KIRI Engine - 3D Scanner App's banner
KIRI Engine - 3D Scanner App's profile picture

KIRI Engine - 3D Scanner App

@KIRI_Engine_App6,237 subscribers

🎁 Use code: kiriengineforever633 for a free 1-day KIRI Engine Pro trial 🖥️ Log in at https://t.co/A6CNaX1ycW and redeem under Me (top right) 🡢 Settings

Shorts

Huawei's new 3D lock screen wallpaper is actually pretty interesting. Unlike iPhone's Spatial Photo, which creates a fixed stereoscopic depth effect from a photo, this lets you scan an object 360°, generate a full 3D Gaussian Splatting asset, and use that as your lock screen. Tilt the phone and you're moving through a reconstructed 3D scene, not a fixed stereo image. The part worth paying attention to: 3D capture moving out of creative pipelines and into everyday phone personalization. That's a different kind of adoption curve.

Huawei's new 3D lock screen wallpaper is actually pretty interesting. Unlike iPhone's Spatial Photo, which creates a fixed stereoscopic depth effect from a photo, this lets you scan an object 360°, generate a full 3D Gaussian Splatting asset, and use that as your lock screen. Tilt the phone and you're moving through a reconstructed 3D scene, not a fixed stereo image. The part worth paying attention to: 3D capture moving out of creative pipelines and into everyday phone personalization. That's a different kind of adoption curve.

185,002 次观看

Single video → a reframeable 4D Gaussian Splatting scene. Not a sequence of separately built 3D frames played back like a video. This is one continuous space-time scene, reconstructed from a single clip shot on an iPhone 16. We combine feed-forward Gaussian generation, 3D tracking, and 4D Gaussian Splatting, aiming to deliver it as a compact 4D video file that runs on your phone. Still early R&D. The goal: make 4DGS something anyone can create and experience, not just researchers with a camera rig.

Single video → a reframeable 4D Gaussian Splatting scene. Not a sequence of separately built 3D frames played back like a video. This is one continuous space-time scene, reconstructed from a single clip shot on an iPhone 16. We combine feed-forward Gaussian generation, 3D tracking, and 4D Gaussian Splatting, aiming to deliver it as a compact 4D video file that runs on your phone. Still early R&D. The goal: make 4DGS something anyone can create and experience, not just researchers with a camera rig.

29,478 次观看

NVIDIA just published ArtiFixer. It tackles one of the most frustrating parts of 3D Gaussian Splatting: what happens in areas you didn't capture. Standard reconstruction falls apart in under-observed regions. Floaters, blurry holes, missing geometry. ArtiFixer patches those gaps with an autoregressive diffusion model that stays consistent with what exists while generating plausible content where there's nothing. 1-3 dB PSNR improvement across all MipNeRF 360 scenes. On some of them, it's the only approach that produces usable output at all. Open source:

NVIDIA just published ArtiFixer. It tackles one of the most frustrating parts of 3D Gaussian Splatting: what happens in areas you didn't capture. Standard reconstruction falls apart in under-observed regions. Floaters, blurry holes, missing geometry. ArtiFixer patches those gaps with an autoregressive diffusion model that stays consistent with what exists while generating plausible content where there's nothing. 1-3 dB PSNR improvement across all MipNeRF 360 scenes. On some of them, it's the only approach that produces usable output at all. Open source:

49,440 次观看

We're giving away $32,600 of models for free 😉 All jokes aside it's actually a pretty good kit for urban environments so we hope it's useful to someone. Download in the comments

We're giving away $32,600 of models for free 😉 All jokes aside it's actually a pretty good kit for urban environments so we hope it's useful to someone. Download in the comments

121,788 次观看

A new #Blender version has been released and there's a lot of good talk about optimizations and speed ups 🏃‍♀️ But why has no-one mentioned we can turn our 3D scenes and models into cartoons so easily now 🤩 Grab the free demo file to try it out!

A new #Blender version has been released and there's a lot of good talk about optimizations and speed ups 🏃‍♀️ But why has no-one mentioned we can turn our 3D scenes and models into cartoons so easily now 🤩 Grab the free demo file to try it out!

126,179 次观看

AI-Enhanced LiDAR. Left vs right. A real LiDAR device costs thousands of dollars. What's in your iPhone Pro is a "baby LiDAR". Limited depth resolution, noisy output, not really built for high-precision 3D. You can't change the hardware. So we built an ML layer on top. Denoising, geometry completion, detail recovery. Processed server-side. Same sensor. Very different result.

AI-Enhanced LiDAR. Left vs right. A real LiDAR device costs thousands of dollars. What's in your iPhone Pro is a "baby LiDAR". Limited depth resolution, noisy output, not really built for high-precision 3D. You can't change the hardware. So we built an ML layer on top. Denoising, geometry completion, detail recovery. Processed server-side. Same sensor. Very different result.

51,645 次观看

Tested Claude + Blender today with two real workflows. Sharing what actually happened. First one was a simple demo. Gave it one sentence to build a cyberpunk room. Geometry, lighting, camera, render. It got there, though not everything in the prompt landed perfectly. Good enough to show the concept, not a stress test. Second one was more interesting. Threw a raw photogrammetry scan at it. Massey Ferguson tractor, 250k faces, grass background everywhere, debris floating all over the place. Asked Claude to clean it up autonomously. It did the work. Removed 106 floating chunks, cut face count by 87%, stripped the grass, flipped the model upright, set up studio lighting and rendered. Technically it worked. But honest answer: the result wasn't clean enough for production. This kind of cleanup still needs the right tools and someone who knows what they're doing. So here's where it actually fits. Not the precise technical stuff. The setup work. The repetitive stuff. The things that take forever if you don't already know Blender. It won't replace your 3D artist. It replaces the boring part before they start.

Tested Claude + Blender today with two real workflows. Sharing what actually happened. First one was a simple demo. Gave it one sentence to build a cyberpunk room. Geometry, lighting, camera, render. It got there, though not everything in the prompt landed perfectly. Good enough to show the concept, not a stress test. Second one was more interesting. Threw a raw photogrammetry scan at it. Massey Ferguson tractor, 250k faces, grass background everywhere, debris floating all over the place. Asked Claude to clean it up autonomously. It did the work. Removed 106 floating chunks, cut face count by 87%, stripped the grass, flipped the model upright, set up studio lighting and rendered. Technically it worked. But honest answer: the result wasn't clean enough for production. This kind of cleanup still needs the right tools and someone who knows what they're doing. So here's where it actually fits. Not the precise technical stuff. The setup work. The repetitive stuff. The things that take forever if you don't already know Blender. It won't replace your 3D artist. It replaces the boring part before they start.

60,887 次观看

Put your scans on the moon 🌜 Blender 4.5 adaptive subdivision is soooo much faster. Perfect time to get some free Moon textures from NASA 🚀 #b3d #blender

Put your scans on the moon 🌜 Blender 4.5 adaptive subdivision is soooo much faster. Perfect time to get some free Moon textures from NASA 🚀 #b3d #blender

93,528 次观看

Gaussian splats are incredible—until you want them to move. Normally, that means crazy 4D capture setups. Not anymore. Here is how anyone can rig and animate static splats using Mixamo. Blender playback can get brutal, so big props to PlayCanvas—their brilliant Super Splat sequence import saves the day. 🧵 Watch the full tutorial breakdown in the comments!

Gaussian splats are incredible—until you want them to move. Normally, that means crazy 4D capture setups. Not anymore. Here is how anyone can rig and animate static splats using Mixamo. Blender playback can get brutal, so big props to PlayCanvas—their brilliant Super Splat sequence import saves the day. 🧵 Watch the full tutorial breakdown in the comments!

16,476 次观看

Right now, 4D capture mostly belongs to labs, studios, and expensive multi-camera rigs. Our goal at KIRI has always been different: put spatial capture in the hands of regular people, on the device they already carry with them. This is a work in progress, but it’s a huge step toward consumer level 4D scanning: record a normal video once, then reframe that moving moment afterward 🤩

Right now, 4D capture mostly belongs to labs, studios, and expensive multi-camera rigs. Our goal at KIRI has always been different: put spatial capture in the hands of regular people, on the device they already carry with them. This is a work in progress, but it’s a huge step toward consumer level 4D scanning: record a normal video once, then reframe that moving moment afterward 🤩

13,415 次观看

3D scans usually begin as triangle meshes, which are great for capturing, viewing, and sharing real-world objects. For editing, animation, cleanup, or production workflows, quad-based topology can be much easier to work with. Our Quad-Mesh Retopology helps convert scan meshes into clean quad meshes, making your model easier to edit, optimize, and use across Blender, Maya, game engines, and other 3D workflows.

3D scans usually begin as triangle meshes, which are great for capturing, viewing, and sharing real-world objects. For editing, animation, cleanup, or production workflows, quad-based topology can be much easier to work with. Our Quad-Mesh Retopology helps convert scan meshes into clean quad meshes, making your model easier to edit, optimize, and use across Blender, Maya, game engines, and other 3D workflows.

11,048 次观看

We have a new FREE tool coming soon - perfect for 3D environments 🌎 But we need your help naming it! It can 'wrap' a 3d scan of bricks, terrain, surfaces etc, onto a base mesh without the flattening classic shrink-wrap methods usually cause. 🏔️ We're thinking something like Mesh Wrap.....Terrain Wrap....Any better ideas? 💡

We have a new FREE tool coming soon - perfect for 3D environments 🌎 But we need your help naming it! It can 'wrap' a 3d scan of bricks, terrain, surfaces etc, onto a base mesh without the flattening classic shrink-wrap methods usually cause. 🏔️ We're thinking something like Mesh Wrap.....Terrain Wrap....Any better ideas? 💡

42,331 次观看

Apple just trained a 3D Gaussian head reconstruction model on 10,000+ subjects. Feed-forward. No test-time optimization. New identity in, reconstructed Gaussian head out. The UV-parameterized Gaussian representation decouples the number of Gaussians from the number and resolution of input images, making it practical to train with many high resolution views. And the heads are not just static either: text-conditioned identity generation, plus blendshape-driven latent animation across identities. We've been building in the 3D Gaussian Splatting space for a while. The gap between "research demo" and "works on real people at scale" is closing fast.

Apple just trained a 3D Gaussian head reconstruction model on 10,000+ subjects. Feed-forward. No test-time optimization. New identity in, reconstructed Gaussian head out. The UV-parameterized Gaussian representation decouples the number of Gaussians from the number and resolution of input images, making it practical to train with many high resolution views. And the heads are not just static either: text-conditioned identity generation, plus blendshape-driven latent animation across identities. We've been building in the 3D Gaussian Splatting space for a while. The gap between "research demo" and "works on real people at scale" is closing fast.

12,125 次观看

ML SHARP is an exciting example of how far single Image 3D inference has come🤯 At KIRI Engine, our focus has always been slightly different🌍🌕 We build tools for capturing the physical world as it is, not approximating it📷 When real world accuracy, editability, and geometric consistency matter, reliable scanning remains essential😝 Different approaches solve different problems⚙️

ML SHARP is an exciting example of how far single Image 3D inference has come🤯 At KIRI Engine, our focus has always been slightly different🌍🌕 We build tools for capturing the physical world as it is, not approximating it📷 When real world accuracy, editability, and geometric consistency matter, reliable scanning remains essential😝 Different approaches solve different problems⚙️

27,217 次观看

Shooting massive photogrammetry datasets while traveling is amazing. Sorting 5,000 messy RAW files into individual scanning sessions when you get home? An absolute nightmare. 🤬 We got tired of doing it manually, so we built an internal tool. It uses EXIF time-gaps and OpenCV feature-matching to automatically sort your camera dumps into session folders. We love making free tools for the 3D community. Should we polish this up and release it for everyone? Let us know if it's worth a release

Shooting massive photogrammetry datasets while traveling is amazing. Sorting 5,000 messy RAW files into individual scanning sessions when you get home? An absolute nightmare. 🤬 We got tired of doing it manually, so we built an internal tool. It uses EXIF time-gaps and OpenCV feature-matching to automatically sort your camera dumps into session folders. We love making free tools for the 3D community. Should we polish this up and release it for everyone? Let us know if it's worth a release

17,679 次观看

I tested Seedance 2.0 using footage of Jack capturing a 3DGS scan🤩 Video 1 → generate a clip where he’s filming and dancing while promoting our PhotoScan + 3DGS Video 2 → generate a full KIRI Engine promo video The results were wild🤯 It didn’t just generate visuals. It synced sound, motion, and effects surprisingly well. Sure, there were some clipping artifacts… but honestly, it’s still insanely impressive😺 And the craziest part? Both videos together cost me about $0.14 USD...💰

I tested Seedance 2.0 using footage of Jack capturing a 3DGS scan🤩 Video 1 → generate a clip where he’s filming and dancing while promoting our PhotoScan + 3DGS Video 2 → generate a full KIRI Engine promo video The results were wild🤯 It didn’t just generate visuals. It synced sound, motion, and effects surprisingly well. Sure, there were some clipping artifacts… but honestly, it’s still insanely impressive😺 And the craziest part? Both videos together cost me about $0.14 USD...💰

14,425 次观看

Gaussian Splats are really gaining traction recently. Which means creatives need more tools! Manually editing tools are great - but we want tools that can be used by everyone! Not just 3D or technical artists. a.k.a = automation, sliders and single button presses. Our new 3DGS editing features are done😃 but it wouldn't right to release them without some proper documentation. So we'll be taking care of that, along with a release on Monday

Gaussian Splats are really gaining traction recently. Which means creatives need more tools! Manually editing tools are great - but we want tools that can be used by everyone! Not just 3D or technical artists. a.k.a = automation, sliders and single button presses. Our new 3DGS editing features are done😃 but it wouldn't right to release them without some proper documentation. So we'll be taking care of that, along with a release on Monday

10,458 次观看

Videos

没有更多内容可加载