ΛПĐY

AndyShaw.

[Will Eastcott @willeastcott]

Splats are getting larger and more detailed. The dataset for this scan of Koriyama Castle in Japan is half a gigabyte. But it loads nearly instantly. Imagine being able to visit perfect digital copies of any location in the world - this is where SuperSplat is heading.
[1 / 2]

[Crysta AI 🧊 3D Printing @Crysta_AI]

It is like holding a window to another world in the palm of your hand. 🧊

Stunning work by @VoxelKei on this Four-seasons landscape. These pieces perfectly demonstrate the magic of 3DGS materialization: capturing the true volumetric depth and ambient light of a landscape.

Always an honor to bring your environments into the physical world! Thank you @VoxelKei and @sekiguchiaimi!

[Crysta AI 🧊 3D Printing @Crysta_AI]

A closer look. 🔎

We grabbed this quick macro video on an iPhone to show the internal structures. Notice how the light scatters through the "trees" just like a real forest.

[filipe @filicroval]

🤖 wake up, new 4d tool!

Take any normal 2D video → instantly turn it into fully explorable 3D space.

You can now orbit, tilt, and view the scene from angles that literally never existed in the original footage.

This is 4D Gaussian Splatting (from 4dv) and it’s next-level.

[Jake Fitzgerald @earthtojake]

new release for text-to-cad, an open source CAD harness and skills for codex / claude:

- mechanism validation (go from text prompt to functional mechanical design)
- parameters + animations for step files
- extended sdf, srdf, urdf support

3k stars, 10k downloads, we cooking

[Richie Rich @gofishh77]

This is wild! Even before the crazy jump he has to suit up on the ledge. Just takes one wrong move. No thanks!

[Dan Kornas @DanKornas]

Single-photo 3D scene reconstruction is still painfully manual.

3D-RE-GEN is an MIT-licensed research codebase for reconstructing complete, editable indoor 3D scenes from one photograph.

It helps you test an end-to-end reconstruction pipeline by combining instance segmentation, context-aware generative inpainting, 2D-to-3D asset creation, camera extraction, constrained optimization, and Blender rendering.

Key features:

• Single-photo input – starts from one indoor scene image instead of requiring a full capture setup
• Object-level reconstruction – segments objects, creates cropped inputs and masks, then generates 3D assets
• Scene completion path – uses inpainting and background reconstruction to fill context around objects
• Geometry + camera steps – includes VGGT camera extraction, point clouds, and constrained scene optimization
• Step-based pipeline – run stages 1-9 for segmentation, generation, rendering, and optional MIDI evaluation

The source code is open-source (MIT license); third-party models and assets have separate licenses.

Link in the reply 👇

[Bilawal Sidhu @bilawalsidhu]

Woot! You can now simulate real world places by grounding Genie 3 experiences with Street View imagery.

Google sitting on the mother lode of real world data, and is starting to put it to work!

Let's dive into some prompts & locations I tested...

[Yaël Bienenstock @YaelBienenstock]

For years I've been taking selfies of my outfits just to remember what I wore or share with friends. Camera roll: thousands of pictures, zero of them findable. So i built the thing i wanted. Meet Yafa 🧵

[Justine Moore @venturetwins]

Here's the link to try it: https://t.co/zglGizJ2cb

[Palmer Luckey @PalmerLuckey]

John Ternus, the new CEO of Apple, has been with the company for 25 years. His only non-Apple job was four years in the late 90s at Virtual Research, a tiny Virtual Reality HMD outfit.

From what I can tell, he was the lead mechanical engineer on the V8 I obtained when I was 16!

[ΛПĐY @_Andy_Shaw]

@ty_kra_lab https://t.co/3cmU40Zf3f this is a similar concept..

[VoxelKei @VoxelKei]

3D Gaussian Splattingを読み込んでガラスケースに入れたりカラーグレーディングした上でエクスポート出来るwebアプリ「Spatialograph Maker」を作ったので公開します。空間をどう切り取ると作品としていい感じになるだろうか、とか模索したりできます。#GaussianSplatting https://t.co/XQ0D8TwJla

[ΛПĐY @_Andy_Shaw]

@ty_kra_lab The real world manufacturing of these objects is a process called subsurface laser etching.

[ΛПĐY @_Andy_Shaw]

@ty_kra_lab I agree with this method of saving your spatial memories., 3 dimensional screenshot. A tangible object.

[Takashi Yoshinaga @Tks_Yoshinaga]

Hosting a 3D Gaussian Splatting study session soon. Made a quick video comparing point cloud vs Gaussian Splats vs trained result, all with the same number of points. Hope it sparks some interest in #3DGS among the attendees.

[Robert Scoble @Scobleizer]

Holy shit.

Now everyone will be able to use their @OpenClaws and all the other agentic platforms to build apps on top of X.

Here's the secret: build lists.

Lists are how you build apps.

The pattern:

Build a list of your favorite football team. Or whatever you are into.

Then ask your AI agents "build an app showing me all the important news about my favorite football team."

In minutes you'll have an app.

And that's just the beginning.

Your agent can build a script about your favorite football team that you can take to places like Google's Notebook LM.

Now you have a video, a podcast, a slide deck, a game, a mind map. All about your favorite football team based on real time news.

You can do the same with something like @HeyGen, create an avatar of your favorite football player. Now you will have your favorite football player telling you everything that's happening on the football team.

And I could go for hours about how many things you can build and not even cover a fraction of them.

This is huge.

Thank you @elonmusk for making it possible to make millions of agentic apps affordably on top of X.

Start building!

[Robert Scoble @Scobleizer]

The founder of Niantic built Google Earth.

He has been building this for years.

I got a demo. It is stunning.

And is the platform that will bring us infinite realities.

I call it the Holodeck.

[Linus ✦ Ekenstam @LinusEkenstam]

Architects are AI maxxing.

Turning rubble into precious building material in no time at all.

by Philmann Architects and Taaod Studio.

[VoxelKei @VoxelKei]

VRChatの世界を高速に3DGS化する仕組みを作ってます。かなり綺麗に再構築出来そう。LichtFeld Studioで3DGSトレーニングして、Spatialograph Makerでガラスに封入、さらにこれを3Dプリントすれば世界が広がるんじゃないかな。

[Brian Bartholomew @BPBartholomew]

Every dot is a piece of grid infrastructure. Every line carries gas, power, or data.

Built on public data from @openstreetmap, @GlobalEnergyMon, @EIAgov, and more.