正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Mission #18: Object Assembly, visualized as synchronized spatial data. The first-person RGB video is paired with ARKit 6DoF camera poses in world coordinates. The 3D viewer plots the camera trajectory and viewing direction against a metric grid, while LiDAR provides depth readings such as gaze-to-surface distance. Each frame connects... show more

ZenO

39,470 subscribers

11,373 次观看 • 5 天前 •via X (Twitter)

教育科学技术

Anya Rossi• Live Now

Private livecam show

35 条评论

Web3Kalito 的头像

Web3Kalito5 天前

Keep Shipping ZenO

Defi Degen❤️‍🔥 的头像

Defi Degen❤️‍🔥5 天前

Very impressive work by team.

An0i🍁 的头像

An0i🍁5 天前

this is really impressive

Lavanya 的头像

Lavanya5 天前

Clean visualization! This level of spatial data is going to level up real- world interactions of AI.

Hashiii_8 的头像

Hashiii_85 天前

iss goodd brooo

𝐃𝐎𝐍 的头像

𝐃𝐎𝐍5 天前

cool

Wizzy204💙 的头像

Wizzy204💙5 天前

Let's keep building ZenO

Unyingsan 的头像

Unyingsan5 天前

so thats the pov

Muhammad Bilal Abid 的头像

Muhammad Bilal Abid5 天前

Amazing

Dee Best 的头像

Dee Best5 天前

Looks easy and simple

POWERADE 的头像

POWERADE5 天前

It‘s always amazing

hotrod 的头像

hotrod5 天前

Let’s get to work

Bruno Jr Talent 的头像

Bruno Jr Talent5 天前

Let's go

Melvin 的头像

Melvin5 天前

Amazing

Shahid21.base.eth 的头像

Shahid21.base.eth5 天前

Amazing

mEEza 的头像

mEEza5 天前

Fairs

Akanbi 的头像

Akanbi5 天前

Let’s keep contributing guys

Dredd 的头像

Dredd5 天前

LFG

Марина Макарова 🕹️ $RCADE .netrum 的头像

Марина Макарова 🕹️ $RCADE .netrum5 天前

Amazing technology!:)

Bi2210 的头像

Bi22105 天前

Cool

Hw1n 的头像

Hw1n5 天前

Very cool 🙌

Denis 的头像

Denis5 天前

😄

dfwm 的头像

dfwm5 天前

Really good

Константин | ETHGas ⛽ 的头像

Константин | ETHGas ⛽5 天前

cool

Sergei 🐐 Tabi 🟧 base.eth | 的头像

Sergei 🐐 Tabi 🟧 base.eth |5 天前

Good

🦁LeoAngryLion🦁 的头像

🦁LeoAngryLion🦁5 天前

We are all in on this

Amazing Grace 🪔 的头像

Amazing Grace 🪔3 天前

Let's get to work 💪

Nimin 的头像

Nimin5 天前

okay letsgow

Ed 的头像

Ed5 天前

That's a cool assignment. I like it.

Amir π || TOKEN2049🇮🇩 的头像

Amir π || TOKEN2049🇮🇩5 天前

Interesting

Leo π² KGeN 🌶️ 的头像

Leo π² KGeN 🌶️5 天前

This is breath taking

Lucky_Gold🪙 的头像

Lucky_Gold🪙4 天前

Let's get to work

TechVibesVN 的头像

TechVibesVN4 天前

New missions are always a welcome sight.

𓆩𝕭𝖔𝖑𝖆𝖏𝖎𓆪 的头像

𓆩𝕭𝖔𝖑𝖆𝖏𝖎𓆪5 天前

Lfg

Aemar (✱,✱) 的头像

Aemar (✱,✱)5 天前

Let's get to work

相关视频

Before AI can understand the physical world, it needs data about the physical world. Not just images. Spatial environments. Real streets, buildings, parks, stores, museums, and public spaces captured in 3D. OVER has already reconstructed 290,000+ real-world 3D scenes, creating a growing dataset for the next generation of spatial and embodied AI. And this is exactly the kind of real-world spatial data AI companies are looking for. We're already in conversations with multiple AI and Robotics companies exploring how OVER's dataset can support the development and training of models that need to understand the physical world. The next AI race will be about real-world data.

Before AI can understand the physical world, it needs data about the physical world. Not just images. Spatial environments. Real streets, buildings, parks, stores, museums, and public spaces captured in 3D. OVER has already reconstructed 290,000+ real-world 3D scenes, creating a growing dataset for the next generation of spatial and embodied AI. And this is exactly the kind of real-world spatial data AI companies are looking for. We're already in conversations with multiple AI and Robotics companies exploring how OVER's dataset can support the development and training of models that need to understand the physical world. The next AI race will be about real-world data.

Over the Reality 🌐

24,343 次观看 • 1 个月前

ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video(ECCV2026) ReViV reconstructs viewer-centric human motion (body, hand, and gaze) and view-centric scene geometry (camera and depth) from a single egocentric RGB video in a unified feed-forward model. For visualization, the initial camera pose and camera intrinsics are estimated with GeoCalib.

ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video(ECCV2026) ReViV reconstructs viewer-centric human motion (body, hand, and gaze) and view-centric scene geometry (camera and depth) from a single egocentric RGB video in a unified feed-forward model. For visualization, the initial camera pose and camera intrinsics are estimated with GeoCalib.

Ryohei Sasaki@engineer

15,096 次观看 • 2 个月前

I tested out the egocentric headset with wrist camera + UMI gripper from Maniformer. Maniformer is the robotics data company incubated by AGIBOT . Now it has 2 product lines for data collection: egocentric headset with wrist cameras + UMI gripper. The MEgo View comes with a 5-camera headset + 2 wrist cameras, 300 degree view, global shutter, 2-hour battery life with hot swapping. The MEgo Gripper comes with 3 cameras, optional 3D tactile, global shutter, 200 degree fisheye. For both devices, you can upload the data by Wifi, USB or SD card. The data output includes 7-camera RGB image, depth info, IMU, trajectory and audio. On top of these, the gripper provides tactile info, gripper distance and angle as well. The app expands multiple use cases. It is not only for enterprises to sync the equipments and check the video stream in real time, but also for consumers to claim the tasks and earn earn real cash. Check the video for details. DM is open.

I tested out the egocentric headset with wrist camera + UMI gripper from Maniformer. Maniformer is the robotics data company incubated by AGIBOT . Now it has 2 product lines for data collection: egocentric headset with wrist cameras + UMI gripper. The MEgo View comes with a 5-camera headset + 2 wrist cameras, 300 degree view, global shutter, 2-hour battery life with hot swapping. The MEgo Gripper comes with 3 cameras, optional 3D tactile, global shutter, 200 degree fisheye. For both devices, you can upload the data by Wifi, USB or SD card. The data output includes 7-camera RGB image, depth info, IMU, trajectory and audio. On top of these, the gripper provides tactile info, gripper distance and angle as well. The app expands multiple use cases. It is not only for enterprises to sync the equipments and check the video stream in real time, but also for consumers to claim the tasks and earn earn real cash. Check the video for details. DM is open.

ClaraChengGo

13,758 次观看 • 2 个月前

This is how the robot sees the world — straight from its camera + LiDAR. A small use case of StrikeRobot Agentic, showing how agentic systems operate in real scenarios: • Detects the target person via edge-optimized face detection • Detects obstacles in real time • Estimates distance using camera physics (beyond depth sensor limits of Unitree G1) • Plans the shortest path with A* + smooth trajectories using Bezier • Continuously replans as the environment changes ✅ Result: the robot avoids obstacles, optimizes its path, and autonomously moves toward the designated person.

This is how the robot sees the world — straight from its camera + LiDAR. A small use case of StrikeRobot Agentic, showing how agentic systems operate in real scenarios: • Detects the target person via edge-optimized face detection • Detects obstacles in real time • Estimates distance using camera physics (beyond depth sensor limits of Unitree G1) • Plans the shortest path with A* + smooth trajectories using Bezier • Continuously replans as the environment changes ✅ Result: the robot avoids obstacles, optimizes its path, and autonomously moves toward the designated person.

Strike Robot

17,016 次观看 • 7 个月前

Let me explain what I'm doing here for those who are interested. I've been building a retro-style D3D12 game engine from scratch, and recently implemented a "Spatial Compression" effect. Essentially its a technique that makes distant geometry appear larger than standard perspective projection would, giving scenes a telephoto compression feel without changing the camera FOV globally (to keep things "normal" when close to the camera). The goal: foreground geometry completely unchanged, objects beyond a configurable start distance progressively scaled up, with a smooth power-curve falloff. The solution: Once the full view-projection transform has been applied, I'm holding 2D screen coordinates. Camera orientation is already resolved at that point, so it's done its job. Scaling those coordinates outward from screen center is a pure 2D operation with no dependency on where the camera is pointing. The scale factor itself is derived from Euclidean world-space distance between the camera and the vertex (not a view-space value, which would rotate with the camera). Combined with the 2D application, both ingredients are fully rotation-invariant. Critically, only the XY screen coordinates are modified. Depth values are left completely untouched, so the depth buffer and any shadow calculations remain correct. I then tried inverting the effect for the opposite in interiors, leading to "Spatial Expansion".

Let me explain what I'm doing here for those who are interested. I've been building a retro-style D3D12 game engine from scratch, and recently implemented a "Spatial Compression" effect. Essentially its a technique that makes distant geometry appear larger than standard perspective projection would, giving scenes a telephoto compression feel without changing the camera FOV globally (to keep things "normal" when close to the camera). The goal: foreground geometry completely unchanged, objects beyond a configurable start distance progressively scaled up, with a smooth power-curve falloff. The solution: Once the full view-projection transform has been applied, I'm holding 2D screen coordinates. Camera orientation is already resolved at that point, so it's done its job. Scaling those coordinates outward from screen center is a pure 2D operation with no dependency on where the camera is pointing. The scale factor itself is derived from Euclidean world-space distance between the camera and the vertex (not a view-space value, which would rotate with the camera). Combined with the 2D application, both ingredients are fully rotation-invariant. Critically, only the XY screen coordinates are modified. Depth values are left completely untouched, so the depth buffer and any shadow calculations remain correct. I then tried inverting the effect for the opposite in interiors, leading to "Spatial Expansion".

Analog Dream Dev

47,246 次观看 • 4 个月前

Robot Learning needs 4D world models! Robot Learning needs 4D world models! Robot Learning needs 4D world models! We introduce TesserAct, a 4D embodied world model that can simulate how agents interact with the 3D world over time! We achieve this by simply extending a pre-trained 2D video generation model to jointly predict RGB, depth, and surface normals. It enables: 1️⃣ Much better policy learning in the wild 2️⃣ Temporal + spatial coherence in 4D dynamic prediction 3️⃣ Novel view synthesis for embodied scenes Code: Paper Link: Project page:

Robot Learning needs 4D world models! Robot Learning needs 4D world models! Robot Learning needs 4D world models! We introduce TesserAct, a 4D embodied world model that can simulate how agents interact with the 3D world over time! We achieve this by simply extending a pre-trained 2D video generation model to jointly predict RGB, depth, and surface normals. It enables: 1️⃣ Much better policy learning in the wild 2️⃣ Temporal + spatial coherence in 4D dynamic prediction 3️⃣ Novel view synthesis for embodied scenes Code: Paper Link: Project page:

Chuang Gan

43,265 次观看 • 1 年前

Variable-length compressive tokenization is a promising direction. Not just for efficiency, but for actually learning powerful representations. FlexTok scratched the surface of this direction with images. But real-world data has additional structure that can be tapped, such as the temporal structure of videos. VideoFlexTok develops this concept for video, integrating the original progressive 1D representation with the temporal structure in the data. It leads to interesting emergent properties, such as the disentanglement of motion and semantics, only by virtue of compression. Real-world data has even more structure. I expect to see more from this direction. Check out the webpages and demos of VideoFlexTok ( image FlexTok ( and generation-by-search on such 1D tokens ( There is a lot of insightful interactive material there.

Variable-length compressive tokenization is a promising direction. Not just for efficiency, but for actually learning powerful representations. FlexTok scratched the surface of this direction with images. But real-world data has additional structure that can be tapped, such as the temporal structure of videos. VideoFlexTok develops this concept for video, integrating the original progressive 1D representation with the temporal structure in the data. It leads to interesting emergent properties, such as the disentanglement of motion and semantics, only by virtue of compression. Real-world data has even more structure. I expect to see more from this direction. Check out the webpages and demos of VideoFlexTok ( image FlexTok ( and generation-by-search on such 1D tokens ( There is a lot of insightful interactive material there.

Amir Zamir

17,787 次观看 • 6 个月前

Jhalmuri PR Video Exposed with Behind The Scenes Footage; Modi asked a woman to keep distance and not disturb the camera frame.

Jhalmuri PR Video Exposed with Behind The Scenes Footage; Modi asked a woman to keep distance and not disturb the camera frame.

Dr Ranjan

490,603 次观看 • 6 个月前

80% of the world’s economy exists in the physical world. AI has barely touched it. Niantic Spatial is building real-world foundation models that give AI the spatial intelligence to understand, navigate, and interact with 3D environments. From robotics and autonomous systems to machine-readable cities, #PhysicalAI could unlock an entirely new layer of the global economy. As CEO Inhi Cho Suh puts it: “We’re just getting started.” #WorldModels #SpatialAI #Robotics #AI

80% of the world’s economy exists in the physical world. AI has barely touched it. Niantic Spatial is building real-world foundation models that give AI the spatial intelligence to understand, navigate, and interact with 3D environments. From robotics and autonomous systems to machine-readable cities, #PhysicalAI could unlock an entirely new layer of the global economy. As CEO Inhi Cho Suh puts it: “We’re just getting started.” #WorldModels #SpatialAI #Robotics #AI

Niantic Spatial 🌎

24,645 次观看 • 2 个月前

Today we are launching Mireye (YCS26) with Y Combinator The easiest way to build agentic applications for the physical world. AI agents are starting to act in the real world, but they can't reliably understand it. Mireye is one API and MCP that connects agents to the physical world: data, enrichment, tools, and signals that power them to make decisions. One line of code to make your agents street smart.

Today we are launching Mireye (YCS26) with Y Combinator The easiest way to build agentic applications for the physical world. AI agents are starting to act in the real world, but they can't reliably understand it. Mireye is one API and MCP that connects agents to the physical world: data, enrichment, tools, and signals that power them to make decisions. One line of code to make your agents street smart.

Ansh

33,951 次观看 • 3 个月前

Today we announced RTFM (Real-Time Frame Model) — a world model that generates frames in real time from any camera viewpoint. Unlike standard video models, RTFM understands 3D geometry. You can literally move the camera through the generated world. 🎥👇

Today we announced RTFM (Real-Time Frame Model) — a world model that generates frames in real time from any camera viewpoint. Unlike standard video models, RTFM understands 3D geometry. You can literally move the camera through the generated world. 🎥👇

Keunhong Park

16,114 次观看 • 1 年前

the micro1 robotics lab: real world data for intelligent models that co-exist in the physical world. we’re in-the-wild across 75 countries in 6,000+ unique environments collecting data. diverse movements, objects, and settings. the future of AI is as human as you can imagine. join us to start training robots today (link in comments).

the micro1 robotics lab: real world data for intelligent models that co-exist in the physical world. we’re in-the-wild across 75 countries in 6,000+ unique environments collecting data. diverse movements, objects, and settings. the future of AI is as human as you can imagine. join us to start training robots today (link in comments).

Ali Ansari

209,148 次观看 • 7 个月前

Introducing Robo360 dataset 🚀, the first real-world omnispective multi-view and multi-material robotic manipulation dataset. Robo360 captures synchronized multi-modal robot-object interaction data (video, audio, proprioception, control) to facilitate research in dynamic novel-view synthesis, robot learning, physics understanding, world models, and more! Code and data coming soon!

Introducing Robo360 dataset 🚀, the first real-world omnispective multi-view and multi-material robotic manipulation dataset. Robo360 captures synchronized multi-modal robot-object interaction data (video, audio, proprioception, control) to facilitate research in dynamic novel-view synthesis, robot learning, physics understanding, world models, and more! Code and data coming soon!

Litian Liang

23,477 次观看 • 2 年前

General Trajectory (General Trajectory) is training reasoning models for robotics to bring AI into the physical world. Their first model automates real-world work like mixed-SKU palletization, picking, sorting & packing. Congrats on the launch Joshua!

General Trajectory (General Trajectory) is training reasoning models for robotics to bring AI into the physical world. Their first model automates real-world work like mixed-SKU palletization, picking, sorting & packing. Congrats on the launch Joshua!

Y Combinator

99,917 次观看 • 1 年前

📁 Fei-Fei Li founder of World Labs, says the next leap in AI is not language. Human intelligence does not just speak, it moves, perceives, and acts in the physical world. Spatial intelligence is the real core of intelligence. From text to space, from models to 3D and 4D worlds, from understanding words to interacting with reality. The next chapter is not read, it is inhabited.

📁 Fei-Fei Li founder of World Labs, says the next leap in AI is not language. Human intelligence does not just speak, it moves, perceives, and acts in the physical world. Spatial intelligence is the real core of intelligence. From text to space, from models to 3D and 4D worlds, from understanding words to interacting with reality. The next chapter is not read, it is inhabited.

Jon Hernandez

20,660 次观看 • 9 个月前

*Why panorama?* Standard video models struggle with object permanence—if a camera pans away and comes back, objects may disappear. With panoramas, the model is forced to generate everything in the scene. This serves as a "working memory" for consistent world generation. (3/N)

Why panorama? Standard video models struggle with object permanence—if a camera pans away and comes back, objects may disappear. With panoramas, the model is forced to generate everything in the scene. This serves as a "working memory" for consistent world generation. (3/N)

Ziyi Wu

22,019 次观看 • 9 个月前

From a rough 3D blockout to the final cinematic shot. Seedance 2.5 turns simple shapes and motion into a whole new world while keeping the original camera direction

From a rough 3D blockout to the final cinematic shot. Seedance 2.5 turns simple shapes and motion into a whole new world while keeping the original camera direction

Patrick

67,466 次观看 • 3 个月前