground.
I love seeing all these experiments coming out from the @playcanvas team and just confirm my thoughts: if you want to deploy 3DGS, your best bet at the moment is the web 😉.
Articraft for scene reconstruction 🏠
Last year we built LiteReality (https://t.co/GWoIV32GAc): an agentic pipeline for graphics-ready indoor recon, but objects weren't articulated.
once @Mattzh1314 showed how well Articraft 🦾works with images, we combined them for scene recon🔥
🤩Excited to share SANA-WM: a 2.6B open-source world model for minute-scale 720p video generation.
Given one image + text + a 6-DoF camera trajectory, it synthesizes action-controllable 60s worlds on a single GPU.
Project: https://t.co/5NINfiFoTK
Paper: https://t.co/JKczmyRsJL
Hoy una industria entera dejó de tener sentido.
Un tío publicó en GitHub un repo que convierte cualquier foto en un mundo 3D explorable: meshes con físicas, splat del fondo, audio ambiente. Todo.
Una imagen entra. Un mundo sale. Cinco minutos.
La gente que se pasó diez años aprendiendo Blender lleva todo el día mirando esto en silencio.
Se llama image-blaster.
We made an interactive client-server viewer for LagerNVS with @JonathonLuiten!
You can now interactively explore scenes from just a photo capture - no optimization, no 3D Gaussians, just load your images, run the model on a cloud GPU and stream the renders to your local browser.
Check out the video below for some spaces I recently captured in Oxford, London and beyond!
Generate an interactive 3D world ✨
I opened this project in Cursor and uploaded an image of a cozy bookstore.
The agent then generated the environment, chose objects to turn into 3D meshes, added colliders, and created sound effects 🤯
3D Gaussian Splatting Mesh 3.0, more results coming in.
The main improvements: smoother large surfaces, better structure retention on thin geometry, and less broken mesh overall. Side-by-side with 2.0 in the video below, thin details is where it really shows.
Full showcase: https://t.co/vFVEo5fJTS
This is what the algorithm change actually looks like in practice.
Yesterday, in the excitement, I didn't realize that a @threejs visualizer to preview with physics/sfx was included 🤦
Today, I've implemented a simple node inspector to see what providers (Fal / Worldlabs) & models (Marble 1.1, nano banana 2, hunyuan3d-v3, elevenlabs) it's using.
3d gaussian splats + photogrammetry can work together beautifully – you don’t have to choose.
I’m using a drone capture for the hero asset. Google maps aerial photogrammetry for the world around it.