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.

Object detection on 3D Gaussian Splats. Accurate bounding boxes per detection, runs locally. Nigel Hartman ᯅ really cooked here SensAI Hackademy is hosting a lecture with Ian Curtis from World Labs on the 8th on this:

Johannes Tscharn

2,468 subscribers

36,147 views • 2 months 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 #CVPR2026 paper from our research team is trending #1 on Hugging Face 🤗 Meet LocateAnything: a vision-language detection model that rethinks bounding box prediction. For AI agents and robots, “seeing” is only useful if a model can pinpoint where something is fast enough to act. Trained on 138M high-quality samples, LocateAnything decodes bounding boxes in parallel instead of one coordinate at a time, improving localization accuracy while dramatically increasing throughput for visual grounding and detection. Project page:

This #CVPR2026 paper from our research team is trending #1 on Hugging Face 🤗 Meet LocateAnything: a vision-language detection model that rethinks bounding box prediction. For AI agents and robots, “seeing” is only useful if a model can pinpoint where something is fast enough to act. Trained on 138M high-quality samples, LocateAnything decodes bounding boxes in parallel instead of one coordinate at a time, improving localization accuracy while dramatically increasing throughput for visual grounding and detection. Project page:

NVIDIA AI

338,464 views • 2 months ago

Today we release Boxer, a new lightweight approach that lifts open-world 2D bounding boxes to *metric* 3D: Here we show Boxer in action on an egocentric sequence captured from smart glasses:

Today we release Boxer, a new lightweight approach that lifts open-world 2D bounding boxes to metric 3D: Here we show Boxer in action on an egocentric sequence captured from smart glasses:

Daniel DeTone

79,889 views • 4 months ago

Train a TensorFlow object detection model – then deploy it on a robot 🤖 Iulia Feroli (Iulia Feroli) shows how to turn a notebook into a real-time object detection app. This tutorial works for any project – though we demonstrate the deployment on (and assisted by!) the #ReachyMini, an open-source robot from Pollen Robotics. Built with PyCharm + Claude Code. 👉 Watch it in action:

Train a TensorFlow object detection model – then deploy it on a robot 🤖 Iulia Feroli (Iulia Feroli) shows how to turn a notebook into a real-time object detection app. This tutorial works for any project – though we demonstrate the deployment on (and assisted by!) the #ReachyMini, an open-source robot from Pollen Robotics. Built with PyCharm + Claude Code. 👉 Watch it in action:

PyCharm, a JetBrains IDE

34,908 views • 3 months ago

Gaussian splats don't simulate light. They capture it. I took one photograph of this room and generated it as a fully walkable 3D world in Mint. The volumetric rays, the shadow play on the rug, all preserved. This is what real-time 3D is becoming

Gaussian splats don't simulate light. They capture it. I took one photograph of this room and generated it as a fully walkable 3D world in Mint. The volumetric rays, the shadow play on the rug, all preserved. This is what real-time 3D is becoming

mint

15,446 views • 2 months ago

IronSight turns 2D range footage into a replayable 4D world -- with shot detection, 3D target tracking, and a camera you can move anywhere. Seeing my own runs reconstructed from every angle is ridiculously fun. Can't wait till we can run this tech in real time.

IronSight turns 2D range footage into a replayable 4D world -- with shot detection, 3D target tracking, and a camera you can move anywhere. Seeing my own runs reconstructed from every angle is ridiculously fun. Can't wait till we can run this tech in real time.

Bilawal Sidhu

21,142 views • 1 month ago

Pothole detection on the road in real time using Ultralytics YOLO26! 🕳️ Manual road inspections are slow, costly, and hard to scale. With object detection, potholes can be identified directly from street-level images or video feeds, enabling faster and more consistent road condition monitoring. How I built this demo: ✅ Trained a segmentation model on a custom dataset. ✅ Generated mask contours for each pothole. ✅ Leveraged the onnx-exported model for faster processing. #Pothole #RoadDamage #AI

Pothole detection on the road in real time using Ultralytics YOLO26! 🕳️ Manual road inspections are slow, costly, and hard to scale. With object detection, potholes can be identified directly from street-level images or video feeds, enabling faster and more consistent road condition monitoring. How I built this demo: ✅ Trained a segmentation model on a custom dataset. ✅ Generated mask contours for each pothole. ✅ Leveraged the onnx-exported model for faster processing. #Pothole #RoadDamage #AI

Muhammad Rizwan Munawar

30,677 views • 5 months ago

Worth mentioning to all the people on me about the pupil detection. It's a bug in the Comfy implementation and will get sorted.... this is day 1 testing remember. Here is the same video ran on Wan's website - near perfect pupil tracking.

Worth mentioning to all the people on me about the pupil detection. It's a bug in the Comfy implementation and will get sorted.... this is day 1 testing remember. Here is the same video ran on Wan's website - near perfect pupil tracking.

A.I.Warper

20,567 views • 11 months ago

Listen as Gen. Stephen Whiting, #USSPACECOM commander, breaks down how missile detection really works while on the sidelines of #SPC25, using "A House of Dynamite" to contrast Hollywood with USSPACECOM's real-world missile warning mission. 👉

Listen as Gen. Stephen Whiting, #USSPACECOM commander, breaks down how missile detection really works while on the sidelines of #SPC25, using "A House of Dynamite" to contrast Hollywood with USSPACECOM's real-world missile warning mission. 👉

U.S. Space Command

13,412 views • 8 months ago

Are we done with object detection? What about tiny objects beyond 200 meters? 🔎 Telescope 🔭 addresses long-range perception by explicitly tackling extreme scale imbalance ⚖️ in images. It hinges on a learnable hyperbolic foveation transform from a low-resolution image, magnifying distant regions 🔍 while compressing nearby ones - effectively normalizing object scales with minimal computational overhead. Objects are detected in the transformed (Riemannian) space using a novel bounding box parameterization and are then mapped back to the original image. Project:

Are we done with object detection? What about tiny objects beyond 200 meters? 🔎 Telescope 🔭 addresses long-range perception by explicitly tackling extreme scale imbalance ⚖️ in images. It hinges on a learnable hyperbolic foveation transform from a low-resolution image, magnifying distant regions 🔍 while compressing nearby ones - effectively normalizing object scales with minimal computational overhead. Objects are detected in the transformed (Riemannian) space using a novel bounding box parameterization and are then mapped back to the original image. Project:

Felix Heide

188,663 views • 3 months ago

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.

KIRI Engine - 3D Scanner App

30,603 views • 1 month ago

Everyone is sleeping on this pass because it isn’t from Pedri Tchouameni really cooked here The first time pass, the touch from Vini 🥶🥶🥶🥶

Everyone is sleeping on this pass because it isn’t from Pedri Tchouameni really cooked here The first time pass, the touch from Vini 🥶🥶🥶🥶

Newton

649,940 views • 5 months ago

This is some quietly impressive work on making video world models actually controllable in 4D space. VerseCrafter lets you take an input image, use something like Blender to animate the 3D camera path and object trajectories, then uses that to condition generation. Scribbling in 2D feels so crude in comparison. The authors represent everything in a shared 4D world state - static background as a point cloud, moving objects as 3D gaussian trajectories. The gaussians are an interesting choice because they capture position, shape, and orientation probabilistically rather than forcing rigid bounding boxes or category specific models like SMPL-X for human bodies. They bolt this onto frozen Wan2.1 with a lightweight adapter, so they get a strong video prior. They also built a pipeline to auto extract 4D annotations from real world videos to train this puppy. It doesn't look sexy yet, but IMO this is the interface video world models need - actual 3D authoring tools to exert control rather than crude scribbles and prompt incantations.

This is some quietly impressive work on making video world models actually controllable in 4D space. VerseCrafter lets you take an input image, use something like Blender to animate the 3D camera path and object trajectories, then uses that to condition generation. Scribbling in 2D feels so crude in comparison. The authors represent everything in a shared 4D world state - static background as a point cloud, moving objects as 3D gaussian trajectories. The gaussians are an interesting choice because they capture position, shape, and orientation probabilistically rather than forcing rigid bounding boxes or category specific models like SMPL-X for human bodies. They bolt this onto frozen Wan2.1 with a lightweight adapter, so they get a strong video prior. They also built a pipeline to auto extract 4D annotations from real world videos to train this puppy. It doesn't look sexy yet, but IMO this is the interface video world models need - actual 3D authoring tools to exert control rather than crude scribbles and prompt incantations.

Bilawal Sidhu

26,017 views • 7 months ago

Generate FULLY CONTROLLABLE 3D assets from a SINGLE image, locally on your PC. Made a 1-click launcher for the official Anigen Gradio app, and a dedicated viewer. Crazy this is now possible. What you're seeing here came from one image. Requires: NVIDIA GPU 6GB VRAM

Generate FULLY CONTROLLABLE 3D assets from a SINGLE image, locally on your PC. Made a 1-click launcher for the official Anigen Gradio app, and a dedicated viewer. Crazy this is now possible. What you're seeing here came from one image. Requires: NVIDIA GPU 6GB VRAM

cocktail peanut

68,177 views • 4 months ago

Every time a sale is made on Shopify this Black Friday weekend, it shows up on this 3D globe. It runs at 120fps in the web with a full 3D environment, physics engine, music synth, VR support, and more. It’s hard to believe it's a React app 👀🧵

Every time a sale is made on Shopify this Black Friday weekend, it shows up on this 3D globe. It runs at 120fps in the web with a full 3D environment, physics engine, music synth, VR support, and more. It’s hard to believe it's a React app 👀🧵

Daniel Beauchamp

464,586 views • 1 year ago

🎨 Gaussian Splat rigging opens infinite artistic possibilities! Realtime rendering with my VHS effect in VR 1.5M splats running at 80 FPS in VR with bone-based Mixamo rig animation. Travel into the volumetric worlds of Valerian and the City of a Thousand Planets, reimagined in that bold 1980s sci-fi aesthetic ✨ World Labs Theoretically Media Technical • GPU compute shader skinning (256 threads) • Linear Blend Skinning (LBS) with up to 4 bones per splat • Bind pose capture for accurate deformation • CommandBuffer synchronization for frame-perfect timing Why splats are perfect for comic art I think: Each splat is a volumetric 3D ellipsoid that naturally creates crisp edges and flat color regions—the essence of cel-shading. No complex shader tricks needed. The volumetric representation itself gives you that graphic novel aesthetic. #Realtime #GaussianSplatting #VR #GameDev #Unity3D #VolumetricRendering #ComicArt

🎨 Gaussian Splat rigging opens infinite artistic possibilities! Realtime rendering with my VHS effect in VR 1.5M splats running at 80 FPS in VR with bone-based Mixamo rig animation. Travel into the volumetric worlds of Valerian and the City of a Thousand Planets, reimagined in that bold 1980s sci-fi aesthetic ✨ World Labs Theoretically Media Technical • GPU compute shader skinning (256 threads) • Linear Blend Skinning (LBS) with up to 4 bones per splat • Bind pose capture for accurate deformation • CommandBuffer synchronization for frame-perfect timing Why splats are perfect for comic art I think: Each splat is a volumetric 3D ellipsoid that naturally creates crisp edges and flat color regions—the essence of cel-shading. No complex shader tricks needed. The volumetric representation itself gives you that graphic novel aesthetic. #Realtime #GaussianSplatting #VR #GameDev #Unity3D #VolumetricRendering #ComicArt

Daniel Skaale

15,155 views • 8 months ago

>Attack in Dubai. The MOD announced the detection of 7 ballistic missiles & 27 drones today >One of the impacts from a Hezbollah barrage earlier >A container ship tried crossing Hormuz and is now on fire with some crew missing >CENTCOM confirms 4 dead in the stratotanker downing

>Attack in Dubai. The MOD announced the detection of 7 ballistic missiles & 27 drones today >One of the impacts from a Hezbollah barrage earlier >A container ship tried crossing Hormuz and is now on fire with some crew missing >CENTCOM confirms 4 dead in the stratotanker downing

barry with the NED

17,217 views • 5 months ago

Atlanta is hosting the first of its six FIFA Club World Cup matches today at Mercedes-Benz Stadium, with Chelsea FC taking on LAFC at 3 p.m. This is the first time the U.S. has hosted a FIFA Club World Cup.

Atlanta is hosting the first of its six FIFA Club World Cup matches today at Mercedes-Benz Stadium, with Chelsea FC taking on LAFC at 3 p.m. This is the first time the U.S. has hosted a FIFA Club World Cup.

Everything Georgia

106,330 views • 1 year ago

🚨 DISTURBING: A man from Northern Nigeria was captured on camera barbing a toddler with a sh@rp object as the child is seen cřy!ng in pá!n. Is this right for a child like this?

🚨 DISTURBING: A man from Northern Nigeria was captured on camera barbing a toddler with a sh@rp object as the child is seen cřy!ng in pá!n. Is this right for a child like this?

BBOreporters

394,179 views • 1 month ago

Trained on zero real-world data. Learned to walk, pick up boxes, and follow multi-step instructions... in the REAL world. ( 📌 Paper below) Researchers from Amazon FAR, Berkeley, Stanford, and CMU scanned real rooms with an iPhone, rebuilt them as 3D Gaussian Splatting scenes, then generated 48,000 synthetic trajectories of a Unitree G1 walking, grasping, and placing objects inside those virtual replicas. They rendered the robot's first-person camera view from each run and paired it with the matching language instruction and motion data. That's the dataset every humanoid team needs and nobody has: synced egocentric video + language + kinematics, at scale. Instead of collecting it in the real world, they manufactured it. They trained a vision-language-kinematics policy on that synthetic data alone, then deployed it on the physical G1 across five task types: navigation to a named object, lifting boxes of three different sizes with no per-size tuning, chained multi-step tasks, robustness to mid-task layout changes and flickering lights, and multi-minute long-horizon runs. No real-world fine-tuning at any point. Real-world interaction data has been the hard limit on humanoid learning... slow, expensive, and small. If scanning a room once and synthesizing thousands of labeled interactions holds up as a general recipe, that limit moves. Data stops being the bottleneck robotics teams have to solve for. 📌 Paper: Project: ——- Weekly robotics and AI insights. Subscribe free:

Trained on zero real-world data. Learned to walk, pick up boxes, and follow multi-step instructions... in the REAL world. ( 📌 Paper below) Researchers from Amazon FAR, Berkeley, Stanford, and CMU scanned real rooms with an iPhone, rebuilt them as 3D Gaussian Splatting scenes, then generated 48,000 synthetic trajectories of a Unitree G1 walking, grasping, and placing objects inside those virtual replicas. They rendered the robot's first-person camera view from each run and paired it with the matching language instruction and motion data. That's the dataset every humanoid team needs and nobody has: synced egocentric video + language + kinematics, at scale. Instead of collecting it in the real world, they manufactured it. They trained a vision-language-kinematics policy on that synthetic data alone, then deployed it on the physical G1 across five task types: navigation to a named object, lifting boxes of three different sizes with no per-size tuning, chained multi-step tasks, robustness to mid-task layout changes and flickering lights, and multi-minute long-horizon runs. No real-world fine-tuning at any point. Real-world interaction data has been the hard limit on humanoid learning... slow, expensive, and small. If scanning a room once and synthesizing thousands of labeled interactions holds up as a general recipe, that limit moves. Data stops being the bottleneck robotics teams have to solve for. 📌 Paper: Project: ——- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

12,950 views • 1 month ago