Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Real-time lens tracing experiment in three.js (WIP) Turns out you can generate metric depth with a 40 MB model on the CPU in the browser in about 10 seconds. That's enough to drive the lens simulation, no 3D scene needed. Might turn the 2D part into its own app. #threejs

Damjan Minovski

3,320 subscribers

19,126 görüntüleme • 7 gün önce •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

12 Yorum

Octamed profil fotoğrafı

Octamed6 gün önce

First thing I wondered about seeing your sim. Getting depth on a real photo. Tried using the iPhone lidar? Obviously I'm making yet another camera app, so I'm keen on your results.

Azuki profil fotoğrafı

Azuki6 gün önce

thats pretty fucking neat

Lane profil fotoğrafı

Lane7 gün önce

10 sec on CPU sounds crazy — what kind of lens effects can it drive?

Leo Phiêu Diêu profil fotoğrafı

Leo Phiêu Diêu6 gün önce

pls release a standalone tool or plugin for After Effects :( @Damjan_Minovski

Hey, it's me. profil fotoğrafı

Hey, it's me.7 gün önce

Incredible stuff.

Seth Thompson profil fotoğrafı

Seth Thompson6 gün önce

looks great! what model are you using? some variant of DepthPro?

Damjan Minovski profil fotoğrafı

Damjan Minovski6 gün önce

I quantized a version of MoGe-2 from Microsoft. It gives metric depth and also important - a FOV estimate. And it seems to run on pretty much everything because its so small

Anders Hjemdahl profil fotoğrafı

Anders Hjemdahl6 gün önce

Very cool, looks great!

Quist profil fotoğrafı

Quist6 gün önce

CSI needs you

sakuraboy profil fotoğrafı

sakuraboy6 gün önce

That’s very creative; I like it.

Danny profil fotoğrafı

Danny6 gün önce

How do you handle occluded areas, rays that pass behind objects?

Damjan Minovski profil fotoğrafı

Damjan Minovski6 gün önce

Not at all - as you can see in the video on the foreground person - its a sharp edge.. But it might be possible to fill in gaps with some tricks

Benzer Videolar

Real-time lens tracing experiment in three.js (WIP). This one's a 1973 Nikon wide-angle, US 3,731,989 - ten spherical surfaces. Rays trace from the sensor through all five lens elements, then hit a 360° photo with a depth map. Every lens parameter is a slider. #threejs

Real-time lens tracing experiment in three.js (WIP). This one's a 1973 Nikon wide-angle, US 3,731,989 - ten spherical surfaces. Rays trace from the sensor through all five lens elements, then hit a 360° photo with a depth map. Every lens parameter is a slider. #threejs

Damjan Minovski

20,344 görüntüleme • 15 gün önce

Took it further with Omma AI, (Spline ) now it works on video, and everything working in a Web Browser. Drop a video, Depth Anything v2 calculates the depth map frame by frame, and Three.js renders a fully lit 3D mesh in real time. Depth estimation on video in the browser +Automatic baking pass + Dynamic lighting reacting to the geometry #vibecoding #threejs #webgl

Took it further with Omma AI, (Spline ) now it works on video, and everything working in a Web Browser. Drop a video, Depth Anything v2 calculates the depth map frame by frame, and Three.js renders a fully lit 3D mesh in real time. Depth estimation on video in the browser +Automatic baking pass + Dynamic lighting reacting to the geometry #vibecoding #threejs #webgl

Joseph Azar

148,148 görüntüleme • 5 ay önce

I prompted Omma to build a #threejs app with real dynamic lighting on a 3D mesh - generated from a single image, using Depth Anything v2 + Transformers from Hugging Face ⚡ Depth estimation in the browser 🫧 3D mesh from the depth map 💡 Dynamic lighting reacting to the geometry No manual code. Pure AI prompting. The future of 3D on the web feels wide open.

I prompted Omma to build a #threejs app with real dynamic lighting on a 3D mesh - generated from a single image, using Depth Anything v2 + Transformers from Hugging Face ⚡ Depth estimation in the browser 🫧 3D mesh from the depth map 💡 Dynamic lighting reacting to the geometry No manual code. Pure AI prompting. The future of 3D on the web feels wide open.

Joseph Azar

14,041 görüntüleme • 5 ay önce

Built this in 2 hours 😂 I asked chatGPT to generate the 2d assets, used Tripo to generate the 3d version, then I used #threejs for the game dev. its just starting, a lot can be done here.

Built this in 2 hours 😂 I asked chatGPT to generate the 2d assets, used Tripo to generate the 3d version, then I used #threejs for the game dev. its just starting, a lot can be done here.

Ibrahim Boona

41,615 görüntüleme • 4 ay önce

Rewrite The Odyssey in your own playable game demo! No 3D modeling, no coding, just one image! With HappyOyster World Model, you can turn any image into an interactive game demo in seconds.

Rewrite The Odyssey in your own playable game demo! No 3D modeling, no coding, just one image! With HappyOyster World Model, you can turn any image into an interactive game demo in seconds.

HappyOyster

1,660,870 görüntüleme • 1 ay önce

Introducing H3 Max Camera Controls, the world's fastest 3D video model. Turn a single viewpoint into a navigable 3D scene in less than 3 seconds. Set the horizontal and vertical camera angle in degrees, and H3 Max Camera Controls moves through the scene while preserving geometry, position, and materials across perspectives. Fast enough to control the camera in real time.

Introducing H3 Max Camera Controls, the world's fastest 3D video model. Turn a single viewpoint into a navigable 3D scene in less than 3 seconds. Set the horizontal and vertical camera angle in degrees, and H3 Max Camera Controls moves through the scene while preserving geometry, position, and materials across perspectives. Fast enough to control the camera in real time.

fal

238,330 görüntüleme • 16 gün önce

How to split a 3D model into printable parts in one click? Here’s the full workflow with Meshy Auto Split: - Generate a draft model with Image-to-3D - Hit Auto Split. In 40 seconds, you get parts that follow the model’s natural structure - Download and open your slicer Every part comes out clean, watertight, and ready to print. Connectors? We hear you. Coming soon 👀

How to split a 3D model into printable parts in one click? Here’s the full workflow with Meshy Auto Split: - Generate a draft model with Image-to-3D - Hit Auto Split. In 40 seconds, you get parts that follow the model’s natural structure - Download and open your slicer Every part comes out clean, watertight, and ready to print. Connectors? We hear you. Coming soon 👀

MeshyAI

71,403 görüntüleme • 2 ay önce

Wait so Gemini can now turn any question into interactive visualizations?! That's just amazing to learn new things. You can generate a simulation about anything just by: - Going to the Gemini web app - Selecting the mode 'pro' - Starting your prompt with "show me" That's it!

Wait so Gemini can now turn any question into interactive visualizations?! That's just amazing to learn new things. You can generate a simulation about anything just by: - Going to the Gemini web app - Selecting the mode 'pro' - Starting your prompt with "show me" That's it!

Paul Couvert

26,049 görüntüleme • 5 ay önce

AI video has a control problem. Most AI tools generate in 2D. Filmmakers think, stage, and direct in 3D. Today we're introducing Flow Studio 3D Editor + Canvas. Build and direct your scene in 3D. Then use Canvas to render and refine the final look with leading AI models. Stay in 2D when speed matters. Move into 3D when you need precision. AI can build the scene. You still call the shots. Start directing:

AI video has a control problem. Most AI tools generate in 2D. Filmmakers think, stage, and direct in 3D. Today we're introducing Flow Studio 3D Editor + Canvas. Build and direct your scene in 3D. Then use Canvas to render and refine the final look with leading AI models. Stay in 2D when speed matters. Move into 3D when you need precision. AI can build the scene. You still call the shots. Start directing:

Autodesk Flow Studio

35,408 görüntüleme • 1 ay önce

oh may.. 3D Gaussian Splat is so crazy now last time we need weeks to turn a room into a 3D model.. now with AI 3DGS, you do it in seconds… even zoom into the text and looks perfect give it like 6 months… you can turn a whole city into a full detailed 3D model

oh may.. 3D Gaussian Splat is so crazy now last time we need weeks to turn a room into a 3D model.. now with AI 3DGS, you do it in seconds… even zoom into the text and looks perfect give it like 6 months… you can turn a whole city into a full detailed 3D model

el.cine

143,676 görüntüleme • 10 ay önce

Studying offline 3D vibe-coding with Three.js: - Gemma 4 E4B runs on-device via llama.cpp (or in-browser via transformers.js, ~13x slower). - Scene renders through WebGPU→Dawn→Metal. - A grammar + verifier outside the weights makes the model reliable at Three.js.

Studying offline 3D vibe-coding with Three.js: - Gemma 4 E4B runs on-device via llama.cpp (or in-browser via transformers.js, ~13x slower). - Scene renders through WebGPU→Dawn→Metal. - A grammar + verifier outside the weights makes the model reliable at Three.js.

Renaud

13,101 görüntüleme • 3 ay önce

Building Three.js shaders is about to get a whole lot easier! 👍 Introducing Three.js Shader Graph — visual node-based editing for TSL. 🖱️Drag & drop nodes 📺Real-time 3D preview 🔄Auto-generate TSL code in realtime Join the waitlist 👉🏻 #threejs #webgl #webgpu #shaders

Building Three.js shaders is about to get a whole lot easier! 👍 Introducing Three.js Shader Graph — visual node-based editing for TSL. 🖱️Drag & drop nodes 📺Real-time 3D preview 🔄Auto-generate TSL code in realtime Join the waitlist 👉🏻 #threejs #webgl #webgpu #shaders

Dan Greenheck

35,464 görüntüleme • 9 ay önce

🤯 A hidden gem in the latest vivo X300 Ultra update! The new Telephoto Calibration feature is more than just an animation. Turn it on in Camera Settings and it asks you to flip the phone over. At first, I thought nothing was happening… until I looked closely at the periscope lens. The telephoto camera was actually moving and adjusting itself in real time for calibration! A phone that can visually calibrate its own periscope lens for optimal performance? That's a proper wow moment 📸🔥 vivo is doing some really interesting things in the camera department.

🤯 A hidden gem in the latest vivo X300 Ultra update! The new Telephoto Calibration feature is more than just an animation. Turn it on in Camera Settings and it asks you to flip the phone over. At first, I thought nothing was happening… until I looked closely at the periscope lens. The telephoto camera was actually moving and adjusting itself in real time for calibration! A phone that can visually calibrate its own periscope lens for optimal performance? That's a proper wow moment 📸🔥 vivo is doing some really interesting things in the camera department.

S M A Sithick

25,336 görüntüleme • 3 ay önce

So uh, simulation theory might be real. I dropped a sim computer into the simulation my Astra agents live in. One agent sat down and built a simulation of his own, with its own agents living inside. Simulations all the way down.

So uh, simulation theory might be real. I dropped a sim computer into the simulation my Astra agents live in. One agent sat down and built a simulation of his own, with its own agents living inside. Simulations all the way down.

Matt Shumer

3,091,510 görüntüleme • 22 gün önce

added World Labs API to the simulation builder, you can now type a prompt and get a full 3D world with physics colliders loaded into MuJoCo all in your browser

added World Labs API to the simulation builder, you can now type a prompt and get a full 3D world with physics colliders loaded into MuJoCo all in your browser

Moyai

61,597 görüntüleme • 8 ay önce

Meta Quest 3 users can beta test at in the Meta Quest 3 Browser - its a #WebXR #threejs webpage so no installs needed. Let me know how you get on! 👾 #MetaQuest3 #MixedReality

Meta Quest 3 users can beta test at in the Meta Quest 3 Browser - its a #WebXR #threejs webpage so no installs needed. Let me know how you get on! 👾 #MetaQuest3 #MixedReality

Dominic Pajak

73,081 görüntüleme • 2 yıl önce

If you own a 3D printer, you need this tool on your radar right now. SNAP3D turns a single 2D image into fully assemblable, multi-part 3D prints with built-in peg-and-socket joints! No glue. No screws. Just print, snap, and build. it cuts the model into semantic parts, optimizes the connectors, and runs physics tests to guarantee stability. Feed it a photo, get real-world snap-fit parts ready for your print bed

If you own a 3D printer, you need this tool on your radar right now. SNAP3D turns a single 2D image into fully assemblable, multi-part 3D prints with built-in peg-and-socket joints! No glue. No screws. Just print, snap, and build. it cuts the model into semantic parts, optimizes the connectors, and runs physics tests to guarantee stability. Feed it a photo, get real-world snap-fit parts ready for your print bed

Wildminder

43,883 görüntüleme • 13 gün önce

The Policy Checker Page is LIVE! Remember we talked about showing our intermediate model and success heatmap? You can now check them live on our hub! For each intermediate policy, you can: - View its summary — success rate, task type, checkpoints, and more. - Run it directly in your browser to observe its real-time inference. (If it looks a bit choppy, that's expected — the model is inferring live!) - Explore its success heatmap — showing the initial states under which the policy successfully completes the task. This gives the community a lens into our backend policy training, and lays the groundwork for better demonstrating our recover from failure training loop going forward. How to enter ⬇️

The Policy Checker Page is LIVE! Remember we talked about showing our intermediate model and success heatmap? You can now check them live on our hub! For each intermediate policy, you can: - View its summary — success rate, task type, checkpoints, and more. - Run it directly in your browser to observe its real-time inference. (If it looks a bit choppy, that's expected — the model is inferring live!) - Explore its success heatmap — showing the initial states under which the policy successfully completes the task. This gives the community a lens into our backend policy training, and lays the groundwork for better demonstrating our recover from failure training loop going forward. How to enter ⬇️

Axis Robotics

13,469 görüntüleme • 3 ay önce

You can now generate, edit, and convert a reference image into 3D inside one tool. Tripo's Image Generation runs Nano Banana and GPT to build the reference, then turns it into a model. Text or photo in, 3D out. One pipeline, zero handoffs.

You can now generate, edit, and convert a reference image into 3D inside one tool. Tripo's Image Generation runs Nano Banana and GPT to build the reference, then turns it into a model. Text or photo in, 3D out. One pipeline, zero handoffs.

Alvaro Cintas

56,246 görüntüleme • 3 ay önce