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.

Perception is a system problem. One camera misses depth, occlusion, and hand interactions. Gen DAS Ego uses 6 synced cameras (270° FOV). What you get: cm-level joint tracking ms-level head–hand sync full coverage Built for real use: plug-and-play fit 24/7 swappable battery

Genrobot.AI

1,232 subscribers

15,317 views • 5 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

2 Comments

Srikanth Vidapanakal4 months ago

Why do you need 6 cameras? Is it not too redundant?

Rohan Paul4 months ago

I think, this is a serious attempt at fixing one of robotics’ least glamorous bottlenecks: getting interaction data that is actually usable.

Related Videos

UBTECH officially launched Cruzr Y1 — a wheeled industrial humanoid built for factory material handling. 🤖 It is designed for bins, cartons, material loading, unloading, palletizing, depalletizing, and sorting. Specs that matter: → 360° omni-wheels + vertical lift for tight workshops and dense equipment areas → Harmonic joint arms with brakes and torque sensors for precise, stable handling → 360° safety perception with LiDAR, depth cameras, ToF, and IMU across the head, wrists, and chassis → 4+ hours under full load, with auto-charging and quick battery swap for 24-hour shift work

UBTECH officially launched Cruzr Y1 — a wheeled industrial humanoid built for factory material handling. 🤖 It is designed for bins, cartons, material loading, unloading, palletizing, depalletizing, and sorting. Specs that matter: → 360° omni-wheels + vertical lift for tight workshops and dense equipment areas → Harmonic joint arms with brakes and torque sensors for precise, stable handling → 360° safety perception with LiDAR, depth cameras, ToF, and IMU across the head, wrists, and chassis → 4+ hours under full load, with auto-charging and quick battery swap for 24-hour shift work

RoboHub🤖

12,791 views • 2 months ago

You can do some pretty fun realtime VFX once the depth output is just another (Type)GPU buffer :D I basically yoinked my old 3D fire sim (that is actually a fluid sim but do not tell anyone) and plugged it into the depth pipeline together with hand tracking Everything here is built from scratch in TypeGPU, so inference, simulation and rendering can share GPU resources and interleave passes directly. That’s 2 NN inferences, a full 3D fluid sim, relighting and rendering in one command encoder, still under 16 ms with no CPU sync in between

You can do some pretty fun realtime VFX once the depth output is just another (Type)GPU buffer :D I basically yoinked my old 3D fire sim (that is actually a fluid sim but do not tell anyone) and plugged it into the depth pipeline together with hand tracking Everything here is built from scratch in TypeGPU, so inference, simulation and rendering can share GPU resources and interleave passes directly. That’s 2 NN inferences, a full 3D fluid sim, relighting and rendering in one command encoder, still under 16 ms with no CPU sync in between

Konrad Reczko

26,915 views • 21 days ago

So cool...a humanoid just drove a go-kart for real. A Unitree G1 lowers itself into the tight cockpit, hands on the wheel, feet on the pedals, then runs the track， even drifts. It shows constrained whole-body loco-manipulation, mobile pick-and-place, and hand-eye-foot coordination in one sequence. This comes from China’s Symbiosis Robotics and their Direct Perception Control (DPC) model. It skips the usual high-level goals + tracker stack, mapping vision, language, body state and feedback straight to joint and hand targets. The focus is whole-body coordination for loco-manipulation. Interestingly, data diversity...Training used 15,010 hours of joint-aligned data-- 6,781h human egocentric, 4,024h armed robots, 3,660h wheeled humanoids, 545h bipedal. Teleop, head-mounted and egocentric sources were all converted into time-aligned joint trajectories across embodiments. A clean test that packs perception, balance and continuous whole-body control into one task chain ,and leaves room for other real-world scenarios.

So cool...a humanoid just drove a go-kart for real. A Unitree G1 lowers itself into the tight cockpit, hands on the wheel, feet on the pedals, then runs the track， even drifts. It shows constrained whole-body loco-manipulation, mobile pick-and-place, and hand-eye-foot coordination in one sequence. This comes from China’s Symbiosis Robotics and their Direct Perception Control (DPC) model. It skips the usual high-level goals + tracker stack, mapping vision, language, body state and feedback straight to joint and hand targets. The focus is whole-body coordination for loco-manipulation. Interestingly, data diversity...Training used 15,010 hours of joint-aligned data-- 6,781h human egocentric, 4,024h armed robots, 3,660h wheeled humanoids, 545h bipedal. Teleop, head-mounted and egocentric sources were all converted into time-aligned joint trajectories across embodiments. A clean test that packs perception, balance and continuous whole-body control into one task chain ,and leaves room for other real-world scenarios.

CyberRobo

76,039 views • 28 days ago

THIS GUY BUILT REAL FLYING SWORD DRONES AND CONTROLS THEM WITH HAND GESTURES fan shisan is a physics student in chengdu who coded and built flying drones shaped like actual swords he controls them entirely with hand gestures. no controller or a phone. just his hands wave your hand and the sword follows. point and it flies where you direct it. multiple swords in the air at the same time responding to different gestures he built the gesture recognition system HIMSELF and coded the flight control algorithms. designed the drone hardware in the shape of swords. the gesture tracking uses sensors that read the position and movement of his hands in real time and translate them into flight commands for each drone independently he even built one large enough to ride on a physics student with coding skills just brought something straight out of a kung fu movie into the real world the line between science fiction and side projects is getting thinner every month

THIS GUY BUILT REAL FLYING SWORD DRONES AND CONTROLS THEM WITH HAND GESTURES fan shisan is a physics student in chengdu who coded and built flying drones shaped like actual swords he controls them entirely with hand gestures. no controller or a phone. just his hands wave your hand and the sword follows. point and it flies where you direct it. multiple swords in the air at the same time responding to different gestures he built the gesture recognition system HIMSELF and coded the flight control algorithms. designed the drone hardware in the shape of swords. the gesture tracking uses sensors that read the position and movement of his hands in real time and translate them into flight commands for each drone independently he even built one large enough to ride on a physics student with coding skills just brought something straight out of a kung fu movie into the real world the line between science fiction and side projects is getting thinner every month

Om Patel

307,609 views • 3 months ago

Dexterous hands are one of the biggest challenges in robotics, with even Elon Musk noting their development accounts for half of a humanoid robot's total work. A new approach from the Y-Hand M1 bionic hand may be a significant step forward. Based on an international first-of-its-kind "bionic tension-compression theory," the M1 replaces traditional rigid hinges with a 6-DoF joint system and uses self-developed magnetic artificial muscles. This design allows it to perform complex, human-like tasks, including: ► Mastering all 33 Feix dexterous grasp categories. ► Precisely twirling playing cards and threading a needle with subtle human-like adjustments. ► Smoothly twisting bottle caps and turning book pages. The team behind the M1 is already working on the next-gen Y-Hand M3, aiming for around 70 degrees of freedom, believing that robotic hands may soon reach or even exceed human-level dexterity.

Dexterous hands are one of the biggest challenges in robotics, with even Elon Musk noting their development accounts for half of a humanoid robot's total work. A new approach from the Y-Hand M1 bionic hand may be a significant step forward. Based on an international first-of-its-kind "bionic tension-compression theory," the M1 replaces traditional rigid hinges with a 6-DoF joint system and uses self-developed magnetic artificial muscles. This design allows it to perform complex, human-like tasks, including: ► Mastering all 33 Feix dexterous grasp categories. ► Precisely twirling playing cards and threading a needle with subtle human-like adjustments. ► Smoothly twisting bottle caps and turning book pages. The team behind the M1 is already working on the next-gen Y-Hand M3, aiming for around 70 degrees of freedom, believing that robotic hands may soon reach or even exceed human-level dexterity.

RoboHub🤖

64,560 views • 1 year ago

342 skilled construction workers retire every day in the US. Use interior wall finishing as an example, you can't just hand someone a trowel and get a Level 5 wall finish. It takes years to develop that skill. This is Okibo's fully autonomous interior finishing robot that does drywall mudding, joint taping, sanding (Level 4 and 5 finishes), and spray and roller painting (the video is a sanding pass). It can reach up to 24' so it's designed for high reach in large industrial spaces (data centers, commercial, offsite manufacturing). You just swap the toolhead for a different finish application. It's an autonomous operation, vision scans the path and starts, there’s one operator overseeing the work and changing tool heads when needed. Today, it can produce 6,000 sqft/day (up to 8-10x more productive depending on the space).

342 skilled construction workers retire every day in the US. Use interior wall finishing as an example, you can't just hand someone a trowel and get a Level 5 wall finish. It takes years to develop that skill. This is Okibo's fully autonomous interior finishing robot that does drywall mudding, joint taping, sanding (Level 4 and 5 finishes), and spray and roller painting (the video is a sanding pass). It can reach up to 24' so it's designed for high reach in large industrial spaces (data centers, commercial, offsite manufacturing). You just swap the toolhead for a different finish application. It's an autonomous operation, vision scans the path and starts, there’s one operator overseeing the work and changing tool heads when needed. Today, it can produce 6,000 sqft/day (up to 8-10x more productive depending on the space).

Nick Durham

324,642 views • 4 months ago

🎙️ Excited to introduce one of my favorite projects from the past year: TeleDexter, from the BIGAI dexterity team. It’s a stable, human-level dexterous teleoperation system and a suite of autonomous policies trained with it. Pen spinning, complex in-hand reorientation, and long-horizon tool use—once seen as the holy grail of manipulation—are now unlocked. 🧵👇 The hardware is already here; we have some incredible high-DoF robotic hands. The bottleneck? The controller. Most current systems are stuck in "quasi-static" grasping mode. Meanwhile, dynamic in-hand dexterity has remained severely limited. 🧠 To unlock the massive capabilities of human-like hands, we need to build an excellent "cerebellum" for dexterous hands. TeleDexter solves this with a novel co-tracking approach: it simultaneously tracks both human hand kinematics and object states, beautifully bridging the gap between human intent and robotic control. In order to train a better co-tracking policy that works robustly in the real world, we designed : (1) a hybrid reward design that combines consecutive goal reaching and dense tracking, (2) an action masking strategy during training that enhances sim2real performance, (3) a dexterous curriculum for learning the long-horizon interactions. Each design is inspired by numerous trials and countless real-world experiments. We’ve synthesized all the system details, engineering challenges, and core insights into our latest post. If you're interested in the future of dexterous manipulation, grab a coffee and check it out (9-min read): If you have more time, check out the paper:

🎙️ Excited to introduce one of my favorite projects from the past year: TeleDexter, from the BIGAI dexterity team. It’s a stable, human-level dexterous teleoperation system and a suite of autonomous policies trained with it. Pen spinning, complex in-hand reorientation, and long-horizon tool use—once seen as the holy grail of manipulation—are now unlocked. 🧵👇 The hardware is already here; we have some incredible high-DoF robotic hands. The bottleneck? The controller. Most current systems are stuck in "quasi-static" grasping mode. Meanwhile, dynamic in-hand dexterity has remained severely limited. 🧠 To unlock the massive capabilities of human-like hands, we need to build an excellent "cerebellum" for dexterous hands. TeleDexter solves this with a novel co-tracking approach: it simultaneously tracks both human hand kinematics and object states, beautifully bridging the gap between human intent and robotic control. In order to train a better co-tracking policy that works robustly in the real world, we designed : (1) a hybrid reward design that combines consecutive goal reaching and dense tracking, (2) an action masking strategy during training that enhances sim2real performance, (3) a dexterous curriculum for learning the long-horizon interactions. Each design is inspired by numerous trials and countless real-world experiments. We’ve synthesized all the system details, engineering challenges, and core insights into our latest post. If you're interested in the future of dexterous manipulation, grab a coffee and check it out (9-min read): If you have more time, check out the paper:

Siyuan Huang

12,541 views • 2 months ago

Just built an end-to-end AI agent workflow stack in 3 days that automates everything from recruiting to reminders to reporting for electrician franchises. What used to take 6+ SaaS tools and a full ops team? Now handled by 12 specialized agents: •Hiring •Screening •Follow-ups •Reminders •AI call reps •Reviews •Marketing •Finance tracking …and more. Trained each one to plug directly into ServiceTitan, Twilio, Slack, email, and CRM. Next: rolling it out to 50+ franchises, replacing entire workflows with agents that work 24/7, never forget, and never need a break. The SaaS model is being rewritten — one operator at a time.

Just built an end-to-end AI agent workflow stack in 3 days that automates everything from recruiting to reminders to reporting for electrician franchises. What used to take 6+ SaaS tools and a full ops team? Now handled by 12 specialized agents: •Hiring •Screening •Follow-ups •Reminders •AI call reps •Reviews •Marketing •Finance tracking …and more. Trained each one to plug directly into ServiceTitan, Twilio, Slack, email, and CRM. Next: rolling it out to 50+ franchises, replacing entire workflows with agents that work 24/7, never forget, and never need a break. The SaaS model is being rewritten — one operator at a time.

Bennett Spooner

10,319 views • 1 year ago

SOMEONE BUILT AN ENTIRE COMPANY BRAIN INSIDE CLAUDE CODE IN 7 DAYS Not Obsidian. Fully custom. A living map of every employee, every agent, every SOP on one screen. Click any node and it opens up: - what department it's in - what SOPs are attached - what it can actually access that permission layer is the whole game an employee opens the chat and the AI already knows their access level, agents, SOPs and tools surface in the conversation like you tagged them by hand Obsidian cannot do this... no dev team. no six month build. no enterprise budget. just Claude Code and one week has everything to build one full guide on building your own team below

SOMEONE BUILT AN ENTIRE COMPANY BRAIN INSIDE CLAUDE CODE IN 7 DAYS Not Obsidian. Fully custom. A living map of every employee, every agent, every SOP on one screen. Click any node and it opens up: - what department it's in - what SOPs are attached - what it can actually access that permission layer is the whole game an employee opens the chat and the AI already knows their access level, agents, SOPs and tools surface in the conversation like you tagged them by hand Obsidian cannot do this... no dev team. no six month build. no enterprise budget. just Claude Code and one week has everything to build one full guide on building your own team below

Madni Aghadi

397,670 views • 2 months ago

If you don't know what a RAG system is, you're already behind. Plenty of people are still typing questions into ChatGPT and pasting answers back out. That's the beginner level. You're renting a smart stranger who forgets you the second you close the tab and makes things up, because it has never seen your actual work. A RAG system is a completely different level of using AI. You build an AI plugged into your own world. Your files, company's docs, notes. It's not pulling from the internet, it only knows what you fed it. Ask it anything and it digs through your data, finds the answer, and shows you which document it came from. That's the gap. One person is asking a chatbot for generic answers. The other has built a private expert that knows their business cold and answers with receipts. And that gap is worth real money: > At work, the person who can wire a company's knowledge into an AI that actually answers correctly is rare and paid like it. > As a business, companies pay serious money for a system that reads their internal docs and answers staff and customers accurately. You build it once, you sell it. > For yourself, you get a second brain that actually remembers. Same skill behind all three, and it's still rare enough to be worth learning. Full breakdown in the article below.

If you don't know what a RAG system is, you're already behind. Plenty of people are still typing questions into ChatGPT and pasting answers back out. That's the beginner level. You're renting a smart stranger who forgets you the second you close the tab and makes things up, because it has never seen your actual work. A RAG system is a completely different level of using AI. You build an AI plugged into your own world. Your files, company's docs, notes. It's not pulling from the internet, it only knows what you fed it. Ask it anything and it digs through your data, finds the answer, and shows you which document it came from. That's the gap. One person is asking a chatbot for generic answers. The other has built a private expert that knows their business cold and answers with receipts. And that gap is worth real money: > At work, the person who can wire a company's knowledge into an AI that actually answers correctly is rare and paid like it. > As a business, companies pay serious money for a system that reads their internal docs and answers staff and customers accurately. You build it once, you sell it. > For yourself, you get a second brain that actually remembers. Same skill behind all three, and it's still rare enough to be worth learning. Full breakdown in the article below.

Yarchi

32,840 views • 2 months ago

🚨 FLOCK JUST GOT CAUGHT BY A REPORTER — THEIR CAMERAS ARE SECRETLY TRACKING PEOPLE IN REAL TIME "You're saying Flock does not track people, correct?" A Flock representative tried to deny it. But then they showed the Condor camera — the one designed to literally follow your movements in real time. No matter which way you move, the camera moves with you. And that's not all. These cameras can zoom in on your phone screen to see what you're looking at, recognize faces, and pull up personal details in minutes using commercial facial recognition. One example: They tracked a couple arguing at a street market and within two minutes knew one just finished medical school and the other has chronic IBS. Cops are openly bragging that "you can't get a breath of fresh air in or out without us knowing." They said it was just for license plates. This is full-blown surveillance, and it's already everywhere. Should Flock's Condor cameras be allowed to track people in real time?

🚨 FLOCK JUST GOT CAUGHT BY A REPORTER — THEIR CAMERAS ARE SECRETLY TRACKING PEOPLE IN REAL TIME "You're saying Flock does not track people, correct?" A Flock representative tried to deny it. But then they showed the Condor camera — the one designed to literally follow your movements in real time. No matter which way you move, the camera moves with you. And that's not all. These cameras can zoom in on your phone screen to see what you're looking at, recognize faces, and pull up personal details in minutes using commercial facial recognition. One example: They tracked a couple arguing at a street market and within two minutes knew one just finished medical school and the other has chronic IBS. Cops are openly bragging that "you can't get a breath of fresh air in or out without us knowing." They said it was just for license plates. This is full-blown surveillance, and it's already everywhere. Should Flock's Condor cameras be allowed to track people in real time?

HustleBitch

675,924 views • 2 months ago

Teaching robots real dexterity has always been a challenge. But what if they could handle tools like a human? DexterityGen (DexGen) is a new system that helps robots use their hands better. It improves how they grip, move, and handle objects… from holding a pen to using a screwdriver. DexGen learns in simulation and refines its skills in the real world, making robotic hands much more useful. What makes DexGen special? ✅ Smarter movements that refine rough actions into precise skills ✅ Trained on a massive collection of dexterous tasks for better learning ✅ Better teleoperation that makes robotic hand control easier and safer ✅ Handles real-world challenges like small objects, tricky angles, and gravity This moves robots closer to real dexterity. It makes tool use more natural, improves stability, and brings robotic hands one step closer to human-level skill. Seen at Zhao-Heng Yin 🫶 Github: Paper:

Teaching robots real dexterity has always been a challenge. But what if they could handle tools like a human? DexterityGen (DexGen) is a new system that helps robots use their hands better. It improves how they grip, move, and handle objects… from holding a pen to using a screwdriver. DexGen learns in simulation and refines its skills in the real world, making robotic hands much more useful. What makes DexGen special? ✅ Smarter movements that refine rough actions into precise skills ✅ Trained on a massive collection of dexterous tasks for better learning ✅ Better teleoperation that makes robotic hand control easier and safer ✅ Handles real-world challenges like small objects, tricky angles, and gravity This moves robots closer to real dexterity. It makes tool use more natural, improves stability, and brings robotic hands one step closer to human-level skill. Seen at Zhao-Heng Yin 🫶 Github: Paper:

Ilir Aliu

51,526 views • 1 year ago

SpaceXAI engineer, Lauren Tan: "My 15-25 GrokBot agents can already replace months or even years of SpaceXAI engineers work I just have one Chief of Staff Bot that manages all the other agents. But the cost of Agents is a real problem - and we’re investing a ton in efficiency" In 30-min SpaceXAI engineer (poteto) shows how she uses GrokBot, what she has already built, and how to replicate her agent team Worth more than any course on agent engineering - from the team that is actually building this Watch it now, build your first GrokBot - then read the article and create a full 24/7 agent system for 100% of your tasks ↓

SpaceXAI engineer, Lauren Tan: "My 15-25 GrokBot agents can already replace months or even years of SpaceXAI engineers work I just have one Chief of Staff Bot that manages all the other agents. But the cost of Agents is a real problem - and we’re investing a ton in efficiency" In 30-min SpaceXAI engineer (poteto) shows how she uses GrokBot, what she has already built, and how to replicate her agent team Worth more than any course on agent engineering - from the team that is actually building this Watch it now, build your first GrokBot - then read the article and create a full 24/7 agent system for 100% of your tasks ↓

codila

38,516 views • 13 days ago

The largest fully annotated open egocentric human dataset. Today we're open-sourcing EgoSuite-Open100K with Hugging Face : 100,000 hours of egocentric human data, free for anyone to use. Physical AI has a scaling law of its own now, and its input is human data. That part is settled. What the field still needs is a shared foundation to build on. 15,000+ tasks. 15,000+ real scenes, from factory floors to retail backrooms. Hand pose, body pose and subtask-level semantics, with wrist camera coverage on part of the set. Licensed for commercial training, not research-only. We build the data infrastructure for Physical AI. Open100K is the first public layer of it. The first 10,000 hours are live now, with the rest rolling out in stages.

The largest fully annotated open egocentric human dataset. Today we're open-sourcing EgoSuite-Open100K with Hugging Face : 100,000 hours of egocentric human data, free for anyone to use. Physical AI has a scaling law of its own now, and its input is human data. That part is settled. What the field still needs is a shared foundation to build on. 15,000+ tasks. 15,000+ real scenes, from factory floors to retail backrooms. Hand pose, body pose and subtask-level semantics, with wrist camera coverage on part of the set. Licensed for commercial training, not research-only. We build the data infrastructure for Physical AI. Open100K is the first public layer of it. The first 10,000 hours are live now, with the rest rolling out in stages.

Lightwheel

73,678 views • 25 days ago

🚀After Years of building battle-tested autonomy for drones, we’re excited to make JETCORE-FC publicly available ! Our flagship compute module along with Flight control carrier board designed for real-time perception, autonomy, and edge AI workloads. Built around NVIDIA Jetson, JETCORE-FC powers our own drones that fly without GPS, without radio, and without compromise. Now, we’re bringing the same power to the hands of developers, researchers, and system integrators. 🔧 Plug-and-play with: High-speed interfaces for camera, LIDAR, and IMU Ruggedized I/O and low-latency networking Full support for ROS, PX4, and custom Linux pipelines Whether you’re building next-gen robotics, defense-grade UGVs, or intelligent drones, JETCORE-FC gives you the reliability and performance we trust in the field. 🛒 Get yours now → #Vecros #JETCORE #EdgeAI #NVIDIAJetson #Robotics #Autonomy #Drones #AI #GPSTech #DroneComputing #SpatialAI NVIDIA NVIDIA Robotics Rashree Besta prem sai RobuIN

🚀After Years of building battle-tested autonomy for drones, we’re excited to make JETCORE-FC publicly available ! Our flagship compute module along with Flight control carrier board designed for real-time perception, autonomy, and edge AI workloads. Built around NVIDIA Jetson, JETCORE-FC powers our own drones that fly without GPS, without radio, and without compromise. Now, we’re bringing the same power to the hands of developers, researchers, and system integrators. 🔧 Plug-and-play with: High-speed interfaces for camera, LIDAR, and IMU Ruggedized I/O and low-latency networking Full support for ROS, PX4, and custom Linux pipelines Whether you’re building next-gen robotics, defense-grade UGVs, or intelligent drones, JETCORE-FC gives you the reliability and performance we trust in the field. 🛒 Get yours now → #Vecros #JETCORE #EdgeAI #NVIDIAJetson #Robotics #Autonomy #Drones #AI #GPSTech #DroneComputing #SpatialAI NVIDIA NVIDIA Robotics Rashree Besta prem sai RobuIN

VECROS

17,278 views • 1 year ago

Wow. Recreating the Shawshank Redemption prison in 3D from a single video, in real time (!) Just read the MASt3R-SLAM paper and it's pretty neat. These folks basically built a real-time dense SLAM system on top of MASt3R, which is a transformer-based neural network that can do 3d reconstruction and localization from uncalibrated image pairs. The cool part is they don't need a fixed camera model -- it just works with arbitrary cameras -- think different focal lengths, sensor sizes, even handling zooming in video (FMV drone video anyone?!). If you've done photogrammetry or played with NeRFs you know that is a HUGE deal. They've solved some tricky problems like efficient point matching and tracking, plus they've figured out how to fuse point clouds and handle loop closures in real-time. Their system runs at about 15 FPS on a 4090 and produces both camera poses and dense geometry. When they know the camera calibration, they get SOTA results across several benchmarks, but even without calibration, they still perform well. What's interesting is the approach -- most recent SLAM work has built on DROID-SLAM's architecture, but these folks went a different direction by leveraging a strong 3D reconstruction prior. Seems to give them more coherent geometry, which makes sense since that's what MASt3R was designed for. For anyone who cares about monocular SLAM and 3D reconstruction, this feels like a significant step toward plug-and-play dense SLAM without calibration headaches -- perfect for drones, robots, AR/VR -- the works!

Wow. Recreating the Shawshank Redemption prison in 3D from a single video, in real time (!) Just read the MASt3R-SLAM paper and it's pretty neat. These folks basically built a real-time dense SLAM system on top of MASt3R, which is a transformer-based neural network that can do 3d reconstruction and localization from uncalibrated image pairs. The cool part is they don't need a fixed camera model -- it just works with arbitrary cameras -- think different focal lengths, sensor sizes, even handling zooming in video (FMV drone video anyone?!). If you've done photogrammetry or played with NeRFs you know that is a HUGE deal. They've solved some tricky problems like efficient point matching and tracking, plus they've figured out how to fuse point clouds and handle loop closures in real-time. Their system runs at about 15 FPS on a 4090 and produces both camera poses and dense geometry. When they know the camera calibration, they get SOTA results across several benchmarks, but even without calibration, they still perform well. What's interesting is the approach -- most recent SLAM work has built on DROID-SLAM's architecture, but these folks went a different direction by leveraging a strong 3D reconstruction prior. Seems to give them more coherent geometry, which makes sense since that's what MASt3R was designed for. For anyone who cares about monocular SLAM and 3D reconstruction, this feels like a significant step toward plug-and-play dense SLAM without calibration headaches -- perfect for drones, robots, AR/VR -- the works!

Bilawal Sidhu

704,241 views • 1 year ago

Most people will never hear this level of alpha. A guy who has made over $3 million with faceless YouTube just dropped the real process for hitting $30k per month. Not the fake "zero effort" guru stuff. The actual playbook: - Use ViewStats to find faceless channels already doing $10K + per month - Deep dive their top 10 videos (titles, thumbnails, hooks, storytelling structure) - Reverse engineer the exact formula - Outsource production on Upwork for $100-200 per video This isn’t “post once and retire.” This is building real assets that print while you sleep. While most of Crypto Twitter is still chasing 10x coins and coping... The smart operators are quietly buying proven formulas and scaling faceless cash machines with actual budgets. This is the type of high-level execution that separates the ones who make it from the ones who stay dreaming. This exact framework is what built multiple 6 and 7-figure faceless empires. If this one actually hit different… smash like and follow me. I only post this level of alpha here.

Most people will never hear this level of alpha. A guy who has made over $3 million with faceless YouTube just dropped the real process for hitting $30k per month. Not the fake "zero effort" guru stuff. The actual playbook: - Use ViewStats to find faceless channels already doing $10K + per month - Deep dive their top 10 videos (titles, thumbnails, hooks, storytelling structure) - Reverse engineer the exact formula - Outsource production on Upwork for $100-200 per video This isn’t “post once and retire.” This is building real assets that print while you sleep. While most of Crypto Twitter is still chasing 10x coins and coping... The smart operators are quietly buying proven formulas and scaling faceless cash machines with actual budgets. This is the type of high-level execution that separates the ones who make it from the ones who stay dreaming. This exact framework is what built multiple 6 and 7-figure faceless empires. If this one actually hit different… smash like and follow me. I only post this level of alpha here.

Frogify

149,154 views • 3 months ago

🚨 BREAKING: Big news in the computer vision world! 🎥 Luxonis | Robotic Vision just dropped its new OAK 4 line, and it’s a big upgrade for edge computer vision. Instead of being “just a stereo camera,” OAK 4 is a fully standalone vision computer with 52 TOPS of on-device AI. Models run locally, depth is computed locally, and no external PC or cloud pipeline is required. This is why robotics teams love it: lower latency, lower cost, fewer failure points in the field. The hardware is built for the real-world. IP67, shock-resistant, wide-FOV RGB + stereo pair, IR projection, IMU, audio, and a patent-pending calibration system that keeps depth accurate even when conditions change. But the real move is the platform. With Luxonis Hub, you can deploy models, grab telemetry, push OTA updates, or collect data when performance drifts, all from a unified interface. It turns a single device into an end-to-end edge CV system. Most customers today in robotics are groups who just want something that works: AMRs, bin-picking systems, trailer-loading robots, and ag-tech. 🤖 And they all say the same thing, the appeal isn’t raw TOPS, it’s the all-in-one simplicity that lets them scale without building custom infrastructure. Feels like the direction edge vision has been waiting for: rugged hardware + high-throughput on-device compute + a real management layer. A next step toward “plug-and-deploy” perception for robots. 🔗 Find out more here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

🚨 BREAKING: Big news in the computer vision world! 🎥 Luxonis | Robotic Vision just dropped its new OAK 4 line, and it’s a big upgrade for edge computer vision. Instead of being “just a stereo camera,” OAK 4 is a fully standalone vision computer with 52 TOPS of on-device AI. Models run locally, depth is computed locally, and no external PC or cloud pipeline is required. This is why robotics teams love it: lower latency, lower cost, fewer failure points in the field. The hardware is built for the real-world. IP67, shock-resistant, wide-FOV RGB + stereo pair, IR projection, IMU, audio, and a patent-pending calibration system that keeps depth accurate even when conditions change. But the real move is the platform. With Luxonis Hub, you can deploy models, grab telemetry, push OTA updates, or collect data when performance drifts, all from a unified interface. It turns a single device into an end-to-end edge CV system. Most customers today in robotics are groups who just want something that works: AMRs, bin-picking systems, trailer-loading robots, and ag-tech. 🤖 And they all say the same thing, the appeal isn’t raw TOPS, it’s the all-in-one simplicity that lets them scale without building custom infrastructure. Feels like the direction edge vision has been waiting for: rugged hardware + high-throughput on-device compute + a real management layer. A next step toward “plug-and-deploy” perception for robots. 🔗 Find out more here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

41,955 views • 9 months ago