Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

a tiny AI 0.5B just turned a normal phone video into a fully labeled 3D room run phone. SpatialLM that understands walls, doors, furniture, and everything layout. it trained as a standard multimodal LLM. Most vision models see pixels, SpatialLM sees space. Open models :

Md Ismail Šojal 🕷️

57,999 subscribers

64,716 Aufrufe • vor 2 Tagen •via X (Twitter)

Nachrichten & Politik Bildung Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

18 Kommentare

Profilbild von Marc Bara

Marc Baravor 1 Tag

It seems the 0.5B model handles the point cloud → layout step, not the whole video pipeline. The repo requires separate 3D reconstruction, alignment and scale correction, and the published inference code runs on CUDA. If you ran it on a phone, how did you do it?

Profilbild von ziziran

ziziranvor 1 Tag

For anyone trying their own video: the official example first reconstructs a point cloud, then aligns and scales it before running SpatialLM. Worth checking the cost of that whole pipeline when targeting a phone.

Profilbild von Honourable

Honourablevor 1 Tag

Amazing stuff

Profilbild von john

johnvor 1 Tag

How are you getting a 3d point cloud from your phone camera? Do you know what a 3d point cloud is?

Profilbild von Dan

Danvor 1 Tag

Nice

Profilbild von Apachon

Apachonvor 1 Tag

This is amazing , ty.

Profilbild von Scobel

Scobelvor 1 Tag

super cool

Profilbild von Joey D

Joey Dvor 1 Tag

Does it need 3D data?

Profilbild von ethan

ethanvor 1 Tag

This is ai

Profilbild von i need YHWH

i need YHWHvor 1 Tag

Imaging budgeting set locations with this

Profilbild von puran thapa

puran thapavor 2 Tagen

Will it labeling in real time or after video process??

Profilbild von Philip

Philipvor 1 Tag

Would love yo try this for my autonomous drone, lets Connect!

Profilbild von Nick

Nickvor 1 Tag

i feel like i saw this 1.5 years ago

Profilbild von Philip Radvan

Philip Radvanvor 1 Tag

Very cool! Thanks for sharing. Having a hard time thinking of real world applications for this...

Profilbild von Shiraz Akmal

Shiraz Akmalvor 1 Tag

Could this be run in real time?

Profilbild von indoor positioning

indoor positioningvor 1 Tag

很早的模型了

Profilbild von John D. Pope 🦒

John D. Pope 🦒vor 1 Tag

I just want apple’s measure tool to do exactly this

Profilbild von Dylan

Dylanvor 1 Tag

群核科技的项目

Ähnliche Videos

What happens when VLMs meet 3D foundation models? See VLM-3R (CVPR 2026). VLM-3R links a vision-language model (e.g., Qwen) with 3D geometric foundation models (e.g., CUT3R) at metric scale. Given an uncalibrated video, it moves beyond pixels to perceive and reason in 3D space. Code (open source):

What happens when VLMs meet 3D foundation models? See VLM-3R (CVPR 2026). VLM-3R links a vision-language model (e.g., Qwen) with 3D geometric foundation models (e.g., CUT3R) at metric scale. Given an uncalibrated video, it moves beyond pixels to perceive and reason in 3D space. Code (open source):

Zhiwen(Aaron) Fan

10,666 Aufrufe • vor 7 Monaten

This AI just turned a flat image into a fully interactive 3D world 👀 Hyper3D WorldGen converts a single image into multiple independent, physics-ready 3D assets while preserving their spatial relationships. It doesn’t just generate a 3D scene it actually understands and structures the objects inside it. Watch the breakdown:

This AI just turned a flat image into a fully interactive 3D world 👀 Hyper3D WorldGen converts a single image into multiple independent, physics-ready 3D assets while preserving their spatial relationships. It doesn’t just generate a 3D scene it actually understands and structures the objects inside it. Watch the breakdown:

Markandey Sharma

31,374 Aufrufe • vor 1 Monat

Took 5 phone photos of my living room and Claude Code rebuilt it in 3D. Then I turned it into a skill. Now I can try different layouts and drag furniture around before moving anything heavy. It even flags when a chair gets boxed in. Inspired by Shimecki's room planner

Took 5 phone photos of my living room and Claude Code rebuilt it in 3D. Then I turned it into a skill. Now I can try different layouts and drag furniture around before moving anything heavy. It even flags when a chair gets boxed in. Inspired by Shimecki's room planner

Skylar Kitchen

50,675 Aufrufe • vor 14 Tagen

You can run local AI models up to 120B without a $10,000 Mac Studio This phone-sized device is your own server for open-source models. 100% local and private. And you can use it to: - Power an agent like OpenClaw 24/7 - Completely replace a chatbot - Literally anything that requires an API It’s called Tiiny, and, once again, you can run the latest open-source models on it. Link below

You can run local AI models up to 120B without a $10,000 Mac Studio This phone-sized device is your own server for open-source models. 100% local and private. And you can use it to: - Power an agent like OpenClaw 24/7 - Completely replace a chatbot - Literally anything that requires an API It’s called Tiiny, and, once again, you can run the latest open-source models on it. Link below

Paul Couvert

41,356 Aufrufe • vor 7 Monaten

converts single 2D images into interactable 3D models; with MonoArt. Interior designers will definitely appreciate this one. - Snap one photo of any furniture - Get a working 3D model in 20 seconds - jointly predicts geometry, part segments, and motion; - built on TRELLIS. Drawers actually slide, doors open.. Test room clearances in VR before buying a thing

converts single 2D images into interactable 3D models; with MonoArt. Interior designers will definitely appreciate this one. - Snap one photo of any furniture - Get a working 3D model in 20 seconds - jointly predicts geometry, part segments, and motion; - built on TRELLIS. Drawers actually slide, doors open.. Test room clearances in VR before buying a thing

Wildminder

25,185 Aufrufe • vor 6 Monaten

Introducing Ollama fully Integrated into VSCode with CodeGPT Now you can download open-source models from ollama with a single click and install them as code assistants in VSCode. In this case, I download the qwen2:0.5b (Qwen) model in under a minute, and it becomes fully functional with just one click. The era of locally running code assistants has begun! 🚀

Introducing Ollama fully Integrated into VSCode with CodeGPT Now you can download open-source models from ollama with a single click and install them as code assistants in VSCode. In this case, I download the qwen2:0.5b (Qwen) model in under a minute, and it becomes fully functional with just one click. The era of locally running code assistants has begun! 🚀

Daniel San

101,567 Aufrufe • vor 2 Jahren

A guy just turned standard home Wi-Fi into a radar that sees through walls. Over 62,000 stars on GitHub for a system that tracks humans without using a single camera lens. It doesn’t just know you’re there. Watch what happens when a person lies down on a bed in another room. The AI instantly maps their exact posture, tracks their breathing, and calculates their heartbeat in real-time. No optical surveillance, no privacy leaks - it just analyzes how your body disrupts ordinary radio waves. The whole thing runs on a tiny $5 microchip. Traditional security requires a direct line of sight and invades your personal space. Now, your Wi-Fi router is a camera that sees through solid brick.

A guy just turned standard home Wi-Fi into a radar that sees through walls. Over 62,000 stars on GitHub for a system that tracks humans without using a single camera lens. It doesn’t just know you’re there. Watch what happens when a person lies down on a bed in another room. The AI instantly maps their exact posture, tracks their breathing, and calculates their heartbeat in real-time. No optical surveillance, no privacy leaks - it just analyzes how your body disrupts ordinary radio waves. The whole thing runs on a tiny $5 microchip. Traditional security requires a direct line of sight and invades your personal space. Now, your Wi-Fi router is a camera that sees through solid brick.

pulmencr

1,843,175 Aufrufe • vor 2 Monaten

Someone just put OpenClaw inside a Unitree G1 humanoid — and it walks. Same agent framework running on your phone. Now integrated with lidar, stereo + RGB cameras, understanding 3D space and temporal context. Works on drones and quadrupeds too. Fully open source. Cool work! Video Source: stash

Someone just put OpenClaw inside a Unitree G1 humanoid — and it walks. Same agent framework running on your phone. Now integrated with lidar, stereo + RGB cameras, understanding 3D space and temporal context. Works on drones and quadrupeds too. Fully open source. Cool work! Video Source: stash

Bo Wang

102,701 Aufrufe • vor 7 Monaten

YOUR OLD ANDROID PHONE IS A FREE AI VISION SERVER AND YOU DON’T KNOW IT one dev built an app that turns any android into a local openai-compatible LLM server with vision support, analyzes camera feeds entirely on-device, no cloud, no subscriptions, nothing leaves your network you already own the hardware, it’s just sitting in a drawer full breakdown below ↓

YOUR OLD ANDROID PHONE IS A FREE AI VISION SERVER AND YOU DON’T KNOW IT one dev built an app that turns any android into a local openai-compatible LLM server with vision support, analyzes camera feeds entirely on-device, no cloud, no subscriptions, nothing leaves your network you already own the hardware, it’s just sitting in a drawer full breakdown below ↓

leopardracer

21,960 Aufrufe • vor 3 Monaten

GPT-6 Astra + Scenario MCP turned 9 crappy photos into a fully interactive 3D room. No measurements. No scans. Just 9 phone photos of our office. Astra understood the spatial layout and rebuilt the geometry in Blender. Scenario MCP pulled the real materials straight from the photos, including the carpet, wood and metal surfaces. An hour later, we were walking through our actual office in 3D.

GPT-6 Astra + Scenario MCP turned 9 crappy photos into a fully interactive 3D room. No measurements. No scans. Just 9 phone photos of our office. Astra understood the spatial layout and rebuilt the geometry in Blender. Scenario MCP pulled the real materials straight from the photos, including the carpet, wood and metal surfaces. An hour later, we were walking through our actual office in 3D.

Scenario

42,461 Aufrufe • vor 25 Tagen

Today we’re releasing V-JEPA, a method for teaching machines to understand and model the physical world by watching videos. This work is another important step towards Yann LeCun’s outlined vision of AI models that use a learned understanding of the world to plan, reason and accomplish complex tasks. Details ➡️ We're releasing a collection of V-JEPA vision models trained with a feature prediction objective using self-supervised learning. The models are able to understand and predict what is going on in a video, even with limited information. It learns by predicting missing or obscured parts of a video in its internal feature space. Unlike generative approaches that fill in missing pixels, this flexible approach enables up to 6x improvements in training and sample efficiency. The models were pre-trained on entirely unlabeled data, and a small amount of labeled data can be used to train a task-specific prediction head on top after pre-training. Our results show that, using a frozen backbone, our top V-JEPA models achieve 82.0% on Kinetics-400, 72.2% on Something-Something-v2 and 77.9% on ImageNet1K — competitive with or exceeding previous leading video models. We believe that this work is an important milestone on the path to advancing machine intelligence.

Today we’re releasing V-JEPA, a method for teaching machines to understand and model the physical world by watching videos. This work is another important step towards Yann LeCun’s outlined vision of AI models that use a learned understanding of the world to plan, reason and accomplish complex tasks. Details ➡️ We're releasing a collection of V-JEPA vision models trained with a feature prediction objective using self-supervised learning. The models are able to understand and predict what is going on in a video, even with limited information. It learns by predicting missing or obscured parts of a video in its internal feature space. Unlike generative approaches that fill in missing pixels, this flexible approach enables up to 6x improvements in training and sample efficiency. The models were pre-trained on entirely unlabeled data, and a small amount of labeled data can be used to train a task-specific prediction head on top after pre-training. Our results show that, using a frozen backbone, our top V-JEPA models achieve 82.0% on Kinetics-400, 72.2% on Something-Something-v2 and 77.9% on ImageNet1K — competitive with or exceeding previous leading video models. We believe that this work is an important milestone on the path to advancing machine intelligence.

AI at Meta

704,200 Aufrufe • vor 2 Jahren

AI + AR is going to change everything! I turned my photo into a 3D bobblehead in under 5 minutes using ChatGPT and Tripo3D. Dropped it into my space with Vision Pro. It’s wild. No wonder Apple and Meta are shifting some of their XR people onto AI teams.

AI + AR is going to change everything! I turned my photo into a 3D bobblehead in under 5 minutes using ChatGPT and Tripo3D. Dropped it into my space with Vision Pro. It’s wild. No wonder Apple and Meta are shifting some of their XR people onto AI teams.

Justin Ryan

12,857 Aufrufe • vor 1 Jahr

Building an Artificial Mechanical Engineer: All of the "AI CAD" demos you've seen have been essentially the same thing, a frontier lab LLM writing code that is translated by an existing geometry kernel into a 3d B-rep model. I think this approach is fine, but generally lossy, and lacks true spatial understanding and geometric reasoning that humans naturally posses and apply when encoding their designs in a CAD system. So I attempted to do something unique in the generative design space, building off of other generative 3d research, and trained my own (two tiny, 16M Parameter) AI models on a hyper specific set of data. Introducing FieldGeo - a set of models that encode geometry, physics (FEA, Stress) and DFM into the same latent space, and reproduces (assisted with an additional design agent) geometries to meet the stated cases. Today, it's just for L shaped brackets.

Building an Artificial Mechanical Engineer: All of the "AI CAD" demos you've seen have been essentially the same thing, a frontier lab LLM writing code that is translated by an existing geometry kernel into a 3d B-rep model. I think this approach is fine, but generally lossy, and lacks true spatial understanding and geometric reasoning that humans naturally posses and apply when encoding their designs in a CAD system. So I attempted to do something unique in the generative design space, building off of other generative 3d research, and trained my own (two tiny, 16M Parameter) AI models on a hyper specific set of data. Introducing FieldGeo - a set of models that encode geometry, physics (FEA, Stress) and DFM into the same latent space, and reproduces (assisted with an additional design agent) geometries to meet the stated cases. Today, it's just for L shaped brackets.

Connor Kapoor

85,869 Aufrufe • vor 1 Monat

2. Humane’s wearable AI device Humane revealed a wearable AI device designed to replace smartphones at a recent TED event. It appears as a tiny black puck that slips into your pocket, takes over your phone, and employs AI to update you on your day.

2. Humane’s wearable AI device Humane revealed a wearable AI device designed to replace smartphones at a recent TED event. It appears as a tiny black puck that slips into your pocket, takes over your phone, and employs AI to update you on your day.

Rowan Cheung

325,589 Aufrufe • vor 3 Jahren

🚨BREAKING: This new AI just turned a text prompt into a fully playable 3D game with NPCs, physics, multiplayer, and persistent state. Not a video. Not a demo. An actual playable world. Backed by NVIDIA, YouTube's founder, and $28M in funding. Here's everything you need to know:

🚨BREAKING: This new AI just turned a text prompt into a fully playable 3D game with NPCs, physics, multiplayer, and persistent state. Not a video. Not a demo. An actual playable world. Backed by NVIDIA, YouTube's founder, and $28M in funding. Here's everything you need to know:

Hasan Toor

91,165 Aufrufe • vor 7 Monaten

Most AI video models struggle with weight and momentum. PixVerse-R1 integrates physical laws into the generation process, ensuring that objects fall, collide, and interact realistically. It’s a physics engine disguised as a creative tool. Here's how it works:

Most AI video models struggle with weight and momentum. PixVerse-R1 integrates physical laws into the generation process, ensuring that objects fall, collide, and interact realistically. It’s a physics engine disguised as a creative tool. Here's how it works:

Farhan

26,841 Aufrufe • vor 9 Monaten

We open-source Action Images — a new representation that translates 7-DoF robot actions into interpretable images. Video models are emerging as powerful robotic foundation models, but a key challenge remains: how can we seamlessly integrate robot policies into video models? Instead of representing actions as low-dimensional control tokens, Action Images provide a pixel-grounded action representation, reframing policy learning as a visual tracking problem! By unifying observations and actions in the same video space, Action Images enable a unified robotics world model that supports video-action joint generation, action-conditioned video generation, and action labeling! Code: Paper:

We open-source Action Images — a new representation that translates 7-DoF robot actions into interpretable images. Video models are emerging as powerful robotic foundation models, but a key challenge remains: how can we seamlessly integrate robot policies into video models? Instead of representing actions as low-dimensional control tokens, Action Images provide a pixel-grounded action representation, reframing policy learning as a visual tracking problem! By unifying observations and actions in the same video space, Action Images enable a unified robotics world model that supports video-action joint generation, action-conditioned video generation, and action labeling! Code: Paper:

Chuang Gan

20,809 Aufrufe • vor 3 Monaten

Here's a look behind the scenes of how I used a 3d model, generated from an image, as a "driver" for ai animation. In the near future we'll see more 3d tools that support these types of workflows, with much more emphasis on enhancing user input instead of just letting the ai do everything. I used the 3d model to generate keyframes that I then animated in Luma Dream. By using a 3d model with a diffusion "layer" done with Krea, I got quite high quality frames with a relatively high consistency as well since the AI didn't have to "hallucinate" that much. I upscaled and detailed the frames using Magnific. Using semi-detailed 3d models as drivers for gen ai is very powerful, and it allows us to use models that are sculpted in a more free-flowing type of workflow that doesn't rely so much on high surface detailing or very time-consuming finish, but instead relies more on gestural 3d sculpting. #art #ai

Here's a look behind the scenes of how I used a 3d model, generated from an image, as a "driver" for ai animation. In the near future we'll see more 3d tools that support these types of workflows, with much more emphasis on enhancing user input instead of just letting the ai do everything. I used the 3d model to generate keyframes that I then animated in Luma Dream. By using a 3d model with a diffusion "layer" done with Krea, I got quite high quality frames with a relatively high consistency as well since the AI didn't have to "hallucinate" that much. I upscaled and detailed the frames using Magnific. Using semi-detailed 3d models as drivers for gen ai is very powerful, and it allows us to use models that are sculpted in a more free-flowing type of workflow that doesn't rely so much on high surface detailing or very time-consuming finish, but instead relies more on gestural 3d sculpting. #art #ai

Martin Nebelong

48,280 Aufrufe • vor 2 Jahren