Forget lidar. One single camera. Runs in real time & is open source: A streaming 3D model that reconstructs scenes live, at ~20 FPS, over long sequences. End-to-end. Optimization tricks, cleanup steps? Nope. And it beats both streaming and even some offline methods. Perception is becoming software-first. Closer to machines that see and understand the world as it unfolds. Thanks for sharing, @YinghaoXu1 📍Models: Project page: Code: Paper: —— Weekly robotics and AI insights. Subscribe free:

Mobile LiDAR (Light Detection And Ranging) system in China. On its roof, the LiDAR emits 532nm green laser light, using backscattering from airborne particles to monitor air pollution distribution.

This mobile LiDAR system scans the atmosphere with laser beams, analysing light scattered by airborne particles to measure pollution levels and map its distribution at different heights in real time.

$OUST at $43 — buy. Lidar for autonomy, robotics, and mapping. Revenue growing 40%+, fresh wins with GeoCue and GUSS, down 16% this month on profit-taking after a 50% YTD run. Street says Buy. Still losing money and lidar is a price-war market, so this is a starter position, not a core hold. But washed-out growth hardware with real deals is exactly the setup that snaps back.

Why Elon rejected LiDAR for cars while personally spearheading LiDAR development at SpaceX “LiDAR is lame. They’re all going to dump LiDAR. Mark my words” And years later, the industry is starting to realize just how massive that mistake that was Automakers spent years piling expensive sensors onto cars while Elon took the opposite path: Solve vision People acted like Elon hated LiDAR He literally spearheaded the development of SpaceX’s own LiDAR system from scratch Dragon uses LiDAR to navigate and dock with the International Space Station Because in space, LiDAR actually solves a real problem But for cars, once vision is solved, LiDAR becomes expensive, redundant hardware That became Tesla’s entire autonomy architecture: Cameras, Neural networks, Massive real-world training data........AI doing the driving And Cybercab is the purest version of that philosophy. It comes with no LiDAR or giant rooftop sensor array or a hardware circus Just cameras, onboard AI and FSD Elon chose this path more than a decade ago while almost everyone else was throwing more sensors at the problem Now Cybercab is being built with pure vision from day one Solve vision well enough...and autonomy becomes dramatically simpler, cheaper and infinitely easier to scale The industry kept building autonomy around more hardware. Elon built Tesla around better intelligence

Waymo’s giant LiDAR hardware covers the entire glass roof, while the Tesla Model Y’s glass roof is fully open, allowing for some awesome views, especially from the second row. Another benefit of computer vision and AI.

People who say LiDAR is needed for night driving should see this Waymo fuckup because it can’t see a turn in complete darkness. It did pretty terrible the first time but kudos to it for remembering and not messing it up a second time. Tesla robotaxi has never had a problem here during the night. Not any hate on Waymo, they are doing great, but clearly it isn’t because of LiDAR lol

High-resolution #dToF# #LiDAR# is bringing more spatial intelligence to the edge enabling more accurate depth perception, improved object detection, and real time decisioning for robotics, smart vehicles, and industrial automation. Discover how🔍