Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Everything in this video is real-time 3D rendered in Flutter. No forks, no platform views, no secondary graphics context. Rendering, physics, gaussian splats, DICOM volumes, accessible scenes, embedded widgets, hot reload for every asset, instanced prefabs with arbitrary overrides, and much more. Get started at

Brandon DeRosier

1,340 subscribers

17,339 views • 13 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

This campfire is 100% procedurally generated at runtime with Flutter Scene. No model files, no image assets. Recorded in debug mode. A full 3D engine built entirely on Flutter's built-in graphics API, Flutter GPU. No forks, no native renderer integrations. macOS, Windows, Linux, iOS, Android, web, and custom embedders.

This campfire is 100% procedurally generated at runtime with Flutter Scene. No model files, no image assets. Recorded in debug mode. A full 3D engine built entirely on Flutter's built-in graphics API, Flutter GPU. No forks, no native renderer integrations. macOS, Windows, Linux, iOS, Android, web, and custom embedders.

Brandon DeRosier

10,905 views • 8 days ago

More and more users are turning their 360 footage into fully explorable 3D Gaussian Splats with View it here: This reconstruction started from a simple capture and is now a fully explorable 3D Gaussian Splat rendered in the FreeGaussian viewer, complete with point cloud reconstruction and high-fidelity spatial detail. More and more creators are discovering that their existing footage can become immersive 3D scenes. And they’re doing it for free with FreeGaussian

More and more users are turning their 360 footage into fully explorable 3D Gaussian Splats with View it here: This reconstruction started from a simple capture and is now a fully explorable 3D Gaussian Splat rendered in the FreeGaussian viewer, complete with point cloud reconstruction and high-fidelity spatial detail. More and more creators are discovering that their existing footage can become immersive 3D scenes. And they’re doing it for free with FreeGaussian

Over the Reality 🌐

14,759 views • 2 months ago

The latest free version of UE5 AVATAR is now available! This update enhances real-time rendering quality and adds hundreds of new digital clothing and accessories. Create personalized 3D models, customize outfits, select scenes, and connect AI motion capture for real-time rendered 3D animations. Anyone can create 3D character models—no professional modeling skills required. Future versions will support 3D model import/export and image-based 3D model generation. Get the download link in the comments!

CYANPUPPETS

16,823 views • 1 year ago

BIG NEWS: Introducing SDF-Splats! 🚨 I just solved one of the biggest problems in 3D Gaussian Splatting: GAPS & HOLES! 🕳️❌ My hybrid approach combines: ✨ Explicit Gaussian Splats (for detail) ✨ Implicit SDFs (for continuity) The result? Seamless 3D reconstruction with NO visible holes, NO transparency artifacts, and REAL-TIME performance at 30-60 FPS! 🔥 Traditional Gaussian Splatting looks amazing but breaks apart in under-sampled regions. SDF-Splats fills every gap using on-demand raymarching through signed distance fields—zero preprocessing, zero neural nets, pure GPU magic! ⚡ Read the full research paper: #GaussianSplatting #SDF Radiance Fields MrNeRF #RealTime3D #VR #3DReconstruction #AIResearch

BIG NEWS: Introducing SDF-Splats! 🚨 I just solved one of the biggest problems in 3D Gaussian Splatting: GAPS & HOLES! 🕳️❌ My hybrid approach combines: ✨ Explicit Gaussian Splats (for detail) ✨ Implicit SDFs (for continuity) The result? Seamless 3D reconstruction with NO visible holes, NO transparency artifacts, and REAL-TIME performance at 30-60 FPS! 🔥 Traditional Gaussian Splatting looks amazing but breaks apart in under-sampled regions. SDF-Splats fills every gap using on-demand raymarching through signed distance fields—zero preprocessing, zero neural nets, pure GPU magic! ⚡ Read the full research paper: #GaussianSplatting #SDF Radiance Fields MrNeRF #RealTime3D #VR #3DReconstruction #AIResearch

Daniel Skaale

21,031 views • 8 months ago

Gaussian Splatting is pretty wild. Being able to take dense collections of assets and package them into fast, real-time splats opens up a ton of new possibilities for look-dev, previs, and interactive scenes. For this test, I built a pile of 400 skulls - roughly 40+ million polygons (and over 400 8K texture instances) - rendered out a 600 frame dataset on The Render Network with OTOY OctaneRender and then converted the result into a single splat asset. Now it runs in real-time as one compact Gaussian Splat.

Gaussian Splatting is pretty wild. Being able to take dense collections of assets and package them into fast, real-time splats opens up a ton of new possibilities for look-dev, previs, and interactive scenes. For this test, I built a pile of 400 skulls - roughly 40+ million polygons (and over 400 8K texture instances) - rendered out a 600 frame dataset on The Render Network with OTOY OctaneRender and then converted the result into a single splat asset. Now it runs in real-time as one compact Gaussian Splat.

Spenser Dickerson

46,560 views • 8 months ago

We've built the best in house observability for Stagehand 🔭 Get inference time, token usage, LLM output, and more on the new dashboard. No more black box, see everything behind the scenes. See for yourself, get started with npx create-browser-app 🤘

We've built the best in house observability for Stagehand 🔭 Get inference time, token usage, LLM output, and more on the new dashboard. No more black box, see everything behind the scenes. See for yourself, get started with npx create-browser-app 🤘

Stagehand

10,887 views • 1 year ago

What happens if you try to push and squash a Gaussian splat? :) Been playing with adding simplified deformation and a lightweight physics simulation layer to Gaussian splats, running directly in real time on mobile. Instead of simulating every splat, this uses a small CPU lattice to drive the deformation, plus a per-splat transform so they actually stretch and compress properly. No mesh conversion, no retraining. Just layered on top of the renderer. You can push, bend, squash a scan and it holds together surprisingly well... Still early, but I can see the potential in making splats feel more real, from static captures to something more tactile, something you can touch, throw, bounce around… or well just fold and squash on the floor :) #GaussianSplatting #3DGS #Unity

What happens if you try to push and squash a Gaussian splat? :) Been playing with adding simplified deformation and a lightweight physics simulation layer to Gaussian splats, running directly in real time on mobile. Instead of simulating every splat, this uses a small CPU lattice to drive the deformation, plus a per-splat transform so they actually stretch and compress properly. No mesh conversion, no retraining. Just layered on top of the renderer. You can push, bend, squash a scan and it holds together surprisingly well... Still early, but I can see the potential in making splats feel more real, from static captures to something more tactile, something you can touch, throw, bounce around… or well just fold and squash on the floor :) #GaussianSplatting #3DGS #Unity

𝐑𝐔𝐁𝐄𝐍🥽𝐅𝐑𝐎

51,154 views • 4 months ago

3D scanning and rendering is moving so fast - got my splats up and running and I'm mind blown getting ~100fps for this complex 3D scene ⬇️ 🤯 1. WAY faster than NeRF: For comparison, NeRFs would takes around 10 seconds per frame (!) Instead I'm zipping around with FPV controls without breaking a sweat - though I do crash a few times towards the end of the video lol 2. Old Meets New: Gaussian Splatting is cool in that it fuses classical graphics and deep learning techniques. Like NeRFs, this is still a radiance field - just without the slower (ne)ural rendering part. 3. Explicit Representation: Instead you represent a 3D scene as a collection of ellipsoidal "splats" called gaussians. Each gaussian has a position, size, and color. Rendering in real-time is done by projecting into the image plane and alpha blending. 4. Photorealistic Effects: Gaussian splatting use spherical harmonics to represent the view-dependent effects and lighting - allowing surfaces to change color when viewed from different angles, enabling greater photorealism. It doesn't use a neural network, but the training loop is similar to deep learning. 5. Enables Direct Editing: But it's not just speed - with Gaussian Splatting you also get 3D editing support! So you can select, move, and delete stuff, even relight stuff. This type of editing has been more tedious to do with NeRFs and their implicit black box representations. 📲 More tests cooking! Much more to unpack here including simpler explanations. If you enjoyed this post, you might enjoy my feed: Bilawal Sidhu

3D scanning and rendering is moving so fast - got my splats up and running and I'm mind blown getting ~100fps for this complex 3D scene ⬇️ 🤯 1. WAY faster than NeRF: For comparison, NeRFs would takes around 10 seconds per frame (!) Instead I'm zipping around with FPV controls without breaking a sweat - though I do crash a few times towards the end of the video lol 2. Old Meets New: Gaussian Splatting is cool in that it fuses classical graphics and deep learning techniques. Like NeRFs, this is still a radiance field - just without the slower (ne)ural rendering part. 3. Explicit Representation: Instead you represent a 3D scene as a collection of ellipsoidal "splats" called gaussians. Each gaussian has a position, size, and color. Rendering in real-time is done by projecting into the image plane and alpha blending. 4. Photorealistic Effects: Gaussian splatting use spherical harmonics to represent the view-dependent effects and lighting - allowing surfaces to change color when viewed from different angles, enabling greater photorealism. It doesn't use a neural network, but the training loop is similar to deep learning. 5. Enables Direct Editing: But it's not just speed - with Gaussian Splatting you also get 3D editing support! So you can select, move, and delete stuff, even relight stuff. This type of editing has been more tedious to do with NeRFs and their implicit black box representations. 📲 More tests cooking! Much more to unpack here including simpler explanations. If you enjoyed this post, you might enjoy my feed: Bilawal Sidhu

Bilawal Sidhu

337,090 views • 2 years ago

2026 is the year of the splat! This is a single patch of moss - scanned top and bottom - turned into a fully modular 3D asset. Flip it one way and it’s lush moss. Flip it the other and it’s damp, detailed soil. Both sides are real. No fake backsides. No tiling tricks. Ultra-lightweight. Fully real-time. Clones cleanly across geometry. And here’s the key difference - splats don’t really care about intersections. Coplanar overlaps don’t break the asset, they add density and realism. To match this traditionally with 3D you’d need thousands of moss scatters or extremely dense geo - and it would still feel off. One splat patch scales into massive 3D plates with almost no resource cost. This is asset development going forward - modular, DCC-agnostic, and built for modern pipelines. Download the moss scan for free on Gumroad and give it some 3D love. Rendered with OTOY Octane 2026

2026 is the year of the splat! This is a single patch of moss - scanned top and bottom - turned into a fully modular 3D asset. Flip it one way and it’s lush moss. Flip it the other and it’s damp, detailed soil. Both sides are real. No fake backsides. No tiling tricks. Ultra-lightweight. Fully real-time. Clones cleanly across geometry. And here’s the key difference - splats don’t really care about intersections. Coplanar overlaps don’t break the asset, they add density and realism. To match this traditionally with 3D you’d need thousands of moss scatters or extremely dense geo - and it would still feel off. One splat patch scales into massive 3D plates with almost no resource cost. This is asset development going forward - modular, DCC-agnostic, and built for modern pipelines. Download the moss scan for free on Gumroad and give it some 3D love. Rendered with OTOY Octane 2026

Spenser Dickerson

11,940 views • 7 months ago

Get the most POWERFUL Video Model out now at UP TO 70% OFF. Higgsfield CINEMA STUDIO 3.0 is LIVE. Cinematic reasoning and Ultimate realism. 100% win-rate. No more broken physics and perfect fight scenes. Next-level action with native audio. Faster and higher quality than every other model on the market. This ACTUALLY changes everything.

Get the most POWERFUL Video Model out now at UP TO 70% OFF. Higgsfield CINEMA STUDIO 3.0 is LIVE. Cinematic reasoning and Ultimate realism. 100% win-rate. No more broken physics and perfect fight scenes. Next-level action with native audio. Faster and higher quality than every other model on the market. This ACTUALLY changes everything.

Higgsfield AI 🧩

296,113 views • 4 months ago

The greatest Gaussian Splatting VR demo ever? Captured live at NVIDIA GTC — Mariya Sha experiencing 4D Gaussian Splatting in VR for the very first time. You can tell just from her reaction that this was something else! The scene was optimized using QUEEN, NVIDIA AI Developer's advanced research project for fast radiance field rendering. It’s an incredible look at what happens when high fidelity static and dynamic gaussian splats meets VR. Watch the full video on YouTube: Robert Scoble Did you get to do this one? #VR #3D #VFX

The greatest Gaussian Splatting VR demo ever? Captured live at NVIDIA GTC — Mariya Sha experiencing 4D Gaussian Splatting in VR for the very first time. You can tell just from her reaction that this was something else! The scene was optimized using QUEEN, NVIDIA AI Developer's advanced research project for fast radiance field rendering. It’s an incredible look at what happens when high fidelity static and dynamic gaussian splats meets VR. Watch the full video on YouTube: Robert Scoble Did you get to do this one? #VR #3D #VFX

Jonathan Stephens

28,114 views • 1 year ago

My #threejs Lumen Decor Studio is getting an update. Added a denoiser to the SSGI pass + better AO. I love how light bounces cascade on objects. It looks like Blender Cycles for the Browser 😍. Everything you see is rendered in real time and loads only 6.7 MB. Rendering SSGI + AO + SSR + Denoisers + Probes. You can manipulate objects, colors, sun, and sky all in real time. No baking at all. Live link soon.

My #threejs Lumen Decor Studio is getting an update. Added a denoiser to the SSGI pass + better AO. I love how light bounces cascade on objects. It looks like Blender Cycles for the Browser 😍. Everything you see is rendered in real time and loads only 6.7 MB. Rendering SSGI + AO + SSR + Denoisers + Probes. You can manipulate objects, colors, sun, and sky all in real time. No baking at all. Live link soon.

Anderson Mancini

23,295 views • 17 days ago

SPZ 4 is here. 🚀 3–5x faster encoding. 2x faster loading. 20x faster in the browser. Tens of millions of points, no sweat. The "JPG for 3D Gaussian splats" just leveled up. Big thanks to everyone who made this release happen, especially the team at Adobe. Read more: #NianticSpatial #Scaniverse #SPZ #GaussianSplat #Reconstruction #PhysicalAI #GeospatialAI #AI #Adobe

SPZ 4 is here. 🚀 3–5x faster encoding. 2x faster loading. 20x faster in the browser. Tens of millions of points, no sweat. The "JPG for 3D Gaussian splats" just leveled up. Big thanks to everyone who made this release happen, especially the team at Adobe. Read more: #NianticSpatial #Scaniverse #SPZ #GaussianSplat #Reconstruction #PhysicalAI #GeospatialAI #AI #Adobe

Niantic Spatial 🌎

63,435 views • 3 months ago

Relay changes everything about building with AI. One single API key. Instantly switch between Claude for scripts, FLUX for stills, Kling for video, and MiniMax. No new accounts. No setup. No breaks in flow. Just change the model name and keep creating. Most see cheaper inference. The real advantage is zero friction; you stay in the zone the entire time. Neo, our AI agent, proved it: he built his own time travel video using the full Relay platform. ❤️ This is what seamless creation feels like. The video is fully automated by Neo using our Relay platform. He made all the scenes, music, and voice, scripted by himself. A bit rough around the edges, but he will get better. Build without limits. open-gpu:native

Relay changes everything about building with AI. One single API key. Instantly switch between Claude for scripts, FLUX for stills, Kling for video, and MiniMax. No new accounts. No setup. No breaks in flow. Just change the model name and keep creating. Most see cheaper inference. The real advantage is zero friction; you stay in the zone the entire time. Neo, our AI agent, proved it: he built his own time travel video using the full Relay platform. ❤️ This is what seamless creation feels like. The video is fully automated by Neo using our Relay platform. He made all the scenes, music, and voice, scripted by himself. A bit rough around the edges, but he will get better. Build without limits. open-gpu:native

OpenGPU Network

473,452 views • 2 months ago

Seedance 2.5’s most underrated industry upgrade is its 3D white model input rendering — worth a close look for anyone in sci-fi film & VFX. It fixes real pre-production pain points, with clear efficiency wins: - Faster previs iteration: Get atmospheric previews straight from locked layout, no waiting on lighting & texture teams. Cheaper creative revisions. - Lower costs for pitches and concept validation. No wasting senior team hours on bid demos. - Earlier reference for VFX & art teams, extending cross-department parallel work. - Fast turnarounds for secondary shots (distant setups, alternates), saving render time and manpower. Official demo: ~100k-face spacecraft animation + style references → fully rendered footage. Structure and proportions hold steady in dynamic shots, and your original layout stays intact. One clear limit: it is still a generative previs tool, and cannot yet replace industrial physically accurate rendering and standard asset pipelines. It won’t take core lighting & rendering jobs, but it will reshape how previs gets done.

Seedance 2.5’s most underrated industry upgrade is its 3D white model input rendering — worth a close look for anyone in sci-fi film & VFX. It fixes real pre-production pain points, with clear efficiency wins: - Faster previs iteration: Get atmospheric previews straight from locked layout, no waiting on lighting & texture teams. Cheaper creative revisions. - Lower costs for pitches and concept validation. No wasting senior team hours on bid demos. - Earlier reference for VFX & art teams, extending cross-department parallel work. - Fast turnarounds for secondary shots (distant setups, alternates), saving render time and manpower. Official demo: ~100k-face spacecraft animation + style references → fully rendered footage. Structure and proportions hold steady in dynamic shots, and your original layout stays intact. One clear limit: it is still a generative previs tool, and cannot yet replace industrial physically accurate rendering and standard asset pipelines. It won’t take core lighting & rendering jobs, but it will reshape how previs gets done.

Alisa Qian

17,565 views • 1 month ago

Meta spent $40 billion and 10 years trying to make hand tracking feel natural. This guy did it with Claude in a weekend. No code written. No team. No hardware. He described what he wanted, Claude built it. The app tracks every finger, every joint, every movement live on his laptop. Physics bend around his hands in real time. The $40B industry just got embarrassed by one person with a Claude subscription. Everything you need to start building like this is in the article above.

Meta spent $40 billion and 10 years trying to make hand tracking feel natural. This guy did it with Claude in a weekend. No code written. No team. No hardware. He described what he wanted, Claude built it. The app tracks every finger, every joint, every movement live on his laptop. Physics bend around his hands in real time. The $40B industry just got embarrassed by one person with a Claude subscription. Everything you need to start building like this is in the article above.

Anatoli Kopadze

189,464 views • 3 months ago

One of the coolest 3d real estate demos I've seen in a while. Treedis brings together gaussian splats for area understanding → BIM data to check which units are available → Matterport for indoor views → and image editing AI to restyle decor and see different times of day. The data conflation problem of wrangling all these mismatched 3D assets into one seamless view is hard to do automatically - but this experience shows why it's worth solving. Every digital twin and AR vision video promises this, but here's someone actually building it.

One of the coolest 3d real estate demos I've seen in a while. Treedis brings together gaussian splats for area understanding → BIM data to check which units are available → Matterport for indoor views → and image editing AI to restyle decor and see different times of day. The data conflation problem of wrangling all these mismatched 3D assets into one seamless view is hard to do automatically - but this experience shows why it's worth solving. Every digital twin and AR vision video promises this, but here's someone actually building it.

Bilawal Sidhu

38,483 views • 8 months ago

Introducing AI video you can watch and interact with, in real-time! Powering this is a new world model that imagines and streams video frames every 40ms(!). No game engine in sight. We call it interactive video, and it's free for anyone to try right now (GPUs permitting)!

Introducing AI video you can watch and interact with, in real-time! Powering this is a new world model that imagines and streams video frames every 40ms(!). No game engine in sight. We call it interactive video, and it's free for anyone to try right now (GPUs permitting)!

Odyssey

704,738 views • 1 year ago

Building and prototyping games is easier than ever with Sidekick. Our designer built a 3D version of this OpenAI GPT-o1 game demo in <1 hour. Used Autodesk Maya for assets, Unity for engine, @bezi_3d Sidekick for scripting & implementation. Sidekick analyzes your project for real-time context of the asset folder, scene objects, components, and more. This allows it to implement simple mechanics—like movement controls and basic physics—for your characters and objects in seconds. It's the AI tool built by game developers, for game developers.

Building and prototyping games is easier than ever with Sidekick. Our designer built a 3D version of this OpenAI GPT-o1 game demo in <1 hour. Used Autodesk Maya for assets, Unity for engine, @bezi_3d Sidekick for scripting & implementation. Sidekick analyzes your project for real-time context of the asset folder, scene objects, components, and more. This allows it to implement simple mechanics—like movement controls and basic physics—for your characters and objects in seconds. It's the AI tool built by game developers, for game developers.

Bezi

15,295 views • 1 year ago